← OSS.Radar home

Powered by aegismemory.com · Aegis Memory repository

Agent Framework AI repositories

OSS Radar projects in the agent framework category.

NousResearch/hermes-agent

The agent that grows with you

Category
agent framework
Stars
227,094
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +3,749 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

ai ai-agent ai-agents anthropic chatgpt claude

firecrawl/firecrawl

The context API to search, scrape, and interact with the web at scale. 🔥

Category
agent framework
Stars
162,913
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +4,254 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

ai ai-agents ai-crawler ai-scraping ai-search crawler

langchain-ai/langchain

The agent engineering platform.

Category
agent framework
Stars
143,653
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +545 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals; open issue backlog is stable or shrinking

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

agents ai ai-agents anthropic chatgpt deepagents

browser-use/browser-use

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Category
agent framework
Stars
108,206
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +794 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

ai-agents ai-tools browser-automation browser-use llm playwright

DietrichGebert/ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

Category
agent framework
Stars
98,263
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +5,311 stars in 7 days; 27 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: response activity.

agent-skills ai-agents claude claude-code claude-code-plugin cursor-rules

bytedance/deer-flow

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of ta

Category
agent framework
Stars
79,519
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +1,106 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

agent agentic agentic-framework agentic-workflow ai ai-agents

shareAI-lab/learn-claude-code

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Category
agent framework
Stars
73,515
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
healthy
Maintenance risk
8/100 · high confidence

Why: +659 stars in 7 days; 18 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity

Strongest signals: push recency, contributor breadth, issue load. Risks: no pull-request review responses in 30 days. Missing inputs: release recency.

agent agent-development ai-agent claude claude-code educational

asgeirtj/system_prompts_leaks

Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor,

Category
agent framework
Stars
62,526
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +870 stars in 7 days; 79 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity

Strongest signals: push recency, commit activity, contributor breadth. Risks: maintenance is concentrated in one contributor. Missing inputs: release recency.

ai ai-agents ai-prompts anthropic chatbot chatgpt

ZhuLinsen/daily_stock_analysis

LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-f

Category
agent framework
Stars
60,478
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +782 stars in 7 days; 66 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: lifetime contributors, response activity.

a-stock ai-agent aigc llm quant quantitative-finance

zhayujie/CowAgent

Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (form

Category
agent framework
Stars
46,400
Readiness
ready (96/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
8/100 · high confidence

Why: +153 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity; open issue backlog is stable or shrinking

Strongest signals: push recency, commit activity, contributor breadth. Risks: no pull-request review responses in 30 days. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors.

ai ai-agent ai-agents chatgpt-on-wechat claude claude-code

langchain-ai/langgraph

Build resilient agents.

Category
agent framework
Stars
39,152
Readiness
ready (96/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +573 stars in 7 days; 43 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: lifetime contributors, response activity.

agents ai ai-agents chatgpt deepagents enterprise

bojieli/ai-agent-book

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

Category
agent framework
Stars
34,329
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +5,907 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, response activity.

agent agent-memory ai-agent book coding-agent context-engineering

esengine/DeepSeek-Reasonix

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

Category
agent framework
Stars
32,903
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +4,674 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

agent agent-framework ai-agent ai-coding cli coding-agent

HKUDS/Vibe-Trading

"Vibe-Trading: Your Personal Trading Agent"

Category
agent framework
Stars
30,249
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1,294 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent algorithmic-trading backtesting fintech llm mcp

FoundationAgents/MetaGPT

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Category
agent framework
Stars
69,700
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
risky
Maintenance risk
42/100 · high confidence

Why: +92 stars in 7 days; 100+ lifetime contributors

Why it may be a gem: healthy maintenance and project fundamentals; open issue backlog is stable or shrinking

Strongest signals: contributor breadth, issue load, documentation. Risks: no push in 198 days, latest release is 516 days old. Missing inputs: None.

Capped lower bounds: lifetime contributors.

agent gpt llm metagpt multi-agent

reworkd/AgentGPT

🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

Category
agent framework
Stars
36,302
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
risky
Maintenance risk
100/100 · high confidence

Why: 69 lifetime contributors

Why it may be a gem: healthy maintenance and project fundamentals; open issue backlog is stable or shrinking

Strongest signals: contributor breadth, issue load, fork interest. Risks: repository is archived, no push in 466 days, latest release is 1010 days old, 219 open issues with no maintainer issue responses in 30 days, no pull-request review responses in 30 days, no maintainer response activity in 30 days. Missing inputs: None.

agent agentgpt agents agi ai ai-agents

RightNow-AI/openfang

Open-source Agent Operating System

Category
agent framework
Stars
18,083
Readiness
needs review (71/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +12 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agents llm mcp open-source openclaw

TransformerOptimus/SuperAGI

<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

Category
agent framework
Stars
17,656
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +9 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 562 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents agi ai artificial-general-intelligence artificial-intelligence autonomous-agents

plandex-ai/plandex

Open source AI coding agent. Designed for large projects and real world tasks.

Category
agent framework
Stars
15,573
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +17 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 308 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents ai-developer-tools ai-tools cli command-line

InternLM/MindSearch

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

Category
agent framework
Stars
6,912
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 399 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-search-engine gpt llm llms multi-agent-systems perplexity-ai

TencentQQGYLab/AppAgent

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

Category
agent framework
Stars
6,844
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 506 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent chatgpt generative-ai gpt4 gpt4v llm

zhouxiaoka/autoclip

AutoClip : AI-powered video clipping and highlight generation · 一款智能高光提取与剪辑的二创工具

Category
agent framework
Stars
6,300
Readiness
needs review (59/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +56 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents ai-tools ai-video ai-video-editor auto

microsoft/TaskWeaver

The first "code-first" agent framework for seamlessly planning and executing data analytics tasks.

Category
agent framework
Stars
6,178
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
93/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: repository is archived, no push in 137 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai-agents code-interpreter copilot data-analysis llm

santifer/career-ops

Open-source AI job search: scan job portals, evaluate listings with a structured A-F rubric into a 1.0-5.0 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code,

Category
agent framework
Stars
63,168
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +774 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

ai ai-agent anthropic ats automation beginner-friendly

CherryHQ/cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

Category
agent framework
Stars
50,022
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +814 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

agent-skills ai-agent awesome-skills claude-code codex deepseek

HKUDS/nanobot

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

Category
agent framework
Stars
46,748
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +269 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

agent-framework ai-agent ai-agents chatbot chatops discord-bot

hugohe3/ppt-master

AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support

Category
agent framework
Stars
43,792
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +1,603 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity

Strongest signals: push recency, commit activity, contributor breadth. Risks: maintenance is concentrated in one contributor. Missing inputs: None.

Capped lower bounds: 30-day commits.

ai-agent aippt office powerpoint powerpoint-generation ppt

agentscope-ai/QwenPaw

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Category
agent framework
Stars
34,238
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: 100+ commits in 30 days; 100+ lifetime contributors

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

agent agent-harness agentscope ai-agent ai-agents chatbot

Gitlawb/openclaude

runs anywhere. uses anything

Category
agent framework
Stars
30,563
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +110 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-tools cli coding

googleworkspace/cli

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

Category
agent framework
Stars
30,257
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +146 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills ai-agent automation cli discovery-api gemini-cli-extension

jackwener/OpenCLI

Make Any Website into CLI & Use your logged-in browser by AI agent.

Category
agent framework
Stars
27,876
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +362 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-agents ai-tools browser-automation browser-use cli

nocobase/nocobase

NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of production-proven infrastructure and a WYSIWYG no

Category
agent framework
Stars
23,588
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +70 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

admin-dashboard ai-agent ai-agents ai-assistant ai-tools airtable

teableio/teable

✨ AI Spreadsheet for Business

Category
agent framework
Stars
21,633
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +33 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent airtable airtable-alternative app-builder database internal-tool

trycua/cua

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

Category
agent framework
Stars
21,024
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +202 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai-agent apple computer-use computer-use-agent containerization

TencentCloud/TencentDB-Agent-Memory

TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, s

Category
agent framework
Stars
17,525
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +7,708 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai-agent embedding llm local-first long-term-memory

browser-use/browser-harness

Browser Harness | Self-healing harness that enables LLMs to complete any task.

Category
agent framework
Stars
16,559
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +165 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent browser-agent browser-automation browser-use browser-use-box browser-use-cloud

fathah/hermes-desktop

Desktop Companion for Hermes Agent

Category
agent framework
Stars
13,774
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +115 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent autonomous-agents chatbot hermes llm

lsdefine/GenericAgent

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

Category
agent framework
Stars
13,691
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +65 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent automation autonomous-agent browser-automation claude computer-control

waooAI/waoowaoo

首家工业级全流程 AI 影视生产平台。Industry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows.

Category
agent framework
Stars
13,489
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +65 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-agents automation film-production generative-ai short-drama

e2b-dev/E2B

Open-source, secure environment with real-world tools for enterprise-grade agents.

Category
agent framework
Stars
13,290
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +80 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai ai-agent ai-agents code-interpreter copilot

opensandbox-group/OpenSandbox

Secure, Fast, and Extensible Sandbox runtime for AI agents.

Category
agent framework
Stars
12,395
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +128 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-infra kubernetes sandbox

walkinglabs/learn-harness-engineering

Harness engineering beginner tutorial, from 0 to 1

Category
agent framework
Stars
11,074
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +196 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic agentic-ai ai ai-agent harness

frankbria/ralph-claude-code

Autonomous AI development loop for Claude Code with intelligent exit detection

Category
agent framework
Stars
9,587
Readiness
ready (78/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +16 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-agents ai-development ai-development-tools claude-code

presenton/presenton

Open-Source AI Presentation Generator and API (Gamma, Canva, Beautiful AI, Decktopus, Presentations AI Alternative)

Category
agent framework
Stars
9,427
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +162 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-presentation api gamma powerpoint-automation powerpoint-free

citrolabs/ego-lite

The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero conf

Category
agent framework
Stars
9,238
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2,271 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills ai-agent automation browser browser-automation claude-code

EvoMap/evolver

The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

Category
agent framework
Stars
8,949
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +46 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a agent-evolution agent-framework agent-protocol ai-agent auditable-ai

Narcooo/inkos

Story Creation AI Agent for novel, scripts, translation, interactive games, and IP content

Category
agent framework
Stars
8,811
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +275 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-game ai-writing chinese-novel creative-writing-ai

simonlin1212/a-stock-data

A股全栈数据工具包 · 10层架构 · 43端点(含3官方备胎) · 15数据源 · 行情/研报/资金面/筹码/公告/打板/ETF期权/舆情互动全覆盖+备用源降级 | China A-Share full-stack data toolkit (43 endpoints)

Category
agent framework
Stars
8,448
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +273 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a-share ai-agent ai-skill china-stocks claude-code financial-data

jo-inc/camofox-browser

Stealth headless browser for AI agents — bypass Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwright replacement.

Category
agent framework
Stars
8,403
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +185 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent anti-bot antidetect-browser automation bot-detection browser-automation

omnigent-ai/omnigent

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and c

Category
agent framework
Stars
8,303
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +325 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-governance agent-orchestration agents ai ai-agent

GetBindu/Bindu

Bindu: The identity, communication, and payments layer for AI agents.

Category
agent framework
Stars
8,228
Readiness
ready (78/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +250 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a agent-communication agent-orchestration ai-agent autonomous-agents eu-ai-act

adongwanai/AgentGuide

https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成

Category
agent framework
Stars
7,966
Readiness
ready (78/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +334 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agenticrag ai-agent crewai graphrag grpo interview

ChatLab/ChatLab

Local-first chat history analyzer with AI. | 本地优先的 AI 聊天记录分析工具

Category
agent framework
Stars
7,117
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +65 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-agents chat-analyzer chat-history data-analysis data-visualization

crestalnetwork/intentkit

IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.

Category
agent framework
Stars
6,506
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agentic ai ai-agent ai-agent-framework blockchain

SWE-agent/mini-swe-agent

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

Category
agent framework
Stars
6,294
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +133 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic-ai agentic-ai-cli ai ai-agent textual

UfoMiao/zcf

Zero-Config Code Flow for Claude code & Codex

Category
agent framework
Stars
6,076
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +9 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai ai-agent bmad-method ccr claude

KunAgent/Kun

Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI.

Category
agent framework
Stars
5,746
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-workflow ai-agent ai-assistant ai-design automation coding-agent

KimYx0207/AI-Coding-Guide-Zh

Claude Code + OpenClaw + Codex 中文教程 | 39篇完整教程 + 1张速查卡 | 80万+内容量 | 1500+实操示例 | AI Coding / Agent 三线学习路径

Category
agent framework
Stars
5,596
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +89 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-assistant ai-tutorial anthropic chinese claude

Q00/ouroboros

Agent OS: Stop prompting. Start specifying.

Category
agent framework
Stars
5,340
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +109 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-os ai-agent llm-orchestration llm-runtime python

worldwonderer/oh-story-claudecode

网文/小说写作 skill 包，覆盖长篇与短篇网络小说的扫榜、拆文、写作、去AI味、封面图全流程 | An all-in-one skill pack for long- and short-form web fiction.

Category
agent framework
Stars
5,214
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +362 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-writing chinese-novel claude-code claude-skills creative-writing

chuspeeism/dashi-ppt-skill

An AI-agent skill that generates browser-editable presentations from multiple visual themes, exportable to HTML, PDF, and PPTX.

Category
agent framework
Stars
4,863
Readiness
ready (78/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +396 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skill ai-agent ai-ppt claude claude-code dashial

iflytek/skillhub

Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.

Category
agent framework
Stars
4,855
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +29 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agent ai-governance ai-infrastructure ai-orchestration audit-log

EvoScientist/EvoScientist

🔬 Harness Vibe Research with Self-evolving AI Scientists

Category
agent framework
Stars
4,542
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +94 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai4science multi-agent-system vibe-research

Agenta-AI/agenta

Agenta is a workspace where you and your team build agents and automations.

Category
agent framework
Stars
4,446
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +43 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-builder agent-observability agent-orchestration agent-workspace agentic-ai ai-agent

AlexAnys/awesome-openclaw-usecases-zh

🇨🇳 OpenClaw中文用例大全 | 50个真实场景 | 国内特色 + 海外案例的国内适配 | 自动化办公·内容创作·运维·AI助理·知识管理 | 新手友好

Category
agent framework
Stars
4,411
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +9 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-assistant ai-automation ai-tools automation awesome-list

WeThinkIn/AIGC-Interview-Book

【三年面试五年模拟】AIGC/LLM/AI Agent算法工程师面试秘籍。涵盖AIGC、LLM大模型、AI Agent、具身智能、传统深度学习、自动驾驶、机器学习、计算机视觉、自然语言处理、强化学习、大数据挖掘、世界模型、元宇宙、AGI等AI行业面试笔试干货经验与核心知识。

Category
agent framework
Stars
4,269
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +54 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent aigc computer-vision deep-learning interview interview-preparation

killop/anything_about_game

A wonderful list of Game Development resources.

Category
agent framework
Stars
3,997
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

2d-game-framework ai-agent awesome-list csharp ecs ecs-libraries

dromara/liteflow

Lightweight, fast, stable, programmable component-based rule engine — where AI Agents orchestrate just like ordinary components. Uniquely designed DSL: component reuse, sync/async & dynamic orchestrat

Category
agent framework
Stars
3,830
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +13 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-agents component dsl flow-engine hot-reload

1186258278/OpenClawChineseTranslation

🦞 OpenClaw (Clawdbot/Moltbot) 汉化版 - 开源个人 AI 助手中文版 | Claude/ChatGPT LLM 接入 | WhatsApp/Telegram/Discord 多平台 | 每小时自动同步 | CLI + Dashboard 全中文 | 全流程搭建教程，以及排错指南！

Category
agent framework
Stars
3,815
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +12 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-assistant chatbot chinese claude-ai clawd

memodb-io/Acontext

Agent Skills as a Memory Layer

Category
agent framework
Stars
3,663
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +73 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-development-kit agent-observability ai-agent anthropic context-data-platform

CommandCodeAI/command-code

Command Code AI

Category
agent framework
Stars
3,637
Readiness
ready (77/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +70 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent anthropic cli coding-agent command-code

nextlevelbuilder/goclaw

GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at scale without compromising on safety.

Category
agent framework
Stars
3,516
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +23 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-orchestration ai-agent ai-gateway anthropic chatbot discord-bot

thedaviddias/Front-End-Checklist

🗂 The essential checklist for modern web development, for humans and AI agents

Category
agent framework
Stars
73,460
Readiness
needs review (46/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
watch
Maintenance risk
18/100 · high confidence

Why: +90 stars in 7 days; 100+ lifetime contributors

Why it may be a gem: open issue backlog is stable or shrinking

Strongest signals: contributor breadth, issue load, documentation. Risks: recent commit cadence is 0/7.2 of its monthly baseline. Missing inputs: None.

