← OSS Radar home
Agent Framework AI repositories
OSS Radar projects in the agent framework category.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
- Category
- agent framework
- Stars
- 227,579
- Adoption
- safe (96%)
- Maintainer health
- healthy
Why: +2,764 stars in 7 days; 100 commits in 30 days
ai-agents anthropic claude claude-code developer-tools llm
The agent that grows with you
- Category
- agent framework
- Stars
- 211,854
- Adoption
- safe (96%)
- Maintainer health
- healthy
Why: +4,277 stars in 7 days; 100 commits in 30 days
ai ai-agent ai-agents anthropic chatgpt claude
Python tool for converting files and office documents to Markdown.
- Category
- agent framework
- Stars
- 164,215
- Adoption
- watch (68%)
- Maintainer health
- watch
Why: +1,974 stars in 7 days; 78 active contributors
autogen autogen-extension langchain markdown microsoft-office openai
The API to search, scrape, and interact with the web at scale. 🔥
- Category
- agent framework
- Stars
- 148,080
- Adoption
- safe (92%)
- Maintainer health
- healthy
Why: +5,157 stars in 7 days; 100 commits in 30 days
ai ai-agents ai-crawler ai-scraping ai-search crawler
The agent engineering platform.
- Category
- agent framework
- Stars
- 141,370
- Adoption
- safe (97%)
- Maintainer health
- healthy
Why: +657 stars in 7 days; 100 commits in 30 days
agents ai ai-agents anthropic chatgpt deepagents
An open-source AI agent that brings the power of Gemini directly into your terminal.
- Category
- agent framework
- Stars
- 105,859
- Adoption
- safe (95%)
- Maintainer health
- healthy
Why: +157 stars in 7 days; 50 commits in 30 days
ai ai-agents cli gemini gemini-api mcp-client
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
- Category
- agent framework
- Stars
- 103,853
- Adoption
- safe (94%)
- Maintainer health
- healthy
Why: +1,759 stars in 7 days; 100 commits in 30 days
ai-agents ai-tools browser-automation browser-use llm playwright
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
- Category
- agent framework
- Stars
- 84,667
- Adoption
- safe (94%)
- Maintainer health
- healthy
Why: +557 stars in 7 days; 100 commits in 30 days
agentic-ai agentic-retrieval agentic-search ai ai-agents context-engine
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
- 78,507
- Adoption
- safe (92%)
- Maintainer health
- healthy
Why: +7,517 stars in 7 days; 100 commits in 30 days
agent-skills ai-agents claude claude-code claude-code-plugin cursor-rules
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
- 76,574
- Adoption
- safe (95%)
- Maintainer health
- healthy
Why: +734 stars in 7 days; 100 commits in 30 days
agent agentic agentic-framework agentic-workflow ai ai-agents
🎨 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
- 76,507
- Adoption
- safe (94%)
- Maintainer health
- healthy
Why: +2,541 stars in 7 days; 100 commits in 30 days
agent-skills ai-agents ai-design byok claude-code-for-design claude-design
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
- Category
- agent framework
- Stars
- 76,317
- Adoption
- watch (52%)
- Maintainer health
- watch
Why: 100 active contributors
agent agents ai-agents chatgpt deep-learning generative-ai
🗂 The essential checklist for modern web development, for humans and AI agents
- Category
- agent framework
- Stars
- 73,156
- Adoption
- watch (65%)
- Maintainer health
- healthy
Why: +64 stars in 7 days; 100 active contributors
ai-agent ai-agents checklist css front-end-developer-tool front-end-development
Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code
- Category
- agent framework
- Stars
- 72,255
- Adoption
- safe (85%)
- Maintainer health
- healthy
Why: 86 commits in 30 days; 100 active contributors
agentic-workflow ai ai-agents ai-runtime ai-sandboxes code-execution
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
- Category
- agent framework
- Stars
- 70,429
- Adoption
- safe (89%)
- Maintainer health
- healthy
Why: +880 stars in 7 days; 25 commits in 30 days
agent agent-development ai-agent claude claude-code educational
12 Lessons to Get Started Building AI Agents
- Category
- agent framework
- Stars
- 68,902
- Adoption
- safe (100%)
- Maintainer health
- healthy
Why: +523 stars in 7 days; 100 commits in 30 days
agentic-ai agentic-framework agentic-rag ai-agents ai-agents-framework autogen
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
- Category
- agent framework
- Stars
- 67,242
- Adoption
- watch (52%)
- Maintainer health
- watch
Why: +1,914 stars in 7 days; 28 active contributors
agent-skills ai-agents antigravity automation claude claude-code
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
- 65,359
- Adoption
- safe (93%)
- Maintainer health
