← OSS.Radar home
Powered by aegismemory.com · Aegis Memory repository
Rag And Search AI repositories
OSS Radar projects in the rag and search category.
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
- Category
- rag and search
- Stars
- 71,570
- Readiness
- ready (83/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · high confidence
Why: +1,754 stars in 7 days; 23 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.
agent llm rag tutorial
Something wrong? Category · Trend · Risk
Universal memory layer for AI Agents
- Category
- rag and search
- Stars
- 62,785
- Readiness
- ready (95/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · high confidence
Why: +575 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 application chatbots chatgpt
Something wrong? Category · Trend · Risk
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
- Category
- rag and search
- Stars
- 38,621
- Readiness
- ready (93/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · high confidence
Why: +230 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.
genai gpt gpt-4 graphrag knowledge-graph large-language-models
Something wrong? Category · Trend · Risk
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI
- Category
- rag and search
- Stars
- 36,382
- Readiness
- needs review (66/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- healthy
- Maintenance risk
- 18/100 · high confidence
Why: +248 stars in 7 days; 73 lifetime contributors
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: push recency, contributor breadth, issue load. Risks: recent commit cadence is 2/8.8 of its monthly baseline. Missing inputs: None.
agent ai assistant chat chatgpt emacs
Something wrong? Category · Trend · Risk
A modular graph-based Retrieval-Augmented Generation (RAG) system
- Category
- rag and search
- Stars
- 35,320
- Readiness
- ready (81/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · high confidence
Why: +196 stars in 7 days; 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, contributor breadth, issue load. Risks: None identified. Missing inputs: None.
gpt gpt-4 gpt4 graphrag llm llms
Something wrong? Category · Trend · Risk
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
- Category
- rag and search
- Stars
- 35,068
- Readiness
- ready (91/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · high confidence
Why: +132 stars in 7 days; 42 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.
agentic-ai agents ai ai-agents context-engineering information-retrieval
Something wrong? Category · Trend · Risk
📚 从零开始构建大模型
- Category
- rag and search
- Stars
- 32,720
- Readiness
- needs review (61/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- healthy
- Maintenance risk
- 8/100 · high confidence
Why: +190 stars in 7 days; 27 lifetime contributors
Why it may be a gem: limited evidence; inspect maintenance signals before adopting
Strongest signals: push recency, contributor breadth, issue load. Risks: no pull-request review responses in 30 days. Missing inputs: None.
agent llm rag
Something wrong? Category · Trend · Risk
Python scraper based on AI
- Category
- rag and search
- Stars
- 29,190
- Readiness
- ready (81/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +348 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-crawler ai-scraping ai-search crawler data-extraction firecrawl-alternative
Something wrong? Category · Trend · Risk
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
- Category
- rag and search
- Stars
- 28,978
- Readiness
- ready (80/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +88 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-rag ai embeddings generative-ai gpt langchain
Something wrong? Category · Trend · Risk
Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, an
- Category
- rag and search
- Stars
- 59,104
- Readiness
- needs review (58/100 heuristic points; not a probability)
- Data confidence
- medium
- Maintainer health
- watch
- Maintenance risk
- 0/100 · high confidence
Why: +174 stars in 7 days; 24 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: None identified. Missing inputs: release recency.
chatbot hugging-face llm llm-local llm-prompting llm-security
Something wrong? Category · Trend · Risk
Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore:
- Category
- rag and search
- Stars
- 39,392
- Readiness
- high risk (44/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- risky
- Maintenance risk
- 42/100 · high confidence
Why: +20 stars in 7 days; 100+ lifetime contributors
Why it may be a gem: limited evidence; inspect maintenance signals before adopting
Strongest signals: contributor breadth, issue load, documentation. Risks: no push in 394 days, latest release is 549 days old. Missing inputs: None.
Capped lower bounds: lifetime contributors.
ai api chatbot chatgpt database docker
Something wrong? Category · Trend · Risk
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Ll
- Category
- rag and search
- Stars
- 38,523
- Readiness
- needs review (51/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- risky
- Maintenance risk
- 50/100 · high confidence
Why: +35 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 270 days, latest release is 756 days old, no pull-request review responses in 30 days. Missing inputs: None.
Capped lower bounds: lifetime contributors.
chatbot chatchat chatglm chatgpt embedding faiss
Something wrong? Category · Trend · Risk
Vane is an AI-powered answering engine.
- Category
- rag and search
- Stars
- 36,040
- Readiness
- needs review (52/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- watch
- Maintenance risk
- 38/100 · high confidence
Why: +107 stars in 7 days; 48 lifetime contributors
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: contributor breadth, issue load, documentation. Risks: no push in 118 days, recent commit cadence is 0/8.4 of its monthly baseline. Missing inputs: None.
ai-agents ai-search-engine answering-engine artificial-intelligence llm machine-learning
Something wrong? Category · Trend · Risk
🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄.