Capped lower bounds: lifetime contributors.

ai-agent ai-agents checklist css front-end-developer-tool front-end-development

browser-use/web-ui

🖥️ Run AI Agent in your browser.

Category
agent framework
Stars
16,268
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +13 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent browser-automation browser-use-box cloud-browser

mahseema/awesome-ai-tools

A curated list of Artificial Intelligence Top Tools

Category
agent framework
Stars
5,899
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
0/100 · low confidence

Why: +72 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-agents ai-assistant ai-tools ai-tools-list

filipecalegario/awesome-vibe-coding

A curated list of vibe coding references, collaborating with AI to write code.

Category
agent framework
Stars
5,092
Readiness
needs review (47/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +28 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-agents ai-coding-assistant ai-coding-tools awesome awesome-list

Integuru-AI/Integuru

The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.

Category
agent framework
Stars
4,749
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +96 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agents ai-agent ai-agents api apis

cbamls/AI_Tutorial

大厂发布的AI落地实践、顶尖实验室的最新论文、工业界的真实踩坑记录

Category
agent framework
Stars
3,688
Readiness
needs review (45/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: limited evidence; inspect maintenance signals before adopting

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent artificial-intelligence artificial-intelligence-algorithms llm machine-learning recommender-systems

didilili/ai-agents-from-zero

🚀 2026 最系统的 AI Agent 速成指南｜智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化

Category
agent framework
Stars
3,564
Readiness
needs review (66/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +316 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework agentic-ai ai-agent aigc coze

Intelligent-Internet/ii-agent

II-Agent: a new open-source framework to build and deploy intelligent agents

Category
agent framework
Stars
3,375
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
19/100 · low confidence

Why: +11 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 116 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic-ai ai ai-agent ai-agent-framework llm

nexu-io/nexu

The simplest desktop client for OpenClaw 🦞 — bridge your Agent to WeChat, Feishu, Slack & Discord in one click. Works with Claude Code, Codex & any LLM. BYOK, Oauth, local-first, chat from your phone

Category
agent framework
Stars
3,247
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
17/100 · low confidence

Why: +12 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 103 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent byok claude claude-code clawbot codex

isjiamu/gzh-design-skill

把 Markdown 一键排成可直接粘进公众号编辑器的精致 HTML —— 6 套精选主题 + 主题生成器 + 双关卡校验。An AI-agent skill that turns Markdown into paste-ready WeChat article HTML.

Category
agent framework
Stars
2,905
Readiness
needs review (66/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skill ai-agent claude-code codex cursor gongzhonghao

ahmedeltaher/Android-MVVM-Architecture-Android-Voice-AI-SDK

Voice AI SDK is a reusable Android library that gives any app a full voice-driven AI conversation pipeline in minutes. Voice Assistant + Android Voide AI + SDK + MVVM + Kotlin

Category
agent framework
Stars
2,573
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent android android-mvvm-architechture mvvm mvvm-android

BAAI-Agents/Cradle

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation,

Category
agent framework
Stars
2,560
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 638 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-agents-framework computer-control cradle foundation-agent

ciembor/agent-rules-books

AGENTS.md rules / skills for AI coding agents: Codex, Cursor & Claude Code. Inspired by Clean Code, Refactoring, DDD, Clean Architecture and DDIA programming books.

Category
agent framework
Stars
2,438
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +91 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-rules agent-skills agents-md ai-agent ai-skills claude-code

lmnr-ai/index

The SOTA Open-Source Browser Agent for autonomously performing complex tasks on the web

Category
agent framework
Stars
2,397
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
100/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: repository is archived, no push in 424 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent browser-agent claude-3-7-sonnet gemini-pro llm

EgoAlpha/prompt-in-context-learning

Awesome resources for in-context learning and prompt engineering: Mastery of the LLMs such as ChatGPT, GPT-3, and FlanT5, with up-to-date and cutting-edge updates.

Category
agent framework
Stars
2,247
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +3 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent chain-of-thought chatbot chatgpt chatgpt-api cot

jim-schwoebel/awesome_ai_agents

🤖 A comprehensive list of 1,500+ resources and tools related to AI agents.

Category
agent framework
Stars
1,920
Readiness
needs review (60/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
0/100 · low confidence

Why: +11 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-based-modeling agentic agentic-ai agentic-workflow agents ai

czl9707/build-your-own-openclaw

A step-by-step guide to build your own AI agent.

Category
agent framework
Stars
1,832
Readiness
ready (77/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent build-your-own-x llm python tutorial

AidanPark/openclaw-android

Run OpenClaw on Android with a single command — no proot, no Linux

Category
agent framework
Stars
1,727
Readiness
needs review (68/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent android homelab low-power nodejs

stakpak/agent

Ship your code, on autopilot. An open source agent that lives on your machines 24/7 and keeps your apps running. 🦀

Category
agent framework
Stars
1,721
Readiness
ready (72/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai-agent autonomous-agent devops devops-agents devtool

NarratorAI-Studio/narrator-ai-cli-skill

AI 解说大师 — Agent skill；封装 narrator-ai-cli 供 Claude/Codex 等工具调用

Category
agent framework
Stars
1,581
Readiness
ready (73/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +155 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills ai-agent ai-video claude-code claude-code-skill content-creation

Core-Mate/OpenGUI

OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.

Category
agent framework
Stars
1,482
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +219 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

accessibility agent-framework ai-agent android android-accessibility android-agent

agi-inc/agent-protocol

Common interface for interacting with AI agents. The protocol is tech stack agnostic - you can use it with any framework for building agents.

Category
agent framework
Stars
1,457
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 486 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai ai-agent api auto-gpt gpt-4

oxylabs/browser-agent-py

AI Browser Agent is an advanced Browser AI tool developed by Oxylabs AI Studio that automates real user browsing tasks using natural language instructions.

Category
agent framework
Stars
1,425
Readiness
high risk (37/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
21/100 · low confidence

Why: +10 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 127 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-agents ai-browser ai-studio browser-agent browser-ai

MiniMax-AI/OpenRoom

A browser-based desktop where AI Agent operates every app through natural language.

Category
agent framework
Stars
1,244
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent browser desktop micro-frontend minimax natural-language

DeepMyst/Mysti

AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate solutions, and synthesize the best approach for your code.

Category
agent framework
Stars
1,117
Readiness
needs review (68/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic-ai agentic-coding agentic-workflow agents ai

moltlaunch/cashclaw

An autonomous agent that takes work, does work, gets paid, and gets better at it.

Category
agent framework
Stars
1,091
Readiness
needs review (59/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
24/100 · low confidence

Why: +5 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 146 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent autonomous-agent base claude llm marketplace

vercel-labs/knowledge-agent-template

Open source file-system and knowledge based agent template. Build AI agents that stay up to date with your knowledge base

Category
agent framework
Stars
967
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai-agent chatbot file-system knowledge-base nuxt

agenmod/immortal-skill

♾️ 开源数字永生框架 — 从聊天记录蒸馏任何人的七维数字分身。支持微信/飞书/iMessage/Telegram等12+平台，7种角色模板，对齐 OpenClaw Soul Spec 标准。一行指令让你的AI学会蒸馏。

Category
agent framework
Stars
961
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
19/100 · low confidence

Why: +18 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 114 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills ai-agent chatbot cursor digital-immortality digital-twin

oxylabs/ai-scraper-py

AI Scraper is a powerful scraping tool and scrape agent built to automate data extraction with unmatched precision. Ideal for scalable AI scraping tasks across diverse web sources, this tool simplifie

Category
agent framework
Stars
936
Readiness
high risk (37/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
21/100 · low confidence

Why: +31 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 127 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-grounding ai-scraper ai-scraping ai-search ai-studio

ythx-101/x-tweet-fetcher

Fetch X/Twitter tweets, replies, timelines, and articles without login or API keys — field tool for AI agents.

Category
agent framework
Stars
924
Readiness
needs review (70/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +30 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-tools ai-agent automation no-api osint scraper

aiflowy/aiflowy

AIFlowy is an enterprise-grade AI application development platform based on Java, comparable to products like Dify and Coze.

Category
agent framework
Stars
902
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai ai-agent aiflowy coze dify langchain4j

joeynyc/hermes-hud

TUI consciousness monitor for Hermes

Category
agent framework
Stars
893
Readiness
needs review (70/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent dashboard neofetch python terminal textual

microsoft/WindowsAgentArena

Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.

Category
agent framework
Stars
885
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
19/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 116 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic ai ai-agent ai-benchmark ai-research computer

CryptoDmitry/hermes-agent-control-room

Control Room-first template for managing Hermes agents from one VPS agent to specialist teams and orchestrated workflows

Category
agent framework
Stars
869
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +7 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-control-room ai-agent ai-agents ai-agents-framework claude-code claude-code-cli

daggerhashimoto/openclaw-nerve

Real-time web cockpit for OpenClaw: voice conversations, agent automated kanban board, workspace/file control, sub-agent sessions, inline charts, and usage visibility.

Category
agent framework
Stars
861
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent claude clawbot dashboard mission-control open-source

Shanyin-ai/shanyin-screenwriting-master

山音超级编剧大师——由 @山音 设计的全格式影视编剧技能。 覆盖从1-3分钟概念超短片到90分钟电影长片、多集剧集的全格式剧本创作。 支持四种格式：概念超短片（how-to-tell/what-if）、5-10分钟叙事短片、90分钟长片（商业/文艺）、多集剧集。 覆盖从人物设计、结构大纲、场景拆解、到完整剧本写作的全流程。

Category
agent framework
Stars
840
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
21/100 · low confidence

Why: +66 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 128 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent claude-ai claude-skills screenwriting skills

context-machine-lab/sleepless-agent

🤖 24/7 AI agent that maximizes Claude Code Pro usage via Slack. Auto-processes tasks, manages isolated workspaces, creates Git commits/PRs, and optimizes day/night usage thresholds.

Category
agent framework
Stars
826
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
22/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 132 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent anthropic automation autonomous-agents claude claude-code

Canner/vulcan-sql

Data API Framework for AI Agents and Data Apps

Category
agent framework
Stars
793
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 767 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent analytics api-builder bigquery clickhouse

eli-labz/Third-Eye

A production-grade OSINT platform that provides situational awareness across multiple intelligence domains.

Category
agent framework
Stars
789
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent geospatial maven-smart-system palantir

hosenur/portal

Mobile first batteries included web ui for sst/opencode. Git integration, in browser terminal, isolated workspaces.

Category
agent framework
Stars
786
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +9 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-agents opencode

regent-vcs/re_gent

Version-Control for AI coding agents.

Category
agent framework
Stars
782
Readiness
needs review (67/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent claude-code developer-tools devtools golang version-control

litanlitudan/skyagi

SkyAGI: Emerging human-behavior simulation capability in LLM

Category
agent framework
Stars
777
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1051 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent aigc langchain language-model llm

dzcmemory-web/bazi-ziwei-skill

AI 八字 + 紫微斗数排盘与综合印证 Skill：算法精准排盘（不靠 LLM 猜），三种分析模式，一键生成水墨风 HTML 命盘海报。兼容 Claude / Codex / Cursor / Workbuddy 等 SKILL.md Agent。

Category
agent framework
Stars
775
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +22 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent bazi bazi-suanming chinese-astrology claude-skill fortune-telling

answeryt/Jumping-Agent-platform

Build your own AI agent through gameplay.

Category
agent framework
Stars
770
Readiness
ready (74/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic-workflow ai-agent platform workflow

4ier/neo

Turn any web app into an API. Chrome extension captures browser traffic, auto-generates schemas, lets AI replay APIs directly. No official API needed.

Category
agent framework
Stars
748
Readiness
high risk (41/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
17/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 101 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent api-discovery browser-automation chrome-extension web-scraping

guoguo-tju/agent_java_offer

公开的 Java 后端 / AI Agent / 系统设计 / 算法面试复习资料库

Category
agent framework
Stars
732
Readiness
needs review (47/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
18/100 · low confidence

Why: +10 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 106 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent algorithms backend interview-prep java langgraph

OtterMind/youclaw

🦞 Your AI Personal Assistant. An intelligent assistant with memory, skills, and scheduled tasks that truly understands you . Helping you tackle everything in work and life.

Category
agent framework
Stars
723
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
20/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 118 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent claude claude-code openclaw

AaronWong1999/hermesclaw

Run Hermes Agent and OpenClaw on the same WeChat account

Category
agent framework
Stars
709
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent chatbot clawbot dual-agent hermes-agent ilink

AlexAnys/openclaw-feishu

飞书插件 × OpenClaw 保姆级配置指南 & 社区支持 （0328 - 更新飞书cli调用指南，增加 API 耗尽根因排查、Lark Webhook 内网穿透方案）

Category
agent framework
Stars
691
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
22/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 130 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent channel-plugin chatbot clawdbot feishu lark

nexu-io/motion-anything

✨ The agentic motion layer — an open-source, chat-native motion engine. Describe the feeling; your AI ships the animation.

Category
agent framework
Stars
658
Readiness
ready (73/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent animation claude design-tools figma-motion-alternative motion-design

Arvincreator/project-golem

OS-level autonomous AI agent with long-term memory, multi-agent coordination, Titan Chronos scheduler & Moltbot Social Core

Category
agent framework
Stars
636
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent autonomous-agents chatbot discord-bot golem long-term-memory

51bitquant/ai-hedge-fund-crypto

AI-Hedge-Fund for Crypto 🚀 AI-powered hedge fund for cryptocurrency trading, leveraging LLM agents for intelligent decision-making.

Category
agent framework
Stars
616
Readiness
needs review (62/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 336 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-trading ai-trading-agent algorithmic-trading backtesting crypto-trading

AgentTeam-TaichuAI/ScienceClaw

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better

Category
agent framework
Stars
604
Readiness
high risk (42/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +39 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent bioinformatics data-analysis docker drug-discovery fastapi

smallnest/goclaw

An open-source AI assistant framework like openclaw

Category
agent framework
Stars
601
Readiness
needs review (59/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
22/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 133 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-agents llm openclaw openclaw-skills

normal-computing/fuji-web

Fuji is an AI agent that lives in your browser's sidepanel. You can now get tasks done online with a single command!

Category
agent framework
Stars
597
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 214 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent browser-extension gpt llm react

velobase/velobase-harness

All AI developers deserve to get paid. Turn your AI prototype into a paid SaaS with open-source infrastructure for usage billing, payments, attribution, affiliates, anti-abuse, and deployment.

Category
agent framework
Stars
592
Readiness
needs review (64/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-saas billing monetization nextjs nextjs-template

husu/loom

一个写接口文档的AI Agent。支持使用Vibe coding 的方式，编写接口文档，同时自带友好的文档查看工具与接口Mock工具

Category
agent framework
Stars
581
Readiness
high risk (32/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent sdd

LeoYeAI/openclaw-auto-dream

Automatic memory consolidation for OpenClaw agents — like sleep for your AI. Powered by MyClaw.ai

Category
agent framework
Stars
548
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
21/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 129 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent auto-dream llm memory memory-management myclaw

ishandutta2007/Velocity

🚀🪐🌕🌑☄️🛸 Opensource equivalent of Google's Antigravity/Claude Code/Cursor

Category
agent framework
Stars
545
Readiness
needs review (63/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-editor anti-gravity antigravity antigravity-ai antigravity-ide

oxbshw/LLM-Agents-Ecosystem-Handbook

One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools.

Category
agent framework
Stars
541
Readiness
needs review (71/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-agents fine-tuning finetuning-llms freamework

Light0305/Light-skills

An AI workflow skill pack for research, competitions, and innovation projects.

Category
agent framework
Stars
512
Readiness
ready (74/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

academic-writing agent-skills ai-agent ai-skills claude-code codex

hoolulu/deep-research

深度调研报告生成 Skill — 一条命令，十分钟出券商级深度调研报告 / Professional deep research report generation Skill · Supports 19 languages

Category
agent framework
Stars
500
Readiness
needs review (68/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent chinese deep-research intelligence-report market-research multi-language

decolua/9remote

📱 Terminal in Your Pocket — Control Claude Code, Codex, Gemini CLI & your Mac/Linux/Windows from any phone or browser. Vibe coding from anywhere. Alternative to MobileCLI, Claude Remote, vibe-remote,

Category
agent framework
Stars
493
Readiness
high risk (40/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
18/100 · low confidence

Why: +20 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 109 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-workflow ai-agent claude-code claude-remote codex coding-agent

AIScientists-Dev/Flowtrace

Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.

Category
agent framework
Stars
485
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills agentic-ai ai ai-agent ai-agents anthropic

AmeNetwork/aser

Aser is a lightweight, self-assembling AI Agent frame.

Category
agent framework
Stars
471
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
18/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 108 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a-protocol agent agents ai ai-agent ai-memory

baidu-baige/LoongFlow

LoongFlow is an expert-grade Agent framework for Loop Engineering. Through a Plan-Execute-Summary loop and structured experiential memory, it enables AI to continuously think, execute, reflect, and ev

Category
agent framework
Stars
468
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
20/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 120 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai ai-agent baidu discovery evolutionary-algorithms

AgentSkillOS/SkillAnything

Making ANY Software Skill-Native -- Auto-generate production-ready AI Agent Skills for Claude Code, OpenClaw, Codex, and more.