- healthy
Why: +818 stars in 7 days; 100 commits in 30 days
ai ai-agents anthropic chatgpt claude claude-skills
🌊 The leading agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RA
- Category
- agent framework
- Stars
- 63,645
- Adoption
- safe (95%)
- Maintainer health
- healthy
Why: +1,140 stars in 7 days; 100 commits in 30 days
agentic-ai agentic-framework agentic-workflow agents ai-agents ai-assistant
from vibe coding to agentic engineering - practice makes claude perfect
- Category
- agent framework
- Stars
- 62,322
- Adoption
- safe (84%)
- Maintainer health
- healthy
Why: +525 stars in 7 days; 100 commits in 30 days
agentic-ai agentic-coding agentic-engineering agentic-workflow ai ai-agents
Universal memory layer for AI Agents
- Category
- agent framework
- Stars
- 60,463
- Adoption
- safe (94%)
- Maintainer health
- healthy
Why: +551 stars in 7 days; 100 commits in 30 days
agents ai ai-agents application chatbots chatgpt
Open-source AI job search: scan job portals, score listings A-F, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Gemini, Codex, OpenCode…)
- Category
- agent framework
- Stars
- 59,255
- Adoption
- safe (98%)
- Maintainer health
- healthy
Why: +2,003 stars in 7 days; 100 commits in 30 days
ai ai-agent anthropic ats automation beginner-friendly
Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full
- Category
- agent framework
- Stars
- 412
- Adoption
- safe (73%)
- Maintainer health
- healthy
Why: +194 stars in 30 days; 100 commits in 30 days
agent-framework ai-agents ai-platform apple-silicon data-sovereignty distributed-computing
Unified LangChain documentation.
- Category
- agent framework
- Stars
- 372
- Adoption
- safe (84%)
- Maintainer health
- healthy
Why: +5 stars in 7 days; 100 commits in 30 days
documentation langchain langgraph langsmith
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
- 366
- Adoption
- safe (94%)
- Maintainer health
- healthy
Why: +7 stars in 7 days; 56 commits in 30 days
ai-agents aiops automation aws azure datadog
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
- 375
- Adoption
- safe (95%)
- Maintainer health
- healthy
Why: +5 stars in 7 days; 100 commits in 30 days
agent-framework agent-memory ai-agent ai-tools claude claude-code
Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.
- Category
- agent framework
- Stars
- 363
- Adoption
- safe (79%)
- Maintainer health
- healthy
Why: +3 stars in 7 days; 85 commits in 30 days
ai-agents ai-safety anthropic audit-trail langchain llm-observability
Explore the unknown, build the future, own your data.
- Category
- agent framework
- Stars
- 454
- Adoption
- safe (82%)
- Maintainer health
- healthy
Why: +3 stars in 7 days; 100 commits in 30 days
agents ai ai-agents artificial-intelligence ide llm-inference
Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.
- Category
- agent framework
- Stars
- 383
- Adoption
- safe (84%)
- Maintainer health
- healthy
Why: +21 stars in 7 days; 19 commits in 30 days
aarm agent-security agentic-ai agentic-security agents ai
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
- 491
- Adoption
- safe (76%)
- Maintainer health
- healthy
Why: +1 stars in 7 days; 29 commits in 30 days
agent-framework agent-runtime agents ai ai-agents anthropic
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
- Category
- agent framework
- Stars
- 76,317
- Adoption
- watch (52%)
- Maintainer health
- watch
Why: 100 active contributors
agent agents ai-agents chatgpt deep-learning generative-ai
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
- Category
- agent framework
- Stars
- 67,242
- Adoption
- watch (52%)
- Maintainer health
- watch
Why: +1,914 stars in 7 days; 28 active contributors
agent-skills ai-agents antigravity automation claude claude-code
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
- 41,682
- Adoption
- watch (60%)
- Maintainer health
- watch
Why: +214 stars in 7 days; 36 active contributors
agent-framework data-analysis deep-research deep-search llms multi-agent-system
Vane is an AI-powered answering engine.
- Category
- agent framework
- Stars
- 35,614
- Adoption
- watch (52%)
- Maintainer health
- watch
Why: 48 active contributors
ai-agents ai-search-engine answering-engine artificial-intelligence llm machine-learning
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
- 34,001
- Adoption
- watch (53%)
- Maintainer health
- watch
Why: +548 stars in 7 days; 7 active contributors
ai-agents genai
Get 10X more out of Claude Code, Codex or any coding agent
- Category
- agent framework
- Stars
- 27,315
- Adoption
- watch (52%)
- Maintainer health
- watch
Why: 61 active contributors
agent ai-agents kanban management task-manager