Category
agent framework
Stars
461
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
21/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 123 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-native ai-agent ai-skills automation claude-code cli-anything

openvort/openvort

Open-source AI Employee Platform — Create AI employees that collaborate with your real team in WeCom, DingTalk, and Feishu, just like hiring a few more colleagues.

Category
agent framework
Stars
460
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
17/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 102 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-employee chatbot enterprise llm openvort

HKUDS/CatchMe

"CatchMe: Make Your AI Agents Truly Personal"

Category
agent framework
Stars
458
Readiness
needs review (62/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +29 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent clawdbot-plugin llm recall-ai retrieval-systems screen-recorder

nexu-io/open-design

🎨 The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTM

Category
agent framework
Stars
84,405
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +1,509 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

agent-skills ai-agents ai-design byok claude-code-for-design claude-design

daytonaio/daytona

Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code

Category
agent framework
Stars
72,023
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
watch
Maintenance risk
26/100 · high confidence

Why: 100+ lifetime contributors

Why it may be a gem: limited evidence; inspect maintenance signals before adopting

Strongest signals: push recency, contributor breadth, issue load. Risks: recent commit cadence is 0/20.0 of its monthly baseline, no pull-request review responses in 30 days. Missing inputs: None.

Capped lower bounds: lifetime contributors.

agentic-workflow ai ai-agents ai-runtime ai-sandboxes code-execution

microsoft/ai-agents-for-beginners

18 Lessons to Get Started Building AI Agents

Category
agent framework
Stars
71,547
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +722 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals; open issue backlog is stable or shrinking

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: release recency.

Capped lower bounds: 30-day commits.

agentic-ai agentic-framework agentic-rag ai-agents ai-agents-framework autogen

code-yeongyu/oh-my-openagent

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

Category
agent framework
Stars
67,460
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +534 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

ai ai-agents anthropic chatgpt claude claude-skills

ruvnet/ruflo

🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, R

Category
agent framework
Stars
67,298
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +619 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity

Strongest signals: push recency, commit activity, contributor breadth. Risks: maintenance is concentrated in one contributor. Missing inputs: None.

Capped lower bounds: 30-day commits, response activity.

agentic-ai agentic-framework agentic-workflow agents ai-agents ai-assistant

shanraisshan/claude-code-best-practice

from vibe coding to agentic engineering - practice makes claude perfect

Category
agent framework
Stars
64,147
Readiness
ready (79/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
healthy
Maintenance risk
16/100 · high confidence

Why: +328 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, issue load. Risks: no pull-request review responses in 30 days, no maintainer response activity in 30 days. Missing inputs: release recency.

Capped lower bounds: 30-day commits.

agentic-ai agentic-coding agentic-engineering agentic-workflow ai ai-agents

crewAIInc/crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Category
agent framework
Stars
56,757
Readiness
ready (96/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +324 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

agents ai ai-agents aiagentframework llms

agno-agi/agno

Build, run, and manage agent platforms.

Category
agent framework
Stars
41,620
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +95 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

agents ai ai-agents developer-tools python

stablyai/orca

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.

Category
agent framework
Stars
39,662
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +5,127 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

ade agent-ide ai-agents claude-code cli codex

wshobson/agents

Multi-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLI

Category
agent framework
Stars
38,600
Readiness
ready (79/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +198 stars in 7 days; 10 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, contributor breadth, issue load. Risks: None identified. Missing inputs: release recency.

agent-skills agentic-ai agents ai-agents anthropic automation

Yeachan-Heo/oh-my-claudecode

Teams-first Multi-agent orchestration for Claude Code

Category
agent framework
Stars
38,423
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +208 stars in 7 days; 60 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity

Strongest signals: push recency, commit activity, contributor breadth. Risks: maintenance is concentrated in one contributor. Missing inputs: None.

Capped lower bounds: lifetime contributors, response activity.

agentic-coding ai-agents automation claude claude-code multi-agent-systems

ashishpatel26/500-AI-Agents-Projects

The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries. It showcases practical applications and provides links to open-source projects for implementation, i

Category
agent framework
Stars
35,987
Readiness
ready (73/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +492 stars in 7 days; 11 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, contributor breadth, issue load. Risks: maintenance is concentrated in one contributor. Missing inputs: release recency.

Capped lower bounds: response activity.

ai-agents genai

JCodesMore/ai-website-cloner-template

Clone any website with one command using AI coding agents

Category
agent framework
Stars
31,177
Readiness
needs review (70/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +459 stars in 7 days; 7 lifetime contributors

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: maintenance is concentrated in one contributor. Missing inputs: None.

ai ai-agents ai-tools automation boilerplate claude

MadsLorentzen/ai-job-search

The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

Category
agent framework
Stars
30,706
Readiness
ready (100/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1,760 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents career claude-code cover-letter cv

nanocoai/nanoclaw

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs direct

Category
agent framework
Stars
30,465
Readiness
ready (99/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +63 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-assistant claude-code claude-skills openclaw

Fincept-Corporation/FinceptTerminal

FinceptTerminal is a modern finance application offering advanced market analytics, investment research, and economic data tools, designed for interactive exploration and data-driven decision-making i

Category
agent framework
Stars
29,980
Readiness
ready (78/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +617 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents algorithmic-trading bloomberg-terminal cpp finance financial-markets

VoltAgent/awesome-agent-skills

A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.

Category
agent framework
Stars
29,791
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +466 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills ai-agents antigravity-skills awesome awesome-list awesome-lists

CloakHQ/CloakBrowser

Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.

Category
agent framework
Stars
29,730
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +269 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents anti-detect antidetect-browser bot-detection browser-automation captcha-bypass

chroma-core/chroma

Search infrastructure for AI

Category
agent framework
Stars
28,975
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +60 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai ai-agents database rust rust-lang

herdrdev/herdr

the runtime your coding agents live on

Category
agent framework
Stars
25,617
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2,588 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-orchestration ai ai-agents claude-code cli

enescingoz/awesome-n8n-templates

280+ free n8n automation templates — ready-to-use workflows for Gmail, Telegram, Slack, Discord, WhatsApp, Google Drive, Notion, OpenAI, and more. AI agents, RAG chatbots, email automation, social m

Category
agent framework
Stars
24,523
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +226 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-automation automation automation-templates awesome awesome-list

letta-ai/letta

Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

Category
agent framework
Stars
24,148
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +110 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents llm llm-agent

VoltAgent/awesome-claude-code-subagents

A collection of 100+ specialized Claude Code subagents covering a wide range of development use cases

Category
agent framework
Stars
24,111
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +203 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent-framework ai-agent-tools ai-agents awesome awesome-list claude

dolthub/dolt

Dolt – Git for Data

Category
agent framework
Stars
24,107
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +86 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-memory agent-memory-server ai-agents ai-database data-version-control data-versioning

NirDiamant/GenAI_Agents

50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.

Category
agent framework
Stars
23,680
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +107 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai agents ai ai-agents autonomous-agents genai

NVIDIA/NemoClaw

Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

Category
agent framework
Stars
22,088
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +86 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents hermes nvidia openclaw openshell sandboxing

vxcontrol/pentagi

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

Category
agent framework
Stars
21,704
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +290 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-security-tool anthropic autonomous-agents golang gpt

NirDiamant/agents-towards-production

End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.

Category
agent framework
Stars
21,257
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +39 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework agentic-ai agents ai-agents deployment

google/adk-python

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Category
agent framework
Stars
21,038
Readiness
ready (96/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +81 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic agentic-ai agents agents-sdk ai

kortix-ai/suna

The open-source AI Management System

Category
agent framework
Stars
20,083
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +32 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents llm

hummingbot/hummingbot

Open source software that helps you create and deploy high-frequency crypto trading bots

Category
agent framework
Stars
19,370
Readiness
ready (98/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +87 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents algotrading arbitrage backtesting binance bitcoin

KKKKhazix/khazix-skills

数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents

Category
agent framework
Stars
19,359
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +501 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills ai-agents claude claude-code codex developer-tools

jnMetaCode/agency-agents-zh

🎭 267 个即插即用的 AI 专家角色 — 支持 Hermes Agent/Claude Code/Cursor/Copilot 等 18 种工具，覆盖工程/设计/营销/金融等 20 个部门。含 52 个中国市场原创智能体（小红书/抖音/微信/飞书/钉钉等）。搭配编排器 agency-orchestrator，一句话即可让多位专家按 DAG 自动协作。

Category
agent framework
Stars
18,958
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +359 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agency-orchestrator agent-definitions ai-agents ai-roles chinese claude

emcie-co/parlant

Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.

Category
agent framework
Stars
18,235
Readiness
ready (75/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +19 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-alignment customer-service customer-success gemini genai

nesquena/hermes-webui

Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!

Category
agent framework
Stars
17,083
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +307 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai-agents hermes hermes-agent nous-research

rowboatlabs/rowboat

Open-source AI coworker, with memory

Category
agent framework
Stars
17,022
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +113 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents agents-sdk ai ai-agents ai-agents-automation chatgpt

cft0808/edict

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

Category
agent framework
Stars
16,338
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +42 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-orchestration autonomous-agents claude dashboard kanban

ag-ui-protocol/ag-ui

AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.

Category
agent framework
Stars
15,180
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +99 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ag-ui-protocol agent-frontend agent-ui agentic-workflow ai-agents

n8n-io/self-hosted-ai-starter-kit

The Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secure, self-hosted AI workflows.

Category
agent framework
Stars
15,159
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +27 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents low-code self-hosted starter-kit

earthtojake/text-to-cad

A library of agent skills for CAD, CAE and CAM

Category
agent framework
Stars
13,048
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1,004 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai-agents cad mechanical-engineering robotics step

BloopAI/vibe-kanban

Get 10X more out of Claude Code, Codex or any coding agent

Category
agent framework
Stars
27,700
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
watch
Maintenance risk
43/100 · high confidence

Why: +96 stars in 7 days; 61 lifetime contributors

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: contributor breadth, issue load, documentation. Risks: no push in 105 days, recent commit cadence is 0/20.0 of its monthly baseline, no pull-request review responses in 30 days. Missing inputs: None.

agent ai-agents kanban management task-manager

Donchitos/Claude-Code-Game-Studios

Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

Category
agent framework
Stars
23,691
Readiness
high risk (41/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
watch
Maintenance risk
26/100 · high confidence

Why: +173 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: recent commit cadence is 0/7.6 of its monthly baseline, no pull-request review responses in 30 days. Missing inputs: None.

ai-agents ai-assisted-development anthropic claude claude-code game-design

nanobrowser/nanobrowser

Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.

Category
agent framework
Stars
13,534
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +21 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 256 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai ai-agents ai-tools automation browser

cloudflare/moltworker

Run OpenClaw, (formerly Moltbot, formerly Clawdbot) on Cloudflare Workers

Category
agent framework
Stars
9,930
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +16 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents cloudflare-workers

ntegrals/openbrowser

Let AI agents browse the web. An autonomous toolkit for browser-based AI agents.

Category
agent framework
Stars
9,506
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
21/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 127 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents automation claude playwright puppeteer sandbox

datahaven-xyz/datahaven

An EVM compatible Substrate chain, powered by StorageHub and secured by EigenLayer

Category
agent framework
Stars
7,917
Readiness
high risk (42/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
19/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 112 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents blockchain decentralized eigenlayer eigenlayer-avs ethereum

Klavis-AI/klavis

Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale

Category
agent framework
Stars
5,786
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai ai-agents api developer-tools discord

liyupi/mianshiya

持续维护的企业面试题库网站，帮你拿到满意 offer！⭐️ 2026年最新Java面试题、前端面试题、AI大模型面试题、AI Agent面试题、RAG面试题、C++面试题、Go面试题、Python面试题、测试面试题、运维面试题、后端面试题、操作系统面试题、计算机网络面试题、Redis面试题、MySQL数据库面试题、算法面试题、Spring面试题、JVM面试题、Java并发面试题、Linux面试题、

Category
agent framework
Stars
5,711
Readiness
needs review (60/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +17 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 184 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents algorithm ant-design backend cpp

serenakeyitan/awesome-notebookLM-prompts

A curated collection of the strongest NotebookLM slide prompts sourced from the real creative underground . Your go-to resource for AI powerpoint :P

Category
agent framework
Stars
4,432
Readiness
needs review (64/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +29 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents gemini google nanobananapro notebooklm

FareedKhan-dev/all-agentic-architectures

35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benc

Category
agent framework
Stars
4,071
Readiness
needs review (67/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +36 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai ai-agents langchain langgraph langsmith llm

mergisi/awesome-openclaw-agents

162 production-ready AI agent templates for OpenClaw. SOUL.md configs across 19 categories. Submit yours!

Category
agent framework
Stars
3,889
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +17 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent-templates ai-agents ai-automation anthropic automation awesome

walkinglabs/awesome-harness-engineering

🛠️ Awesome tools & guides for harness engineering.

Category
agent framework
Stars
3,779
Readiness
needs review (45/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +54 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agemt agentic agentic-ai ai ai-agents harness

muxuuu/serenity-skill

Serenity-inspired Agent Skill for supply-chain bottleneck stock research

Category
agent framework
Stars
3,713
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
16/100 · low confidence

Why: +65 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 94 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills ai-agents claude-code codex investment-research stock-research

oxylabs/ai-crawler-py

Crawl a website starting from a URL, find relevant pages, and extract data – all guided by your natural language prompt.

Category
agent framework
Stars
3,136
Readiness
high risk (37/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
0/100 · low confidence

Why: +13 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents ai-crawler ai-scraping ai-studio ai-web-crawler

eli64s/readme-ai

README file generator, powered by AI.

Category
agent framework
Stars
2,964
Readiness
needs review (70/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai ai-agents ai-documentation anthropic badge-generator

open-webui/open-terminal

A computer you can curl ⚡

Category
agent framework
Stars
2,952
Readiness
needs review (62/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +21 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai ai ai-agents ai-tools open-webui

wquguru/nof0

NOF0 - 开源的 AI 交易竞技场

Category
agent framework
Stars
2,751
Readiness
needs review (45/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: limited evidence; inspect maintenance signals before adopting

Strongest signals: issue load, documentation. Risks: no push in 243 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai ai ai-agents crypto golang hyperliquid

wquguru/harness-books

📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev

Category
agent framework
Stars
2,741
Readiness
high risk (43/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +22 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai ai-agents ai-engineering claude-code codex context-engineering

wanikua/danghuangshang

AI 朝廷搭建完整教程 - 从零基础到进阶

Category
agent framework
Stars
2,701
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents ai-collaboration ai-court ai-orchestration ancient-china

wshobson/commands

A collection of production-ready slash commands for Claude Code

Category
agent framework
Stars
2,604
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 300 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents anthropic automation claude claude-code

kayba-ai/agentic-context-engine

🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai

Category
agent framework
Stars
2,548
Readiness
ready (74/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-learning agent-memory agents ai ai-agents ai-tools

QIN2DIM/hcaptcha-challenger

🥂 Gracefully face hCaptcha challenge with multimodal large language model.

Category
agent framework
Stars
2,455
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +57 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 191 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai-agents captcha captcha-solver captcha-solving chatgpt

zerobootdev/zeroboot

Sub-millisecond VM sandboxes for AI agents via copy-on-write forking

Category
agent framework
Stars
2,417
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
23/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 139 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents code-execution copy-on-write firecracker kvm rust

kevinluosl/deepbot

DeepBot is a system-level AI assistant built for both personal productivity and enterprise workflows — one-click setup, seamless experience, and native Feishu integration.

Category
agent framework
Stars
2,364
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +5 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills agent-tools agentic-workflow agentos ai-agents harness

GammaLabTechnologies/harmonist

Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.

Category
agent framework
Stars
2,345
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +187 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-system ai-agents claude-code cursor-ide llm

Turbo1123/roubao

Android Automation Tool Based on Vision-Language Models

Category
agent framework
Stars
2,304
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 211 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents android android-automation kotlin mobile-agents

bergside/awesome-design-skills

List of 67 awesome DESIGN.md and SKILL.md design skill files for agentic tools like Claude Design, Google Stitch, Codex, Cursor, and other AI tools

Category
agent framework
Stars
2,224
Readiness
needs review (67/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +108 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills agentic-ai agentic-workflow agents ai ai-agents

LiuMengxuan04/shushu-internship-tool

把岗位描述变项目，把项目变简历，把简历变面试。

Category
agent framework
Stars
1,845
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +27 stars in 7 days

Why it may be a gem: limited evidence; inspect maintenance signals before adopting

Strongest signals: issue load. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents skills

unicodeveloper/globalthreatmap

Global threat map. Learn wars, conflicts, military bases and history of nations.

Category
agent framework
Stars
1,780
Readiness
needs review (60/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents ai-assistant intelligence nato osint

ballred/obsidian-claude-pkm

A complete starter kit for an Obsidian + Claude Code personal knowledge management system.

Category
agent framework
Stars
1,738
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
28/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 170 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents claude-code goal-tracking obsidian pkm productivity

lst97/claude-code-sub-agents

Collection of specialized AI subagents for Claude Code for personal use (full-stack development).

Category
agent framework
Stars
1,633
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 357 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents claude-code claudecode-config claudecode-subagents sub-agents subagents

MeetKai/functionary

Chat language model that can use tools and interpret the results

Category
agent framework
Stars
1,595
Readiness
needs review (66/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai ai-agents function-calling llm ml

lucaswalter/n8n-ai-automations

Collection of n8n workflows, n8n templates, AI automations, and AI agents created for The Recap AI YouTube channel and the AI Automation Mastery free Skool community.

Category
agent framework
Stars
1,582
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
26/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 158 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai agentic-workflows agents ai ai-agents artificial-intelligence

langwatch/better-agents

Standards for building agents, better

Category
agent framework
Stars
1,553
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-testing ai-agents cli dev-tool lllm

caramaschiHG/awesome-ai-agents-2026

🤖 The most comprehensive list of AI agents, frameworks & tools in 2026. 300+ resources · 20+ categories · Updated monthly.

Category
agent framework
Stars
1,547
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +32 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

2026 ai-agents artificial-intelligence awesome-list chatgpt langchain

video-db/Director

AI video agents framework for next-gen video interactions and workflows.

Category
agent framework
Stars
1,499
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +45 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 196 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework ai-agents framework llm openai

OpenRaiser/NanoResearch

🦞+🔬 NanoResearch: The Autonomous AI Research Assistant

Category
agent framework
Stars
1,479
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills agents ai ai-agents ai-scientist artificial-intelligence

win4r/ClawTeam-OpenClaw

ClawTeam fork fully adapted for OpenClaw — multi-agent swarm coordination with OpenClaw as the default agent

Category
agent framework
Stars
1,439
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents clawdbot openclaw openclaw-extension openclaw-plugin openclaw-skills

hesamsheikh/octogent

A thin orchestration dashboard over Claude Code for managing context, automation, and developer headspace. You need tentacles. 🦑

Category
agent framework
Stars
1,391
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
18/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 109 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-engineering agentic-workflow ai-agents claude claude-code claude-hooks

tmgthb/Autonomous-Agents

Autonomous Agents (LLMs) research papers. Updated Daily.

Category
agent framework
Stars
1,362
Readiness
needs review (63/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-context agent-harness agentic agentic-ai agents

ntegrals/10x

⚡️ 10x - Up to 20x faster AI coding with multi-step Superpowers. Open-source agent with smart model routing, BYOK, fully self-hosted.

Category
agent framework
Stars
1,359
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +6 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 214 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents anthropic claude claude-code codex coding-agent

firecrawl/open-scouts

🔥 AI-powered web monitoring platform. Create automated scouts that search the web and send email alerts when they find what you're looking for.

Category
agent framework
Stars
1,350
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents alerts automation email-notifications firecrawl nextjs

ray-r-ren/agent-apprenticeship

The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reus

Category
agent framework
Stars
1,342
Readiness
needs review (69/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-apprenticeship agent-economy agent-experience agent-learning agent-traces agentic-ai

jayminwest/overstory

Multi-agent orchestration for AI coding agents — pluggable runtime adapters for Claude Code, Pi, and more

Category
agent framework
Stars
1,328
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
70/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: repository is archived. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-swarms ai-agents claude-code tmux

SmythOS/sre

The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across

Category
agent framework
Stars
1,286
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
21/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 126 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agents agi ai ai-agents artificial-intelligence

Agentshire/Agentshire

OpenClaw / QClaw plugin that visualizes AI agents as 3D NPCs in a game town — with social simulation, a map editor, and a character workshop.

Category
agent framework
Stars
1,266
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

3d ai-agents gamedev multi-agents openclaw qclaw

YGYOOO/WorldX

One sentence creates an AI-driven world — generate maps, characters, and watch stories emerge on their own. 一句话生成一个AI自主驱动的世界.

Category
agent framework
Stars
1,264
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai ai-agents ai-characters ai-simulation ai-world

PentesterFlow/agent

Agentic offensive-security in your terminal

Category
agent framework
Stars
1,205
Readiness
needs review (62/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +47 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents bugbounty penetration-testing security-audit security-automation

browserable/browserable

Open source and self-hostable browser automation library for AI agents

Category
agent framework
Stars
1,199
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 345 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-tools browser-automation browser-use browser-use-js deep-research

TrafficGuard/typedai

TypeScript AI platform with AI chat, Autonomous agents, Software developer agents, chatbots and more

Category
agent framework
Stars
1,193
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 228 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-framework agents ai-agents ai-agents-framework ai-code-review ai-software-engineer

Ido-Levi/Hephaestus

Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to be done, not what you predicted upfront.

Category
agent framework
Stars
1,178
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 249 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents autonomous-agents claude-code llm

pskrunner14/trading-bot

Stock Trading Bot using Deep Q-Learning

Category
agent framework
Stars
1,173
Readiness
needs review (62/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 978 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents deep-q-learning q-learning reinforcement-learning stock-price-prediction stock-trading

dariubs/awesome-workflow-automation

A curated list of Workflow Automation Software, Engines and Tools

Category
agent framework
Stars
1,158
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

activepieces agents ai-agents ai-agents-cli ai-agents-framework awesome-ai-agents

digitalknk/openclaw-runbook

Unofficial OpenClaw runbook for running agents day to day without burning money, exposing your gateway, or trusting random automation.

Category
agent framework
Stars
1,101
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +5 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents openclaw runbook security-hardening self-hosting tailscale

bubblelabai/BubbleLab

Open-core workflow engine powering Bubble Lab — and fully runnable, hostable, and extensible on its own.

Category
agent framework
Stars
1,096
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
17/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 99 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents apis cli code developer-tool

andrepimenta/claude-code-chat

Beautiful Claude Code Chat Interface for VS Code

Category
agent framework
Stars
1,075
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: limited evidence; inspect maintenance signals before adopting

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents claude claude-code vibe-coding vscode

metaskills/experts

Experts.js is the easiest way to create and deploy OpenAI's Assistants and link them together as Tools to create advanced Multi AI Agent Systems with expanded memory and attention to detail.

Category
agent framework
Stars
1,066
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 697 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai ai-agents assistants-api multi-agent-systems openai

lennybase/browsernode

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Category
agent framework
Stars
1,055
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 366 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-tools browser-automation browsernode javascript llm

swarmclawai/swarmclaw

Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter,

Category
agent framework
Stars
636
Readiness
ready (74/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-memory agent-runtime agent-swarm agents ai

OTA-Tech-AI/web-agent-protocol

🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

Category
agent framework
Stars
505
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 414 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-tools browser-automation browser-use llm mcp

MemTensor/MemOS

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

Category
agent framework
Stars
10,641
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +126 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic-ai ai ai-agents chatgpt claude

VoltAgent/voltagent

AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework

Category
agent framework
Stars
10,313
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +73 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai ai-agents ai-agents-framework aiagentframework chatbots

codefuse-ai/codefuse-chatbot

An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework, working with DevOps Toolkits, Code&Doc Repo RAG, etc.

Category
agent framework
Stars
1,289
Readiness
needs review (47/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 767 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aiops chatbot code-repo-analysis code-repo-generation devops gpt

microsoft/markitdown

Python tool for converting files and office documents to Markdown.

Category
agent framework
Stars
172,223
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +1,704 stars in 7 days; 81 lifetime contributors

Why it may be a gem: healthy maintenance and project fundamentals; open issue backlog is stable or shrinking

Strongest signals: push recency, contributor breadth, issue load. Risks: None identified. Missing inputs: None.

Capped lower bounds: response activity.

autogen autogen-extension langchain markdown microsoft-office openai

langchain-ai/deepagents

The batteries-included agent harness.

Category
agent framework
Stars
27,493
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +327 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai deepagents langchain langgraph python typescript

PurpleAILAB/Decepticon

Autonomous Hacking Agent for Red Team

Category
agent framework
Stars
5,008
Readiness
ready (96/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +59 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai cybersecurity generative-ai hacking langchain

strukto-ai/mirage

The World's First Unified Virtual Filesystem For AI Agents

Category
agent framework
Stars
3,389
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +17 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-sandbox agent-tools ai-agents bash claude-code fuse

guy-hartstein/company-research-agent

An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages Google's Gemini 2.5 Flash and OpenAI's GPT-5.1 on

Category
agent framework
Stars
2,212
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +14 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai company financial-analysis gemini gemini-3-flash

vonzosten/awesome-LangGraph

An index of the LangChain + LangGraph ecosystem: concepts, projects, tools, templates, and guides for LLM & multi-agent apps.

Category
agent framework
Stars
1,947
Readiness
needs review (67/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +9 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai awesome awesome-list langchain langgraph llm

moorcheh-ai/memanto

Memory that AI Agents Love!

Category
agent framework
Stars
1,780
Readiness
ready (99/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +37 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-memory ai-agents crewai langchain llm-memory long-term-memory

vstorm-co/full-stack-ai-agent-template

Full-stack AI app generator — FastAPI + Next.js with AI Agents, RAG, streaming, auth, and 20+ integrations out of the box.

Category
agent framework
Stars
1,695
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +22 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agent-template ai-agents crewai docker fastapi

cortexkit/magic-context

Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.

Category
agent framework
Stars
1,674
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +107 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-memory ai ai-agents ai-context ai-memory

langchain-ai/deepagentsjs

The batteries included agent harness.

Category
agent framework
Stars
1,468
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +26 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai deepagents langchain langgraph

datawhalechina/deepagents-in-action

📚 《Deep Agents 实战》—— LangChain 官方大使出品，基于 LangChain / LangGraph 生态，从零构建生产级 AI Agent 的完整指南

Category
agent framework
Stars
1,438
Readiness
ready (79/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +72 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai ai-agents astro chinese context-engineering course

FunnyWolf/agentic-soc-platform

Agentic SOC Platform: A powerful, flexible, open-source, and agent-centric automated security operations platform (AI SOC)

Category
agent framework
Stars
1,126
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +151 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-soc ai blueteam cybersecurity dify langchain

Nicolepcx/ai-agents-the-definitive-guide

Repo for AI Agents The Definitive Guide

Category
agent framework
Stars
909
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai-agents benchmarks deployment evaluation-framework langchain

cognizant-ai-lab/neuro-san-studio

A playground for neuro-san

Category
agent framework
Stars
853
Readiness
ready (98/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +10 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aaosa agentic-ai agentic-framework agents ai ai-agents

emarco177/langgraph-course

Hands-on LangGraph course repo for building production-grade LLM agents with Agentic RAG, ReAct, and reflection workflows.

Category
agent framework
Stars
649
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-rag langchain langgraph reflection

judahpaul16/gpt-home

ChatGPT at home! A better alternative to commercial smart home assistants, built on the Raspberry Pi using LiteLLM and LangGraph.

Category
agent framework
Stars
644
Readiness
ready (72/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai automation docker fastapi home-assistant home-automation

mayooear/ai-pdf-chatbot-langchain

AI PDF chatbot agent built with LangChain & LangGraph

Category
agent framework
Stars
16,593
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
92/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: repository is archived, no push in 133 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai chatbot langchain langgraph nextjs

AgentOps-AI/agentops

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and Ca

Category
agent framework
Stars
5,758
Readiness
needs review (65/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +11 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentops agents-sdk ai anthropic autogen

wassim249/fastapi-langgraph-agent-production-ready-template

A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agent s

Category
agent framework
Stars
2,566
Readiness
needs review (67/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +22 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic-ai docker fastapi fastapi-template langchain

LangChain-OpenTutorial/LangChain-OpenTutorial

LangChain, LangGraph Open Tutorial for everyone!

Category
agent framework
Stars
1,105
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
18/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, license. Risks: no push in 323 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent langchain langgraph

curiousily/AI-Bootcamp

Self-paced bootcamp on Generative AI. Tutorials on ML fundamentals, Ollama, LLMs, RAGs, LangChain, LangGraph, Fine-tuning, DSPy & AI Agents (CrewAI), (Using ChatGPT, gpt-oss, Claude, Qwen, Gemma, Llam

Category
agent framework
Stars
931
Readiness
needs review (70/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents artificial-intelligence chatgpt crewai langchain langgraph

FareedKhan-dev/production-grade-agentic-system

Core 7 layers of production grade agentic system

Category
agent framework
Stars
916
Readiness
needs review (59/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +15 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 232 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai langchain langgraph production

zamalali/DeepGit

Deep research agent to help you find the best GitHub repositories 🕵️!

Category
agent framework
Stars
899
Readiness
high risk (43/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent deep-research github-search langchain langgraph llm

langchain-ai/agent-chat-ui

🦜💬 Web app for interacting with any LangGraph agent (PY & TS) via a chat interface.

Category
agent framework
Stars
3,041
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +16 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent chat langgraph llm

simonlin1212/TradingAgents-astock

A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment。

Category
agent framework
Stars
2,768
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +84 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a-share ai-agent china-stocks claude fintech investment-research

langgraph4j/langgraph4j

🚀 LangGraph for Java. A library for develop AI Agentic Architectures in the Java ecosystem. Designed to work seamlessly with both Langchain4j and Spring AI.

Category
agent framework
Stars
1,895
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +29 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai langchain4j langgraph spring-ai workflow

kyegomez/awesome-multi-agent-papers

A compilation of the best multi-agent papers

Category
agent framework
Stars
1,640
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents agents-team attention autogen autonomous-agents crewai

langchain-ai/langgraph-swarm-py

For your multi-agent needs

Category
agent framework
Stars
1,550
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents langgraph llms multiagent multiagent-systems python

langchain-ai/react-agent

LangGraph template for a simple ReAct agent

Category
agent framework
Stars
810
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

langgraph langgraph-python langgraph-template

chirpz-ai/pandaprobe

open source agent engineering platform: traces, evals, and metrics to debug and improve your AI agents. Integrates with LangGraph, CrewAI, Claude Agent SDK, and more.

Category
agent framework
Stars
736
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +20 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-engineering agent-evaluation agent-observability agentic-ai claude-agent-sdk crewai

zhongyu09/openchatbi

OpenChatBI is an intelligent chat-based BI tool powered by large language models, designed to help users query, analyze, and visualize data through natural language conversations. It uses LangGraph an

Category
agent framework
Stars
617
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai analytics anomaly-detection bi chatbi

w8123/EnterpriseAgentFramework

面向 OA、ERP、CRM、工单等企业系统快速构建智能体，让 AI 在权限、审计与治理约束下安全调用真实业务能力。Build agents quickly for enterprise systems such as OA, ERP, CRM, and ticketing, enabling AI to safely call real business capabilities under pe

Category
agent framework
Stars
552
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +35 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a agent-framework ai-agents ai-capability ai-gateway ai-platform

datawhalechina/easy-langent

📚“langent”由“lang”与“agent”合并而来的学习教程

Category
agent framework
Stars
445
Readiness
needs review (64/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
healthy
Maintenance risk
18/100 · high confidence

Why: +4 stars in 7 days; 22 lifetime contributors

Why it may be a gem: healthy maintenance and project fundamentals; open issue backlog is stable or shrinking

Strongest signals: contributor breadth, issue load, fork interest. Risks: recent commit cadence is 2/19.6 of its monthly baseline. Missing inputs: release recency.

agent ai-agents langchain langgraph

hawkli-1994/deerflow-book

本书围绕 DeerFlow 2.0，从理论到源码，系统讲解如何进行二次开发。(精校)

Category
agent framework
Stars
440
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
watch
Maintenance risk
18/100 · high confidence

Why: +16 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: recent commit cadence is 0/5.6 of its monthly baseline. Missing inputs: release recency.

agent-framework ai-agent book bytecode chinese deep-research

luochang212/dive-into-langgraph

LangGraph 1.0 Tutorial

Category
agent framework
Stars
435
Readiness
needs review (60/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +3 stars in 7 days; 16 commits in 30 days

Why it may be a gem: open issue backlog is stable or shrinking

Strongest signals: push recency, issue load, documentation. Risks: maintenance is concentrated in one contributor. Missing inputs: release recency.

agent agent-skills e-book guide handbook langchain

Pan-Chera/Multi-Agent-CAD

MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute

Category
agent framework
Stars
425
Readiness
ready (72/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
watch
Maintenance risk
0/100 · high confidence

Why: 28 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity; open issue backlog is stable or shrinking

Strongest signals: push recency, commit activity, issue load. Risks: maintenance is concentrated in one contributor. Missing inputs: None.

3d-modeling 3d-printing agent-pipeline aider build123d cad

swytchcodehq/swytchcode-examples

Swytchcode demo projects with different agents

Category
agent framework
Stars
402
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

claude gpt hermes langchain langgraph openclaw

CopilotKit/open-research-ANA

🤖 An open-source, AI agent-native research canvas application that performs real-time search with HITL (Human in The Loop) capabilities, powered by CopilotKit, Tavily and LangGraph

Category
agent framework
Stars
395
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-native ai anthropic canvas chatbot chatgpt

Arvo-AI/aurora

Aurora — Open source AI-powered agentic incident management & root cause analysis for SREs. LangGraph agents investigate across AWS, Azure, GCP, Kubernetes. Integrates with PagerDuty, Datadog, Grafana

Category
agent framework
Stars
386
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents aiops automation aws azure datadog

cacheplane/dawnai

Build LangGraph agents like Next.js apps.

Category
agent framework
Stars
383
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +293 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai developer-tools framework langchain langgraph

Xeron2000/openOii

故事想法 → 多智能体协作 → 漫剧成片 | 基于 LangGraph 的 AI 漫剧生成平台

Category
agent framework
Stars
369
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai ai-video comic fastapi langgraph

a-agmon/rs-graph-llm

High-performance framework for building interactive workflow systems in Rust. Designed for complex workflows and multi-agent systems

Category
agent framework
Stars
358
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents graph langgraph llm rust workflow

rajudandigam/agent-inspect

Local execution trees for TypeScript AI agents. agent-inspect helps you understand what happened inside an AI agent run — locally. It turns manual steps, tool calls, LLM calls, structured logs, failu

Category
agent framework
Stars
342
Readiness
ready (98/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents cli debugging devtools evidence jsonl

cqzyys/lang-agent

基于LangChain和LangGraph实现的AI Agent配置平台

Category
agent framework
Stars
331
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai chatbot fastapi langchain langgraph

Prompthon-IO/agent-systems-handbook

A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend

Category
agent framework
Stars
326
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a agent-framework agent-memory agentic-ai agentic-workflow ai-agent

sinanuozdemir/oreilly-ai-agents

An introduction to the world of AI Agents

Category
agent framework
Stars
299
Readiness
needs review (70/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic-ai agents ai autogen claude

smallnest/langgraphgo

功能那么强大，代码如此简单

Category
agent framework
Stars
295
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic ai langchain langgraph

langchain-ai/new-langgraph-project

No description

Category
agent framework
Stars
284
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

langgraph langgraph-python langgraph-template

huygiatrng/AlpacaTradingAgent

AlpacaTradingAgent: Multi-Agents LLM Financial Trading Framework and perform trades on alpaca

Category
agent framework
Stars
246
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents algorithmic-trading alpaca alpaca-api automated-trading crypto-trading

langchain-ai/data-enrichment

LangGraph Studio template for creating an agent that does web research to genearte or enrich structured data.

Category
agent framework
Stars
243
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

langgraph langgraph-python langgraph-template

redis-developer/langgraph-redis

Redis checkpointer and store for memory management in LangGraph

Category
agent framework
Stars
235
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai langchain langgraph memory redis

unipds-engenharia-de-ia-aplicada/awesome-unipds-projects

A curated list of original projects built by students of the UNIPDS Software engineering with Applied AI Engineering postgrad course.

Category
agent framework
Stars
222
Readiness
ready (78/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents gemini gemininano langchain langchain-js langgraph

santosomar/AI-agents-for-cybersecurity

This repository contains resources and materials for courses and presentations related to AI Agents and Agentic Systems for Cybersecurity Operations by Omar Santos.

Category
agent framework
Stars
219
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai agentic-rag agents ai artificial-intelligence cyber

yonatangross/orchestkit

The Complete AI Development Toolkit for Claude Code — 114 skills, 37 agents, 212 hooks. Production-ready patterns for full-stack development.

Category
agent framework
Stars
215
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-orchestration agents ai-agents ai-development anthropic claude-code

rootflo/wavefront

🔥🔥🔥 Enterprise AI middleware, alternative to unifyapps, n8n, lyzr

Category
agent framework
Stars
200
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai agentic-rag ai-guardrails ai-middleware ai-workflow crewai

velocitybolt/open-extract

Structured Data Extractor for AI Agents. Search your documents or the web for specific data and get it back in JSON or Markdown in a single tool call.

Category
agent framework
Stars
188
Readiness
ready (78/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-tools ai autogen context-aware context-aware-structured-outputs crewai

OnePunchMonk/AgentQuant

Autonomous quantitative trading research platform that transforms stock lists into fully backtested strategies using AI agents, real market data, and mathematical formulations, all without requiring a

Category
agent framework
Stars
170
Readiness
ready (79/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +9 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai autonomous-agent finance-ai fintech langchain langgraph

langchain-ai/retrieval-agent-template

No description

Category
agent framework
Stars
168
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

langgraph langgraph-python langgraph-template

proactive-agent/langgraphics

Visualize live LangGraph execution and see how your agent thinks as it runs.

Category
agent framework
Stars
140
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +8 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

animation deepagents graph langfuse langgraph langsmith

kevin333353/jobsmith

針對台灣求職市場的開源多代理 AI 求職 co-pilot：自動找職缺、履歷健檢、一鍵產生客製投遞包（履歷・求職信・面試準備・公司情報）與模擬面試。本機 Claude Code／Codex CLI 免 API key，也可自備金鑰接 OpenAI 相容模型。

Category
agent framework
Stars
139
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-agents career-tools claude-code codex-cli desktop-app

nihalashetty/Forge

Forge is an open-source, self-hosted alternative for visually building and shipping AI agents and workflows without giving up control of your infrastructure.

Category
agent framework
Stars
137
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents langchain langgraph llms mcp rag

hidai25/eval-view

Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGraph, CrewAI, OpenAI, Anthropic.

Category
agent framework
Stars
128
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-benchmark agent-evaluation agentic-ai ai-agents anthropic autogen

ljxpython/ai-agent-platform

AI agent平台开发 --以测试 方向为例，搭建了一套 harness 可落地方案，不需要手写一段代码，企业级通用 AI 智能体平台框架（平台控制面 + LangGraph 运行时），可以在这个基础轻松二次开发

Category
agent framework
Stars
122
Readiness
ready (74/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic-ai harness-engineering langgraph testng vibe-coding

loopgain-ai/loopgain

An open-source cost controller for AI agent loops — stops a loop when it's actually converged and rolls back before it degrades, instead of running to a fixed max_iterations cap. Real-time loop-gain (

Category
agent framework
Stars
120
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-orchestration agentic agentic-ai ai-agents anthropic autogen

Agentic-Analyst/stock-analyst

VYNN AI Agent Backend is a standalone agent execution system for financial analysis. It orchestrates LLM-based agents to scrape historical financial data, build valuation models, analyze real-time fin

Category
agent framework
Stars
116
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai dcf-valuation financial-modeling langgraph price-prediction sentiment-analysis

langchain-ai/react-agent-js

No description

Category
agent framework
Stars
113
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

langgraph langgraph-js langgraph-template

yaalalabs/agent-kernel

The Operating System for Scalable Enterprise AI Agents - Run, orchestrate, and deploy Compliant Enterprise AI Agents at scale across frameworks, without lock-in, rewrites or fragile glue code. Native

Category
agent framework
Stars
112
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +12 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a adk ai-agents aws azure cloud-native

rooneyrulz/agentic-stock-research-system

A sophisticated multi-agent AI system for analyzing Indian NSE-listed stocks using real-time data, technical indicators, news sentiment, and advanced AI reasoning.

Category
agent framework
Stars
111
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents groq langchain langgraph llms mcp

OpenDCAI/Paper2Any

Turn paper/text/topic into editable research figures, technical route diagrams, and presentation slides.

Category
agent framework
Stars
2,760
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +12 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai aippt editable-pptx langgraph paper2slides

StreetLamb/tribe

Low code tool to rapidly build and coordinate multi-agent teams

Category
agent framework
Stars
1,081
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 284 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-based-framework agent-oriented-programming agentic agentic-agi ai ai-tools

ScrapeGraphAI/scrapecraft

🤖 AI-powered web scraping editor with visual workflow builder. Build, test & deploy web scrapers using natural language. Powered by ScrapeGraphAI & LangGraph.

Category
agent framework
Stars
679
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 224 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai automation data-extraction docker fastapi hacktoberfest

nuglifeleoji/Options-Analytics-Agent

A sophisticated LangGraph-based agent that automates financial options analysis with real-time data from Polygon.io, smart caching, persistent memory, and professional-grade analysis. Built for trader

Category
agent framework
Stars
639
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 235 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

chroma-db fastapi langgraph options rag-chatbot

BrandPeng/Langchain1.0-Langgraph1.0-Learning

这是一个 LangChain 1.0 和 LangGraph 1.0 的学习仓库，学习如何进行agent开发，涵盖从基础概念到实战项目的完整学习路径。

Category
agent framework
Stars
616
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, license. Risks: no push in 208 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent langchain langgraph

evolution-foundation/evo-ai

Evo AI is an open-source platform for creating and managing AI agents, enabling integration with different AI models and services.

Category
agent framework
Stars
601
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 431 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a-protocol adk agent agentic-ai agentic-workflow ai

firecrawl/firesearch

🔥 AI-powered deep research tool that breaks down complex queries, validates answers, and provides cited comprehensive results using Firecrawl and LangGraph

Category
agent framework
Stars
496
Readiness
needs review (48/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 431 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

firecrawl langchain langgraph llm research

girijesh-ai/ai-interview-codex

Comprehensive ML/AI interview codex with iterative system design, production-ready code, and 2026 standards. Includes LLM/GenAI, RAG systems, agentic AI, and algorithms from scratch.

Category
agent framework
Stars
482
Readiness
needs review (46/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 203 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai deep-learning interview-preparation langgraph machine-learning system-design

alirezadir/Agentic-AI-Systems

Practical system design, tools, and hands-on resources for building Gen-AI agents & agentic AI systems.

Category
agent framework
Stars
420
Readiness
needs review (68/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai agentic-framework agentic-workflow agents ai-agents ai-systems

Annyfee/agent-craft

AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体

Category
agent framework
Stars
412
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +12 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent artificial-intelligence beginner-guide chatbot deepseek langchain

leonyangdev/lc-studylab

LC-StudyLab 是一个完整演示 LangChain v1.0 全家桶能力的开源项目，整合了 LangGraph、DeepAgents、RAG 检索增强生成、Guardrails 安全校验与流式输出智能体等核心特性，帮助开发者系统掌握 LangChain v1 的所有关键组件

Category
agent framework
Stars
390
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, license. Risks: no push in 241 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

langchain langgraph

skygazer42/GustoBot

五星大厨:全面Multi-Agent 的客服机器人，基于langraph实现，txt2sql ,txt2cypher, lightrag, 多模态 等

Category
agent framework
Stars
379
Readiness
needs review (65/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent graphrag langchain langgraph lightrag multi-agent

FareedKhan-dev/Multi-Agent-AI-System

Building a Multi-Agent AI System with LangGraph and LangSmith

Category
agent framework
Stars
369
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 433 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents langchain langgraph langsmith multi-agent-systems openai

Karovia/fullstack-ai-agent-roadmap

🎯 从零基础到 AI Agent 全栈工程师 · 110 个详细教程 · 58 万字 · 400+ GitHub 项目精选 · Obsidian 友好 · 中文

Category
agent framework
Stars
369
Readiness
needs review (48/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +12 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent chinese claude fastapi fullstack

kaymen99/sales-outreach-automation-langgraph

Automate lead research, qualification, and outreach with AI agents and Langgraph, creating personalized messaging and connecting with your CRMs (HubSpot, Airtable, Google Sheets)

Category
agent framework
Stars
363
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 569 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-automation automation crm-connections hubspot langchain

ttguy0707/CyberClaw

👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态

Category
agent framework
Stars
325
Readiness
needs review (65/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework ai-agent ai-safety claude-code cross-platform

rokbenko/ai-playground

📽️ Code from tutorials presented on the "Code AI with Rok" YouTube channel

Category
agent framework
Stars
320
Readiness
needs review (62/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

anthropic crewai exa fetchai gemini langchain

lhh737/LangChain-ReAct-Agent

基于 LangChain/LangGraph 的 ReAct Agent ，结合 RAG、工具调用与 Streamlit 界面，面向智能客服与报告生成场景。

Category
agent framework
Stars
303
Readiness
needs review (60/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +10 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent chromadb dashscope langchain langgraph llm

GenseeAI/cognify

Multi-Faceted AI Agent and Workflow Autotuning. Automatically optimizes LangChain, LangGraph, DSPy programs for better quality, lower execution latency, and lower execution cost. Also has a simple age

Category
agent framework
Stars
280
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +3 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 448 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic-workflow agents ai automl autotuning

didilili/shopkeeper-agent

📊 电商数仓智能问数 AI Agent，最适合用于系统学习 LangGraph 的实战项目：基于 LangGraph、FastAPI、Qdrant、Elasticsearch、MySQL 与 React，完整实现元数据知识库、混合检索、自然语言生成 NL2SQL 生成校验、SQL 执行与流式查询展示。前后端完整代码全栈可跑，Docker 环境一键部署，配套 ai-agents-from-zero

Category
agent framework
Stars
273
Readiness
needs review (62/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +25 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-workflow ai-agent elasticsearch fastapi langchain langgraph

kaymen99/langgraph-email-automation

Multi AI agents for customer support email automation built with Langchain & Langgraph

Category
agent framework
Stars
264
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 540 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-automation ai-customer-service ai-customer-support customer-support customer-support-automation

aws-samples/sample-agentic-frameworks-on-aws

Build Agentic AI solutions on AWS, using latest OSS Agentic Frameworks.

Category
agent framework
Stars
262
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a-protocol agentic-ai arize-phoenix crewai langgraph llamaindex

bernatsampera/event-deep-research

AI Agent that researches the lives of historical figures and extracts events into structured JSON timelines using LangGraph multi-agent orchestration.

Category
agent framework
Stars
252
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 292 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent context-engineering deep-agent langchain langgraph llm-orchestration

MODSetter/gpt-instagram

A GPT-based autonomous multi-agent AI in Next.js that research & recommends Instagram Viral Posts reflecting your personality.

Category
agent framework
Stars
244
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 596 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai dalle gpt langchain langchain-js

langchain-ai/langchain-sandbox

Safely run untrusted Python code using Pyodide and Deno

Category
agent framework
Stars
242
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
100/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: limited evidence; inspect maintenance signals before adopting

Strongest signals: issue load, documentation. Risks: repository is archived, no push in 205 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

code-interpreter langchain langgraph llm llms pyodide

YassWorks/Ally

A local private agentic system that works in your terminal.

Category
agent framework
Stars
241
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
21/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 124 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai ai langchain langgraph privacy

eosho/langchain_data_agent

NL2SQL - Ask questions in plain English, get SQL queries and results. Powered by LangGraph.

Category
agent framework
Stars
234
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 205 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a a2a-protocol ai-agents azure data-agent database

jkmaina/LangGraphProjects

This is the official companion repository for the book The Complete LangGraph Blueprint: Build 50+ AI Agents for Business Success. The repository provides source code, practical examples, and resource

Category
agent framework
Stars
209
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

langchain langchain-python langgraph langgraph-chabot langgraph-python langgraph-template

muratcankoylan/readwren

An adaptive multi-agent system that extracts your literary DNA through conversation and generates actionable reading profiles.

Category
agent framework
Stars
202
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: issue load, documentation, license. Risks: no push in 271 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai kimi-k2 langchain langgraph llm moonshot

iniwap/AIWriteX

AIWriteX - 微信公众号全自动AI工具：全网热搜舆情聚合+趋势分析+爆款选题+文章采集+一键生成排版发布 | AI自动配图 | 去AI味、过朱雀检测 | 支持小红书/百家号/头条等多平台 | 洗稿润色支持多账号 | 专家赛道 | 手机控制 | 小说连载 | 爆文10w+神器

Category
agent framework
Stars
1,794
Readiness
ready (98/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +46 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai-agents ai-auto-wxgzh ai-wx aipy aipyapp

johnsonhk88/AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction

AI Bank Statement Document Automation By LLM model and Personal Finanical Analysis

Category
agent framework
Stars
616
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents crewai document-automation gemma langchain llm

TryCaspian/caspian-sdk

Agent communication SDK. The open-source agent communication layer for AI agents — email, WhatsApp, Slack, Discord, Telegram, SMS. Python & TypeScript.

Category
agent framework
Stars
527
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +159 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-communication agent-messaging ai-agent ai-agents communication crewai

RyjoxTechnologies/Octopoda-OS

The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.

Category
agent framework
Stars
502
Readiness
needs review (71/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +153 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agents ai-memory autogen crash-recovery crewai

lawglance/lawglance

A free open source RAG based AI legal assistant.

Category
agent framework
Stars
306
Readiness
ready (99/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai assistance chromadb crewai django langchain-python

shuxiachai/academic-commercialization-agent

Turn any research paper into a commercialization report — 6 AI agents, TRL/MRL scoring, patent landscape, market intelligence, verified citations. DeepSeek / OpenAI / Claude.

Category
agent framework
Stars
293
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +102 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

academic-research ai-agent anthropic commercialization crewai deepseek

ARUNAGIRINATHAN-K/awesome-ai-agents-2026

Awesome AI Agents for 2026 - 300+ AI Agents, Frameworks & Coding • Creative • Voice • Research • Enterprise. Comparison guides, benchmarks & deep dives

Category
agent framework
Stars
287
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

2026 agent-frameworks ai-agents ai-tools autonomous-agents awesome

jagmarques/asqav-sdk

Python and TypeScript SDKs for verifiable evidence of AI agent actions. Signed receipts, policy enforcement, audit trails. Works with LangChain, CrewAI, MCP.

Category
agent framework
Stars
259
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent-governance ai-agents ai-compliance ai-governance ai-security audit-trail

LangGraph-GUI/CrewAI-GUI-Qt

A Node-Based Frontend for CrewAI: Revolutionizing AI Workflow Creation

Category
agent framework
Stars
209
Readiness
ready (78/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-agents crewai gui pyside

AISquare-Studio/AISquare-Studio-QA

Setting up QA testing agents using playwright and crewAI

Category
agent framework
Stars
167
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai automation crewai github-actions multi-agent openai

faramesh/faramesh-core

Governance-as-Code for AI agents. Declarative constraints with deterministic enforcement. Provisioning Identity, Tool-based rules, Brokering Credentials & Ensuring safe deployment

Category
agent framework
Stars
100
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-governance agent-governance-toolkit agent-runtime agent-security agentic-ai ai-agents

seehiong/seehiong.github.io

seehiong.github.io Tech Blog

Category
agent framework
Stars
95
Readiness
needs review (69/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai autogen blog crewai deepseek-r1 giscus

startino/aitino

Aitino is a platform that allows for the creation of crews of AI Agents to help you automate tasks and solve complex problems.

Category
agent framework
Stars
91
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai aitino autogen automation crewai llm

aozyildirim/Agena

Agentic AI platform with pixel agent technology — autonomous code generation, PR automation & multi-tenant SaaS

Category
agent framework
Stars
88
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai agentic-ai-development agentic-workflow ai-agents crewai pixel

Jovancoding/Network-AI

Traffic light for AI Agents and TypeScript/Node multi-agent orchestrator with shared state, guardrails, and adapters for 32 AI frameworks

Category
agent framework
Stars
69
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-orchestration ai-agents autogen blackboard blackboard-architecture

maximem-ai/maximem_synap_sdk

Maximem Synap is the memory layer that makes AI agents remember. 92% LongMemEval, 93.2% on LOCOMO. Works natively with LangChain, LlamaIndex, CrewAI, Google ADK, AutoGen, OpenAI Agents, Semantic Kerne

Category
agent framework
Stars
59
Readiness
ready (96/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-memory ai ai-agents ai-memory autogen context

raia-live/amfs

Git for agent memory. Branches, diffs, PRs, and rollback for what your agents know.

Category
agent framework
Stars
59
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-management agent-memory ai ai-agent ai-agents ai-tools

dunetrace/dunetrace

The runtime reliability layer for AI agents.

Category
agent framework
Stars
59
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-monitoring agent-observability agent-reliability agent-tools ai-agents ai-tools

getclyro/clyro

Clyro is a governance platform for AI agents. While most tools let you watch agents fail, Clyro stops failures before they happen, catching infinite loops, runaway costs, and policy violations in real

Category
agent framework
Stars
53
Readiness
ready (78/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai ai-governance anthropic claude claude-code

IBM/watsonx-developer-hub

Examples and guides for building Gen AI applications on the watsonx platform.

Category
agent framework
Stars
49
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai autogen beeai crewai genai

SAP-samples/codejam-code-based-agents

Learn how to write code-based agents using Python, JavaScript and well-known industry standard frameworks. Learn how to deploy your code-based agent to SAP BTP, Kyma runtime, orchestrate them using Jo

Category
agent framework
Stars
38
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai crewai javascript joule langraph

mishrasanjeev/grantex

grantex is the identity, authorization, and audit infrastructure for AI agents — the "OAuth moment" for the agentic internet. We provide a universal SDK and cloud service that lets any AI agent act on

Category
agent framework
Stars
31
Readiness
ready (79/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents audit-trail authorization compliance crewai

yanyongyu/operagents

Dynamic, highly customizable language agents framework

Category
agent framework
Stars
31
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent crewai gpt langgraph language-model sop

rhein1/agoragentic-integrations

Public adapters and discovery catalog for Triptych OS (Agent OS): agent frameworks, MCP/A2A/x402 protocols, workflows, wallets, SDKs, and examples for execute-first routing, governed handoffs, and rec

Category
agent framework
Stars
27
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a agent-commerce agent-framework agent-marketplace agent-os agentic-ai

18534516725/llm-api-setup-guides

47篇中文 AI 工具自定义 API 教程：Claude Code、Codex CLI、Qwen Code、Gemini CLI、Cherry Studio、Dify、OpenAI Agents SDK，包含安装、配置、协议兼容与报错排查。

Category
agent framework
Stars
25
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-api aider api-proxy api-testing cherry-studio chinese-tutorial

CodNoob100/null-drift

No description

Category
agent framework
Stars
23
Readiness
ready (73/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents cognitive-architecture crewai fastapi hyperdimensional-computing langgraph

temiroff/Blacknode

A visual runtime for AI, GPU computing, and robotics, workflow framework for AI agents. MCP-native typed graphs, visual editor, Python export.

Category
agent framework
Stars
21
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +11 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-workflows ai-agents ai-tools anthropic crewai langgraph

datarobot-community/datarobot-agent-templates

DataRobot Agentic Workflow Templates

Category
agent framework
Stars
20
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai crewai datarobot langgraph llamaindex llm

udaysaai/mycelium

🍄 The open-source internet for AI agents. pip install → discover → communicate → collaborate.

Category
agent framework
Stars
18
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-frameworks agents ai ai-agents crewai developer-tools

Defend-AI-Tech-Inc/agent-discover-scanner

The industry-standard Agentic Identity & Inventory Scanner. Automatically inventory autonomous agents (LangChain, AutoGen, CrewAI, PydanticAI) using static analysis, network heuristics, and eBPF. Foun

Category
agent framework
Stars
18
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-ops agentic-governance ai-native ai-security aibom autogen

frangelbarrera/awesome-ai-agents

Awesome AI agents 2026 — Kimi K3, Claude, GPT-5, Gemini & 200+ tools. Frameworks, autonomous agents, MCP servers.

Category
agent framework
Stars
17
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +8 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

2026 agentic ai ai-agent artificial-intelligence autogpt

tezansahu/ai-garage

Mini-Projects using Cutting-Edge AI Frameworks

Category
agent framework
Stars
16
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents artificial-intelligence autogen crewai hands-on

supervaize/supervaizer

SUPERVAIZER is a toolkit built for the age of AI interoperability. At its core, it implements Google's Agent-to-Agent (A2A) protocol, enabling seamless discovery and interaction between agents across

Category
agent framework
Stars
15
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a acp agentic agentic-workflow ai-agents crewai

comply54/comply54

African AI governance — runtime compliance enforcement for AI agents operating under NDPA, CBN, NIMC Act 2026, KDPA, POPIA and 15+ African regulations. LangGraph, CrewAI, and AutoGen adapters included

Category
agent framework
Stars
12
Readiness
needs review (69/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

africa ai-agents ai-governance autogen compliance crewai

sattyamjjain/agent-airlock

A deny-by-default contract & type-checker layer for AI agent tool calls — Pydantic-based, in-process, zero-core-deps. Validates the actual tool-call payload (ghost-arg stripping, strict types, self-he

Category
agent framework
Stars
12
Readiness
ready (98/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-security crewai firewall langchain llm-safety

sensein/structsense

A multi-agent system for extracting structured information from unstructured text and documents. It orchestrates a configurable pipeline of AI agents — extractor → alignment → judge → human feedback —

Category
agent framework
Stars
11
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: strong signals despite limited visibility

Strongest signals: fork interest, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

crewai information-extraction multi-agent-systems ontology

Shuyib/crewai_apps

Hyperagents that collaboratively work to act on your instructions. Example Blog Post editors.

Category
agent framework
Stars
11
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

autogen crewai hyperagents journalism llms openai-api

abhinaykrupa/cowork-to-code-bridge

Let Claude run code on your real machine — safely — from any Claude chat. Bridges Claude Cowork to Claude Code on your Mac/Linux box. One command, idempotent, no open ports.

Category
agent framework
Stars
11
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents anthropic async autogen automation bridge

3IVIS/buildaharness

A visual harness builder for ai agents

Category
agent framework
Stars
10
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a ai crewai harness harness-engineering langgraph

Cohexa-ai/agent-coherence

The coordination layer for Multiplayer AI

Category
agent framework
Stars
10
Readiness
needs review (71/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-memory ai-agent autogen cache-coherence crewai langchain

alsoleg89/ai-knot

Deterministic, self-hosted long-term memory for AI agents: store facts instead of transcripts, recall only what matters.

Category
agent framework
Stars
9
Readiness
needs review (69/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-memory ai-agents ai-memory context-engineering crewai gigachat

acailic/agent_debugger

Local-first agent debugger with replay, failure memory, smart highlights, and drift detection.

Category
agent framework
Stars
9
Readiness
needs review (68/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-tracing ai-agents ai-debugging crewai debugging developer-tools

10mudassir007/Agentic-Systems

A go-to repository for building web search agents and multi-agent systems using LangChain, LangGraph, Phidata/Agno, Pydantic, and CrewAI. It includes a multi-agent email response agent, LLaMA OCR, an

Category
agent framework
Stars
9
Readiness
needs review (70/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai agents crewai langgraph

Providex-AI/rootsign

Rootsign is an open-source tamper-evident decision and action provenance logging library for AI agents

Category
agent framework
Stars
8
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-accountability agents ai-agents audit-trail compliance crewai

aiperceivable/apflow

**AI-Perceivable Distributed Orchestration** apflow is a distributed task orchestration engine where every capability is AI-perceivable — discoverable, understandable, and invocable by AI agents thro

Category
agent framework
Stars
8
Readiness
ready (77/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a-protocol agent-framework ai-agents automation-task-scheduler crewai distributed-systems

knowledgestack/ks-cookbook

Developer acceleration layer for enterprise RAG + agent pipelines. 32 production-style flagships on LangChain, LangGraph, CrewAI, Temporal, OpenAI Agents SDK, pydantic-ai. Permission-aware retrieval,

Category
agent framework
Stars
7
Readiness
ready (79/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai-agents citation-grounding compliance cookbook crewai

skitsanos/tiny-crew

Multi-Agent AI system to tackle complex tasks through intelligent collaboration

Category
agent framework
Stars
7
Readiness
needs review (69/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai artificial-intelligence crew crewai llm llms

kalyan-1845/lexicon

📚 Lexicon AI — Agentic Research Workspace. Multi-agent literature intelligence powered by Next.js, FastAPI, ChromaDB, and CrewAI.

Category
agent framework
Stars
7
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents chromadb crewai fastapi multi-agent nextjs

Sedrah/Trace-lit-SDK

No description

Category
agent framework
Stars
7
Readiness
needs review (69/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents crewai langchain monitoring observability

Maventlabs/Moxielabs

An autonomous multi-agent AI system built with CrewAI. Automate UI/UX design, branding, and copywriting through a 5-agent creative agency crew, orchestrated directly via Telegram.

Category
agent framework
Stars
6
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents creative-agency crewai langgraph multi-agent-systems

linny006/llm-agents-radar

Live-updating index of LLM agent frameworks shipping on GitHub, refreshed every 15 minutes

Category
agent framework
Stars
6
Readiness
ready (75/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-tooling agentic agentic-ai ai-agent ai-agents ai-engineering

DrakoLabs/drako

AI agent security and governance platform for the full lifecycle. Scan before you ship. Govern and block at runtime. No Azure required.

Category
agent framework
Stars
6
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-security ai ai-agents ai-governance compliance crewai

crewAIInc/crewAI-examples

A collection of examples that show how to use CrewAI framework to automate workflows.

Category
agent framework
Stars
6,129
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
88/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest. Risks: repository is archived, no push in 109 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

crewai examples

jgravelle/AutoGroq

AutoGroq is a groundbreaking tool that revolutionizes the way users interact with Autogen™ and other AI assistants. By dynamically generating tailored teams of AI agents based on your project requirem

Category
agent framework
Stars
1,502
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +3 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 592 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai artificial-intelligence autogen crewai groq

crewAIInc/crewAI-tools

Extend the capabilities of your CrewAI agents with Tools

Category
agent framework
Stars
1,461
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
100/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: repository is archived, no push in 288 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai aiagents crewai crewai-tools

alexfazio/viral-clips-crew

Your CrewAI Powered Video Editing Assistant

Category
agent framework
Stars
761
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
29/100 · low confidence

Why: +4 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 172 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

crewai ffmpeg whisper yt-dlp

rnadigital/agentcloud

Agent Cloud is like having your own GPT builder with a bunch extra goodies. The GUI features 1) RAG pipeline which can natively embed 260+ datasources 2) Create Conversational apps (like GPTs) 3) Crea

Category
agent framework
Stars
686
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 382 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai autogen chatgpt crewai dockerized-application genai

alexfazio/crewAI-quickstart

A collection of notebooks, cookbooks, and recipes showcasing fun and effective ways to use CrewAI's agentic workflow implementations and tools.

Category
agent framework
Stars
422
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, license. Risks: no push in 681 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents cookbook crewai

Repello-AI/Agent-Wiz

A CLI tool for threat modeling and visualizing AI agents built using popular frameworks like LangGraph, AutoGen, CrewAI, and more.

Category
agent framework
Stars
385
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +4 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 278 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic-ai ai ai-agents autogen crewai

theyashwanthsai/Devyan

Building a Software Dev Team. Experimental Project to orchestrate a team of agents to solve programming tasks.

Category
agent framework
Stars
291
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 755 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents crewai gpt4o multiagent-systems openapi

Corpus-OS/corpusos

Open-source protocol suite standardizing LLM, Vector, Graph, and Embedding infrastructure across LangChain, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, and MCP. 3,330+ conformance tests. One protoco

Category
agent framework
Stars
213
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
15/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: issue load, documentation, license. Risks: no push in 91 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai-agents ai-infrastructure anthropic autogen chatgpt

lioensky/VCPToolBox

VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。

Category
agent framework
Stars
2,232
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +11 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agent ai-assistant ai-companion context-management context-management-system

unohee/OpenSwarm

OpenSwarm — Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integration, cognitive memory.

Category
agent framework
Stars
835
Readiness
ready (96/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-coding autonomous-agents claude claude-code devops

nexu-io/html-anything

✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed pre

Category
agent framework
Stars
8,134
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +104 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills agentic ai-agents ai-design ai-editor byok

2FastLabs/agent-squad

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

Category
agent framework
Stars
7,732
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai agents ai-agents ai-agents-framework anthropic anthropic-claude

grab/cursor-talk-to-figma-mcp

TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.

Category
agent framework
Stars
6,958
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +14 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic agentic-ai ai ai-agents automation

strands-agents/harness-sdk

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

Category
agent framework
Stars
6,832
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +80 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agentic agentic-ai agents ai ai-agents

embabel/embabel-agent

Agent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/

Category
agent framework
Stars
4,012
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +177 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic-ai agents ai ai-agents aiagentframework

RunMaestro/Maestro

Agent Orchestration Command Center

Category
agent framework
Stars
3,217
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +38 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents claude-code codex generative-ai opencode

trypromptly/LLMStack

No-code multi-agent framework to build LLM Agents, workflows and applications with your data

Category
agent framework
Stars
2,309
Readiness
needs review (48/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 604 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai ai-agents-framework generative-ai llm-agents llm-chain

friuns2/codex-mobile

🚀 Run Codex Mobile Anywhere: Linux, Windows, or Termux on Android 🚀

Category
agent framework
Stars
846
Readiness
needs review (59/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +18 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai ai-agents ai-assistant ai-coding-agent claude codex

AIScientists-Dev/WorldSeed

More is Different. A multi-agent world engine where AI agents live, talk, compete, ally.

Category
agent framework
Stars
809
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
15/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 91 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-based-simulation agentic-ai agents ai ai-agents autonomous-agents

victordibia/designing-multiagent-systems

Building LLM-Enabled Multi Agent Applications from Scratch

Category
agent framework
Stars
778
Readiness
needs review (62/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
25/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 148 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents autogen generative-ai large-language-models multiagent-systems

steel-dev/steel-browser

🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.

Category
agent framework
Stars
7,437
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +31 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents ai-tools browser-automation llm

judge0/judge0

Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.

Category
agent framework
Stars
4,360
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +16 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent-tools ai-agents ai-tools code-execution code-executor code-runner

liaohch3/claude-tap

Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.

Category
agent framework
Stars
2,982
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +54 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-debugging agent-observability ai-agents ai-tools api-debugging claude-code

qingchencloud/clawpanel

🦞 OpenClaw & Hermes Agent 多引擎 AI 管理面板 — 内置 AI 助手（工具调用 + 图片识别 + 多模态），一键安装 | Tauri v2 跨平台桌面应用 | 11 种语言

Category
agent framework
Stars
2,917
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +12 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

admin-panel ai-agent ai-assistant ai-chat ai-tools chatgpt

Unclecheng-li/VulnClaw

基于 AI Agent + MCP 工具链 + 渗透 Skill 编排， 配合大语言模型， 自然语言输入 → 自动完成「信息收集 → 漏洞发现 → 漏洞利用 → 报告生成」全流程。

Category
agent framework
Stars
2,624
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +245 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-tools ctf cybersecurity openclaw

webfuse-com/awesome-autoresearch

A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.

Category
agent framework
Stars
2,355
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +13 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-systems ai-agents ai-research ai-tools autonomous-agents autoresearch

Anil-matcha/ai-creator-academy

Free, open-source curriculum for making money with generative AI image, video, and audio — for creators and agencies.

Category
agent framework
Stars
1,921
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +19 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents ai-audio ai-avatars ai-filmmaking ai-image

fcakyon/claude-codex-settings

Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

Category
agent framework
Stars
1,013
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +146 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-tools claude-ai claude-code claude-code-plugin claude-skills

tomasz-tomczyk/crit

Your feedback loop with the agent

Category
agent framework
Stars
873
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +21 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-coding ai-agents ai-tools cli code-review developer-tools

ai-for-developers/awesome-vibe-coding

A hand-picked collection of tools and resources for Vibe Coding

Category
agent framework
Stars
809
Readiness
ready (77/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents ai-app-builder ai-ide ai-tools awesome-ai

taracodlabs/aiden

Aiden — Autonomous AI agent that operates your computer with prompts: browser control, terminal execution, workflows, tools, recovery systems, and persistent memory. Built solo. AGPL-3.0.

Category
agent framework
Stars
776
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +9 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentskills ai ai-agents ai-os ai-skills ai-tools

VersusControl/versus-incident

Versus Incident is the self-hosted AI SRE agent. It learns what your system normally look like and escalates only what is new or unexpected issues — routing to your chat channels and on-call platform.

Category
agent framework
Stars
716
Readiness
ready (96/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +11 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-tools alert aws devops

rlaope/oh-my-hermes

Just install once. Anyone can use hermes-agent professionally. the powerful intelligence and memory system for your agent ⚚

Category
agent framework
Stars
695
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai ai-agent ai-tools claude-code codex

best-of-ai/best-of-ai

A curated list of best ai tools

Category
agent framework
Stars
693
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +11 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-agents ai-assistant ai-chatbot ai-engineering

ShaikhWarsi/free-ai-tools

Curated list of free and low cost AI tools, LLM APIs, IDEs, agents, and infrastructure for building real AI apps

Category
agent framework
Stars
675
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +31 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents ai-directory ai-tools ai-tools-directory ai-tools-list

alirezarezvani/claude-code-skill-factory

Claude Code Skill Factory — A powerful open-source toolkit for building and deploying production-ready Claude Skills, Code Agents, custom Slash Commands, and LLM Prompts at scale. Easily generate stru

Category
agent framework
Stars
843
Readiness
needs review (59/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 268 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-tools claude-ai claude-code claude-skills claude-skills-creator

Mintplex-Labs/openai-assistant-swarm

Introducing the Assistant Swarm. An extension to the OpenAI Node SDK to automatically delegate work to any assistant you create in OpenAi through one united interface and manager. Now you can delegate

Category
agent framework
Stars
615
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 994 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents ai-agents-framework ai-assistant ai-tools autogpt

momozi1996/awesome-ai-persona-skills

全网最全的、持续更新的、最火爆的 100+ 人格 蒸馏skills 合集｜ 多agent系统 ｜名人/导演/天涯大神/古籍/二次元/职场/情感全品类

Category
agent framework
Stars
510
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +23 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-skills agentic agents ai ai-agents

angelnicolasc/graymatter

Three lines of code to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.

Category
agent framework
Stars
450
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-memory ai-agents ai-tools claude-code cli go

Charlie85270/Dorothy

Dorothy, the wife your AI agents needs.

Category
agent framework
Stars
330
Readiness
ready (75/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents ai-tools orchestration

geekjourneyx/jina-cli

A lightweight CLI tool wrapping Jina AI Reader API for AI Agents. Fetch and parse any URL into LLM-friendly formats (Markdown/Text/HTML). Perfect for reading X(Twitter), blogs, and news sites.

Category
agent framework
Stars
307
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
27/100 · low confidence

Why: +4 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 159 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-tools claude-code cli jina-ai-reader openclaw

vizra-ai/vizra-adk

Build, test, and deploy intelligent AI agents the Laravel way

Category
agent framework
Stars
296
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai ai-agents ai-tools anthropic autonomous-agents

kwalus/Canopy

A local-first, encrypted Slack/Discord alternative built for the agentic era. AI agents, such as openclaw, join channels, receive tasks, and coordinate on equal footing with humans — over a serverless

Category
agent framework
Stars
295
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills agentic-ai agentic-framework agentic-systems agentic-workflow ai

princezuda/safestclaw

Safestclaw is the alternative to openclaw.. You can naturally chat with it via text and voice, and you can choose not to use a language model., By default it picks up on intent and semantics.. No pro

Category
agent framework
Stars
281
Readiness
needs review (62/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai ai ai-agent ai-assistant ai-tools openclaw

Agentic-Systems-Lab/rigorous

A comprehensive suite of tools, built to liberate science by making the creation, evaluation, and dissemination of research more transparent, affordable, and efficient.

Category
agent framework
Stars
251
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 364 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

academic-paper academic-writing ai-agents ai-tools llm manuscript-analyses

kayba-ai/recursive-improve

🪞 Make your agents recursively self-improve

Category
agent framework
Stars
242
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
21/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 129 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-learning agents ai ai-agent ai-tools llm

bitloops/bitloops

Give AI coding agents the context they need to ship production-quality software.

Category
agent framework
Stars
235
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-agents ai-assistant ai-infra ai-infrastructure

cairn-dev/cairn

A background agent system for automating end-to-end software engineering tasks, direct from your github repos.

Category
agent framework
Stars
214
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: issue load, documentation, license. Risks: no push in 401 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-tools background-agent github-integrations open-source python

kstevica/captain-claw

Self-hosted framework for orchestrating fleets of specialist AI agents — ensemble reasoning and a full agentic coding pipeline, model-agnostic and local-friendly.

Category
agent framework
Stars
161
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-orchestration agentic-coding agentic-workflow ai-agent ai-agents anthropic

darrenhinde/OpenAgentsControl

AI agent framework for plan-first development workflows with approval-based execution. Multi-language support (TypeScript, Python, Go, Rust) with automatic testing, code review, and validation built f

Category
agent framework
Stars
4,693
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +29 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-agents-framework ai-t automation code-generation code-validation

0xNyk/council-of-high-intelligence

Structured multi-perspective deliberation for hard decisions. Run full councils, focused triads, or duo debates across Claude Code, Codex, Gemini CLI, and OpenCode.

Category
agent framework
Stars
3,828
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +27 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skill ai-agents claude-code codex decision-making deliberation

microsoft/apm

Agent Package Manager

Category
agent framework
Stars
3,483
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +73 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents claude-code codex-cli context-engineering github-copilot package-manager

UditAkhourii/adhd

ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deep

Category
agent framework
Stars
3,376
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +404 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

adhd agents ai ai-agents brainstorm chain-of-thought

Forward-Future/loopy

A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

Category
agent framework
Stars
2,983
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +50 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills agentic-workflows ai-agents automation codex prompt-engineering

foryourhealth111-pixel/Vibe-Skills

VibeSkills is a general-purpose Skill that automatically routes local Skills and intelligently orchestrates harness workflows.

Category
agent framework
Stars
2,637
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +86 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-skills agentic-coding ai-agents ai-scientist ai-skills

4thfever/cultivation-world-simulator

基于 AI Agent 工作流的修仙世界模拟器，旨在还原智能、开放的仙侠世界。| An open-source Cultivation World Simulator using Agentic Workflow to create a dynamic, emerging Xianxia world.

Category
agent framework
Stars
2,003
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +11 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-workflow ai ai-agents ai-native autonomous-agents cultivation

promptise-com/Foundry

The foundation layer for agentic intelligence.

Category
agent framework
Stars
863
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-runtime agentic-ai agents ai ai-agents

russelleNVy/three-man-team

A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files.

Category
agent framework
Stars
896
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills agent-workflow ai-agents claude context-files developer-tools

AgnosticUI/agnosticui

AgnosticUI Local (v2) is a CLI-based UI component library that copies components directly into your project. Works with AI tools, agent-driven UIs, and prompt-ready workflows.

Category
agent framework
Stars
822
Readiness
needs review (66/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

accessibility agent-skills ai-agents context-engineering css generative-ui

yzhao062/agent-style

21 writing rules for AI coding and writing agents. Drop-in for Claude Code, Codex, Copilot, Cursor, and Aider, so their output reads like a tech pro.

Category
agent framework
Stars
613
Readiness
high risk (43/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +14 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents llm prompt-engineering style-guide technical-writing writing-style

bakiraa/qyvaria-hardlogic-kernel-engine

Top Open-Source AI Engineering Platform 2026 Qyvaria Kernel

Category
agent framework
Stars
151
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-runtime agentic-ai ai-agents ai-bios ai-framework ai-kernel

cubeplexai/cubepi

CubePi — An async-first Python agent kernel inspired by Pi, built for coding agents, tools, and continuous sessions.

Category
agent framework
Stars
35
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai ai-agents ai-framework anthropic langgraph langgraph-alternative

sendbird/delight-ai-agent

Sendbird AI-Agent

Category
agent framework
Stars
21
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent-framework ai-agents ai-chat ai-chatbot ai-chatbots

fb0sh/pentester

基于 AI Agent 的渗透测试自动化框架，严格遵循 PTES（Penetration Testing Execution Standard）标准，覆盖渗透测试全生命周期。| An automated penetration testing framework based on AI agents strictly adheres to the PTES (Penetration Testing

Category
agent framework
Stars
20
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-framework pentest pentest-tool

bearded-illirian/trailmark

Artifact-first agent framework — disciplined skill chain for AI-driven multi-step engineering tasks. MIT.

Category
agent framework
Stars
19
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-orchestration ai-framework artifact-first claude-code developer-tools engineering-productivity

Djtony707/TITAN

Building TITAN — the open-source AI operating system for trusted autonomous work: agents, tools, memory, approvals, receipts, voice, mission control, and SOMA. npm i -g titan-agent

Category
agent framework
Stars
18
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework ai ai-agents ai-framework amthropic

caioimori/sinapse-ai

Governed AI agent orchestration for Claude Code and Codex: 17 squads, 172 agents, software delivery workflows.

Category
agent framework
Stars
13
Readiness
ready (79/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-orchestration ai-agents ai-framework automation claude-code cli

aksika/abtars

Agent harness with frontier persistent memory, skills, scheduled tasks, extended messaging connectivity, self-healing supervision, and distributed multi-agent collaboration. Pi harness integration

Category
agent framework
Stars
8
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

abmind abtars agent-harness agent-security agent-swarm agentic-ai

leprachuan/Wee-Orchestrator

🍀 Self-hosted multi-agent AI orchestrator — chat with Claude, Gemini & Copilot CLI from Telegram, WebEx, or browser. 5 runtimes, 17+ models, task scheduling, skill plugins.

Category
agent framework
Stars
7
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-framework automation chatbot claude copilot

halo-dev/plugin-ai-foundation

Halo 官方 AI 能力平台，统一接入主流大模型，为插件生态提供文本生成、嵌入向量、工具调用等智能化能力。

Category
agent framework
Stars
6
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents ai-framework halo halo-plugin

MunnaXbadmash/ai-dev-assistant-framework

A plug-and-play framework for AI-assisted software development, enhancing context-aware collaboration in complex codebases. Perfect for tools like GitHub Copilot. 🐙✨

Category
agent framework
Stars
5
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-agents-framework ai-framework ai-governance claude-ai

open-multi-agent/open-multi-agent

TypeScript AI agent orchestration framework with dynamic workflows. Describe the goal, not the graph: a coordinator plans the task DAG at runtime and runs it on any LLM (Claude, ChatGPT, Gemini, DeepS

Category
agent framework
Stars
6,737
Readiness
ready (100/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +47 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-orchestration agentic-ai ai-agents anthropic claude

jnMetaCode/agency-orchestrator

🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 267 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id/ar) · zero-code YAML · auto-verified acceptance · Web Studi

Category
agent framework
Stars
2,008
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +47 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agency-agents agent-orchestration ai-agents autogen-alternative claude codex

microsoft/agent-governance-toolkit

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

Category
agent framework
Stars
5,764
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +233 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agents ai-safety compliance governance microsoft

xyaz1313/phoenix

不死鸟 Phoenix — Hermes Agent 插件：路由分档/风险防线/自愈/存档点提醒/审批策略自适应，官方钩子接入，不改 Hermes 核心代码

Category
agent framework
Stars
150
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agent ai-safety chinese claude hermes-agent

OrlojHQ/orloj

An orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and governs them for production-grade operation.

Category
agent framework
Stars
113
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agentic-ai agentic-orchestration ai ai-agents ai-governance

JKHeadley/instar

Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.

Category
agent framework
Stars
75
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-identity agent-infrastructure agent-memory agent-skills ai-agents

AbuZar-Ansarii/PocketStrike-AI

Turn Android Termux into an autonomous AI agent and security orchestrator. Powered by a local ReAct framework with 50 system tools and MCP support, a background task │ scheduler, on-device ADB contr

Category
agent framework
Stars
52
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-agents ai-coding ai-safety ai-tools

swarm-ai-research/swarm

SWARM: System-Wide Assessment of Risk in Multi-agent systems

Category
agent framework
Stars
39
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 30 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agi-safety ai ai-agent ai-agents ai-safety alignment

666ghj/BettaFish

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

Category
agent framework
Stars
41,975
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +68 stars in 7 days; 22 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity; open issue backlog is stable or shrinking

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

agent-framework data-analysis deep-research deep-search llms multi-agent-system

pydantic/pydantic-ai

AI Agent Framework, the Pydantic way

Category
agent framework
Stars
19,133
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +201 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework genai llm pydantic python

eigent-ai/eigent

Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex

Category
agent framework
Stars
14,812
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +103 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-skills agentic-ai agentic-workflow claude-cowork claude-cowork-alternative

microsoft/agent-framework

A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.

Category
agent framework
Stars
12,668
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +150 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agentic-ai agents ai dotnet multi-agent

rllm-org/rllm

Democratizing Reinforcement Learning for LLMs

Category
agent framework
Stars
5,770
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +20 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agentic-workflow coding-agent distributed-training llm-reasoning llm-training

agentscope-ai/agentscope-java

Build distributed, production-grade, long-running agents.

Category
agent framework
Stars
4,949
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +117 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

adk agent agent-framework agentic agentic-ai agentscope

ag2ai/ag2

AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

Category
agent framework
Stars
4,839
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +17 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a ag2 agent-framework agentic agentic-ai ai

yomorun/yomo

🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra.

Category
agent framework
Stars
1,920
Readiness
ready (79/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a-protocol agent-framework claude-code distributed-cloud function-calling geodistributedsystems

agentjido/jido

🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows.

Category
agent framework
Stars
1,797
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +17 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agents core elixir elixir-package event-driven-architecture

trpc-group/trpc-agent-go

A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.

Category
agent framework
Stars
1,647
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +34 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a a2a-protocol ag-ui agent agent-framework ai

AgentEra/Agently

[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow *T

Category
agent framework
Stars
1,636
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-based-framework agent-framework chatglm claude deepseek

codeaholicguy/ai-devkit

The control plane for AI coding agents.

Category
agent framework
Stars
1,576
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +9 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-skills ai ai-agents ai-coding antigravity

ThousandBirdsInc/chidori

The agent framework where every run is durable, replayable, and resumable by default.

Category
agent framework
Stars
1,362
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agents ai checkpointing deterministic durable-execution

inkeep/agents

Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.

Category
agent framework
Stars
1,355
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +20 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-builder agent-framework agents-sdk ai ai-agent

Team-Commonly/commonly

Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infra — no per-agent fees.

Category
agent framework
Stars
1,285
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-harness agent-protocol agentic agentic-ai agents

wanxingai/LightAgent

LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and workflows.

Category
agent framework
Stars
1,199
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-hooks agents ai-agent lifecycle-hooks llm

agentlas-ai/Agentlas-OS

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

Category
agent framework
Stars
1,140
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +9 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a agent agent-framework agent-os-desktop agent-skills agentic-ai

Rath-Team/OpenRath

An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.

Category
agent framework
Stars
1,098
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agentic-ai ai-agents anthropic lllm-agent llm

vstorm-co/pydantic-deepagents

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pyd

Category
agent framework
Stars
1,019
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agents anthropic claude-code cli coding-agent

ShenSeanChen/waku-agent

Waku Waku! Waku agent is your personal AI agent, on your own laptop, in code you can read in an afternoon — harness + loop + memory + eval

Category
agent framework
Stars
962
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +298 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agent ai-assistant claude evals llm

Human-Agent-Society/CORAL

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared memory, and multi-agent evolution. Accepted at COLM 2026.

Category
agent framework
Stars
877
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +14 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-orchestration agentic-ai ai-agents alpha-evolve autonomous-agents

go-kratos/blades

Blades is a Go-based multimodal AI Agent framework.

Category
agent framework
Stars
806
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework agent-kit agent-sdk agent-workflow ai

crabtalk/crabtalk

Agents daemon that hides nothing

Category
agent framework
Stars
717
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-runtime ai ai-agent composable developer-tool

lofcz/LLMTornado

The .NET library to build AI agents with 30+ built-in connectors.

Category
agent framework
Stars
632
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a agent agent-framework agent-orchestration agent2agent agentic-ai

aeonfun/aeon

The most autonomous agent framework. No approval loops. No babysitting. Configure once, forget forever.

Category
agent framework
Stars
616
Readiness
ready (100/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +34 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agents ai ai-agents anthropic claude

framerslab/agentos

TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.

Category
agent framework
Stars
613
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-memory agentic-ai ai-agent-framework ai-agents autonomous-agents

RyanAlberts/best-of-Agent-Harnesses

🏆 Curated, ranked list of AI agent harnesses (100+) — plus an MCP server, llms.txt & JSON so agents can recommend them too. Rescored weekly.

Category
agent framework
Stars
497
Readiness
ready (75/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +63 stars in 7 days; 36 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity

Strongest signals: push recency, commit activity, issue load. Risks: maintenance is concentrated in one contributor. Missing inputs: release recency.

agent-framework agent-harness agentic-ai agents ai-agent ai-agent-framework

GizClaw/flowcraft

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.

Category
agent framework
Stars
483
Readiness
ready (77/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: 50 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity; open issue backlog is stable or shrinking

Strongest signals: push recency, commit activity, issue load. Risks: maintenance is concentrated in one contributor. Missing inputs: release recency.

agent-framework agent-runtime agents ai ai-agents anthropic

Ikalus1988/MisakaNet

📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. Python stdlib only. | https://misakanet.org

Category
agent framework
Stars
419
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +78 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, response activity.

agent-framework agent-network ai-agent claude devops distributed-memory

mnemon-dev/mnemon

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with Claude Code, OpenClaw, and any CLI agent.

Category
agent framework
Stars
396
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-memory ai-agent ai-tools claude claude-code

agenvoy/Agenvoy

Make AI actually work for you - A personal agent that writes its own tools and repairs itself.

Category
agent framework
Stars
370
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +11 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai ai-agents claude codex deepseek

DougTrajano/pydantic-ai-skills

This package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills.

Category
agent framework
Stars
357
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-skills agentic-ai ai-agents claude-code pydantic-ai

shibing624/agentica

Build AI agents that run for hours, not seconds. Async-first Python harness: auto context-compaction, cost budgets & death-spiral guards, persistent cross-session memory, self-evolving SKILL.md, /goal

Category
agent framework
Stars
341
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework agentica agents ai-agent cli

Gloriaameng/Awesome-Agent-Harness

Agent Harness for Large Language Model Agents: A Survey. Survey on LLM agentharnessengineering with a taxonomy. 110+papers, 23 systems analyzed.

Category
agent framework
Stars
322
Readiness
ready (75/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework agent-harness awesome-list harness harness-engineering

xuiltul/animaworks

Organization-as-Code for autonomous AI agents. Brain-inspired memory that grows, consolidates, and forgets. Multi-model (Claude/Codex/Gemini/Cursor/Ollama).

Category
agent framework
Stars
253
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agents autonomous-agents brain-inspired claude forgetting

cortexkit/aft

Give your agent a proper IDE and OS. The sensorimotor cortex for coding agents (OpenCode + Pi), part of CortexKit: symbol-aware edits, semantic search, code health, fast grep/glob, bash compression, b

Category
agent framework
Stars
241
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +13 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai ai-agents ai-agents-framework opencode pi

zenml-io/kitaru

Record, replay, and improve AI agents in production, built on ZenML

Category
agent framework
Stars
229
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agents checkpoints durable-execution llm mcp

openma-ai/open-managed-agents

Open-source Claude Managed Agents API implementation and self-hosted Claude Tag-style agent runtime. Drop-in compatible; runs on Cloudflare Workers/Durable Objects or Node.js. Apache 2.0.

Category
agent framework
Stars
222
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +9 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-infrastructure agent-platform ai-agents anthropic-api anthropic-managed-agents

ranxi2001/zero2Agent

面向大厂Agent研发岗位求职的agent教程网站，涵盖技术路线与面试八股文

Category
agent framework
Stars
218
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +20 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework langraph learning llm

Zijian-Ni/awesome-ai-agents-2026

🤖 A curated list of AI Agent frameworks, tools, platforms, and resources for 2026 — the year agents went mainstream

Category
agent framework
Stars
216
Readiness
ready (98/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

2026 agent-framework ai ai-agents autonomous-agents awesome-list

huangjia2019/agent-design-patterns

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider, OpenHands, DeerFlow. Companion to Desig

Category
agent framework
Stars
210
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-architecture agent-design agent-framework agent-patterns agentic-architecture

DemonDamon/AgenticX

AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical m

Category
agent framework
Stars
206
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agentic-workflows ai-agent ai-orchestration chatbot desktop-app

vixues/LeAgent

Open-source desktop AI agent that gets work done — plans & self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in one self-hostable stack.

Category
agent framework
Stars
200
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework agent-skills agentic-ai agentic-workflow agents

livecontext-ai/livecontext-ce

The AI automation platform, self-hosted. Describe the job in chat and LiveContext builds it: readable workflows, scoped AI agents, and small apps your team uses. Chat, Workflow, Agent and App on one c

Category
agent framework
Stars
194
Readiness
ready (79/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agents ai ai-agents ai-automation automation

muxi-ai/muxi

Deploy intelligence. Open-source infrastructure for AI agents in production.

Category
agent framework
Stars
192
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a agent-framework agent-orchestration agent-server agentic-ai ai

XiaoConstantine/dspy-go

DSPy Go implementation

Category
agent framework
Stars
192
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agents ai dspy golang llms

beilusaiying/always-accompany

Companionship, chat, coding, and work share one memory and context framework — the kind of AI you see in science fiction: it keeps you company, and it gets things done with you.(这是一个基于上下文和注意力机制做的一个多元化

Category
agent framework
Stars
191
Readiness
ready (79/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework ai-agents ai-coding bot cli

EvoMap/awesome-agent-evolution

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

Category
agent framework
Stars
183
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

a2a agent-evolution agent-framework agent-protocol agentic-ai ai-agent

Shiyao-Huang/awesome-agent-evolution

Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.

Category
agent framework
Stars
175
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-evolution agent-framework agent-swarm ai-agent ai-agents ai-research

yologdev/yoagent

The agent loop for Rust — stream from 7 LLM protocols, run tools, loop until done.

Category
agent framework
Stars
173
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework ai ai-agents anthropic claude

aden-hive/hive

Multi-Agent Harness for Production AI

Category
agent framework
Stars
10,883
Readiness
needs review (60/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +57 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework agent-skills anthropic automation autonomous-agents

MiroMindAI/MiroThinker

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

Category
agent framework
Stars
8,367
Readiness
needs review (71/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework browsecomp deep-research futurex gaia

TencentCloudADP/youtu-agent

A simple yet powerful agent framework that delivers with open-source models

Category
agent framework
Stars
4,593
Readiness
high risk (43/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
23/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 139 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agents openai-agents python

MiroMindAI/MiroFlow

🏆 Top-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAI

Category
agent framework
Stars
3,087
Readiness
ready (72/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agents browsecomp claude deep-research futurex

open-gitagent/opengap

A framework-agnostic, git-native standard for defining AI agents

Category
agent framework
Stars
2,907
Readiness
needs review (70/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +13 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-framework agent-skills agents assistant claude-code

langfengQ/verl-agent

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

Category
agent framework
Stars
2,192
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +26 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework deepseek-r1 gigpo grpo large-language-models llm-agents

howl-anderson/agentsilex

A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.

Category
agent framework
Stars
453
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 217 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agent anthropic educational gemini hackable

aiming-lab/AutoHarness

AutoHarness: Automated Harness Engineering for AI Agents

Category
agent framework
Stars
365
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
21/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 127 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agents audit context-management governance harness-engineering

microsoft/Agent-Framework-Samples

Agent Framework Samples - showcasing ways in which agent framework can be utilized.

Category
agent framework
Stars
353
Readiness
needs review (66/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agents

opencmit/alphora

A Production-Ready Framework for Building Composable AI Agents

Category
agent framework
Stars
348
Readiness
needs review (70/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agents llm multi-agent-systems

fetchai/agents-aea

A framework for autonomous economic agent (AEA) development

Category
agent framework
Stars
240
Readiness
ready (74/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: fork interest, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aea agent agent-framework autonomous autonomous-agents autonomous-economic-agents

NeuZhou/awesome-ai-anatomy

Source code teardowns of 15 AI coding agents. What is actually inside Claude Code, Dify, OpenHands, Cline, MemPalace, oh-my-codex, Goose, Codex CLI, and 7 more. Architecture diagrams, design patterns.

Category
agent framework
Stars
236
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agent ai-security architecture awesome-list claude-code

Owl-Listener/designpowers

An agent design team you control: 10 agents that run an inclusive design process while you direct.

Category
agent framework
Stars
234
Readiness
needs review (71/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-orchestration agentic-ai ai ai-agents design

Ray-Code-Svg/SuperNovaAgent

SuperNova is a Windows-first desktop AI Workbench that turns chat into traceable tasks. It combines a Tauri + React Workbench, Rust Product Runtime, typed protocol, and Process Kernel so actions can p

Category
agent framework
Stars
209
Readiness
ready (77/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-orchestration desktop-application harness-engineering harness-framework windows

2417467487-hub/Trend2Video-Pro

Trend-to-Video Agent Framework for publish-ready short video packages

Category
agent framework
Stars
208
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agents ai-video chrome-extension content-automation content-execution

hertz-ai/HARTOS

An AI-native OS. Models run on your own hardware, nodes federate peer-to-peer with no broker, and the API is OpenAI-compatible. Boots, has its own Wayland compositor, and runs on 8GB. Apache 2.0.

Category
agent framework
Stars
50
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agentic-ai ai-agent ai-runtime chatbot computer-use

JasonColapietro/suede-creator-skills

71 open-source Agent Skills for Claude Code and Codex: Full Send orchestration, A-F code review, AI evals, CI gates, design, copy, SEO/AEO/GEO, Instagram growth, app shipping, creator rights, and cons

Category
agent framework
Stars
150
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-orchestration agent-skill agent-skills ai-agents ai-coding anthropic

GH05TCREW/pentestagent

PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.

Category
agent framework
Stars
2,898
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +43 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents ai-assistant ai-cybersecurity ai-hacking ai-security-tool

susyimes/android-agent-harness

Provider-neutral bounded agent runtime for Android/JVM: controlled context (trust/priority/budgets), profile-scoped tools, OpenAI-compatible live mode, governed-evolution eval, and a high-risk-pause d

Category
agent framework
Stars
33
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-harness ai-agent android deepseek kotlin

antgroup/Napaxi

Mobile-native agent SDK for building on-device AI agents with sandboxed execution, extensible tools, and x-app / x-agent / x-channel connectivity.

Category
agent framework
Stars
29
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai ai-agent android automation flutter

amajorai/ryu

The fully self-hostable, open composable platform for agent orchestration and human collaboration. With tools, security, memory, cost saving, and routing all built in.

Category
agent framework
Stars
35
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agents ai-orchestration byo llm llm-gateway

RikyZ90/ShibaClaw

🐕 Self-hosted security-first AI agent · 28 providers · 11 chat channels · WebUI · 3-level memory · task-schedule · automation · skills · MCP

Category
agent framework
Stars
79
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-agent ai-agents automation chatbot docker

asheshgoplani/agent-deck

Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

Category
agent framework
Stars
677
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +37 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-agents ai-coding-assistant aider bubble-tea claude-code

mixpeek/amux

Open-source control plane for AI coding agents — run, monitor & orchestrate dozens of parallel Claude Code, Codex & Gemini sessions from one web dashboard or your phone. Self-healing, single-file, tmu

Category
agent framework
Stars
335
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +14 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-orchestration agentic-ai ai-agents ai-coding-assistant anthropic automation

majiayu000/spellbook

Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.

Category
agent framework
Stars
257
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +16 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills ai-agent-skills ai-agents ai-coding-assistant automation claude

KbWen/agentic-os

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for C

Category
agent framework
Stars
117
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agent-orchestration agentic-development agents-md ai-agent ai-coding-assistant

ofekron/better-agent

Local web workspace for coding agents — Claude, Codex, Gemini, and more in one inspectable, LAN-ready hub.

Category
agent framework
Stars
53
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-orchestration ai-agents ai-coding-assistant claude-code codex coding-agents

5dive-ai/5dive

Run a company of AI agents on a server you own. Spin up named agents (claude, codex, pi…), put them on an org chart with a shared backlog, let them hand off work and ping your phone only when a human

Category
agent framework
Stars
38
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-runtime agentic-engineering agentic-loops agents ai-agents ai-assistant

tao12345666333/amcp

Out-of-the-box coding-agent runtime for terminal, IDE, server, and Telegram: built-in tools, subagents, skills, memory, MCP/ACP, hooks, and automation.

Category
agent framework
Stars
34
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-client-protocol ai-agent ai-coding-assistant autonomous-agents cli coding-agent

fujibee/agmsg

Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no daemon, no framework.

Category
agent framework
Stars
1,409
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +47 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-communication agent-teams agentic ai-agents bash claude-code

mco-org/mco

CLI-first orchestration for AI coding agents: run selected agents and models in parallel, compare raw answers, and coordinate review or implementation workflows.

Category
agent framework
Stars
476
Readiness
needs review (66/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: 10 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; open issue backlog is stable or shrinking

Strongest signals: push recency, issue load, documentation. Risks: maintenance is concentrated in one contributor. Missing inputs: None.

ai-agents ai-ide claude cli code-review codex

Agent-Field/SWE-AF

Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.

Category
agent framework
Stars
969
Readiness
ready (96/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +13 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-factory agentfield agentic-ai ai-agents ai-factory autonomous-agents

amilworks/ultra

AI research agents + scientific image viewer for bioimaging & neuroimaging — LangGraph agents, GPU inference, and native in-browser OME-Zarr / TIFF / NIfTI / HDF5 viewers.

Category
agent framework
Stars
6
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework agentic-ai autonomous-agents bioimaging chat-ui golang

dkedar7/langstage

The web stage for your LangGraph agent — self-hosted chat UI, file browser, canvas, and task board (MIT)

Category
agent framework
Stars
5
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ag-ui agent-ui agents ai-agents chat-ui deepagents

neocortex-link/neocortex-unity-sdk

Neocortex Unity SDK for Smart NPCs and Virtual Assistants

Category
agent framework
Stars
34
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-agents ai-tools aiagent aiagents

hgsanyang/SoulTuner-Agent

🎵 专属你的私人数字调音师|AI 音乐搜索推荐 Agent | 基于大模型 + 知识图谱 + 双模型声学向量的本地智能音乐推荐系统 | LLM-powered Music Recommendation Agent with Hybrid RAG, Neo4j, and Long-term Memory

Category
agent framework
Stars
17
Readiness
ready (99/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent audio-embedding hybrid-retrieval knowledge-graph langgraph llm-agent

white0dew/ViralSim

让一群 AI 用户先刷到你的笔记：模拟小红书图文的停留、阅读与互动，并用真实发布数据持续校准爆款概率。

Category
agent framework
Stars
10
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents content-analysis creator-tools multi-agent multimodal-ai nextjs

confused-ai/personaforge

TypeScript AI agent framework — 40+ LLM providers, 100+ tools, multi-agent orchestration, RAG, guardrails, circuit breakers, HITL, budget enforcement. Open-source CrewAI / LangChain alternative. — For

Category
agent framework
Stars
9
Readiness
ready (96/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal agent framework project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents agents-sdk agentskills ai ai-agents crewai-alternative

Kaelio/ktx

ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company

Category
agent framework
Stars
1,529
Readiness
ready (78/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agent-skills agents ai-agent ai-agents analytics