- Category
- rag and search
- Stars
- 23,823
- Readiness
- high risk (0/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- risky
- Maintenance risk
- 100/100 · high confidence
Why: 71 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: repository is archived, no push in 186 days, 291 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 ai data-visualization database llm rag
Something wrong? Category · Trend · Risk
✅（已完结）超级全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】
- Category
- rag and search
- Stars
- 23,203
- Readiness
- high risk (33/100 heuristic points; not a probability)
- Data confidence
- medium
- Maintainer health
- watch
- Maintenance risk
- 34/100 · high confidence
Why: +143 stars in 7 days
Why it may be a gem: open issue backlog is stable or shrinking
Strongest signals: issue load, documentation. Risks: recent commit cadence is 0/4.2 of its monthly baseline, no pull-request review responses in 30 days, no maintainer response activity in 30 days. Missing inputs: release recency.
agent agents book chinese computer-vision cv
Something wrong? Category · Trend · Risk
Unified framework for building enterprise RAG pipelines with small, specialized models
- Category
- rag and search
- Stars
- 14,858
- Readiness
- needs review (59/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- Maintenance risk
- 0/100 · low confidence
Why: +42 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.
agents generative-ai-tools llamacpp llm onnx openvino
Something wrong? Category · Trend · Risk
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
- Category
- rag and search
- Stars
- 12,963
- Readiness
- needs review (61/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- Maintenance risk
- 0/100 · low confidence
Why: +10 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.
bert compression distributed-training document-intelligence embedding ernie
Something wrong? Category · Trend · Risk
Retrieval and Retrieval-augmented LLMs
- Category
- rag and search
- Stars
- 12,031
- Readiness
- needs review (52/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- Maintenance risk
- 18/100 · low confidence
Why: +31 stars in 7 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 107 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings information-retrieval llm retrieval-augmented-generation sentence-embeddings text-semantic-similarity
Something wrong? Category · Trend · Risk
Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/
- Category
- rag and search
- Stars
- 11,979
- 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 rag and search 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 302 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai chatgpt embeddings fedramp generative gpt
Something wrong? Category · Trend · Risk
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
- Category
- rag and search
- Stars
- 8,123
- Readiness
- needs review (53/100 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 392 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
aigc autogpt babyagi chatbot chatgpt chatgpt-api
Something wrong? Category · Trend · Risk
每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈
- Category
- rag and search
- Stars
- 7,108
- Readiness
- needs review (54/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- Maintenance risk
- 0/100 · low confidence
Why: +52 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 interview-practice interview-questions learnllm llm rag
Something wrong? Category · Trend · Risk
Postgres with GPUs for ML/AI apps.
- Category
- rag and search
- Stars
- 6,817
- 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 7 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 402 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai ann approximate-nearest-neighbor-search artificial-intelligence classification clustering
Something wrong? Category · Trend · Risk
Open-source context retrieval layer for AI agents
- Category
- rag and search
- Stars
- 6,542
- Readiness
- needs review (55/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- 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: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agent-infrastructure ai ai-agents ai-infrastructure api context-retrieval
Something wrong? Category · Trend · Risk
Large Action Model framework to develop AI Web Agents
- Category
- rag and search
- Stars
- 6,383
- Readiness
- needs review (53/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · 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: no push in 563 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai browser large-action-model llm oss rag
Something wrong? Category · Trend · Risk
Easiest and laziest way for building multi-agent LLMs applications.
- Category
- rag and search
- Stars
- 3,866
- Readiness
- ready (92/100 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.
agents ai-agent data deep-learning documentation-tool finetuning
Something wrong? Category · Trend · Risk
Open-source AI Agent Customer Service Platform. Build AI agent teams with LLM orchestration, RAG knowledge base, multi-channel support, and human collaboration.
- Category
- rag and search
- Stars
- 575
- Readiness
- needs review (50/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- Maintenance risk
- 17/100 · 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 101 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai-agent artificial-intelligence chatbot customer-service customer-support llm
Something wrong? Category · Trend · Risk
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Cla
- Category
- rag and search
- Stars
- 90,008
- Readiness
- ready (91/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · high confidence
Why: +847 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: maintenance is concentrated in one contributor. Missing inputs: None.
Capped lower bounds: 30-day commits, lifetime contributors, response activity.
ai ai-agents ai-memory anthropic artificial-intelligence chromadb
Something wrong? Category · Trend · Risk
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
- rag and search
- Stars
- 87,042
- Readiness
- ready (91/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · high confidence
Why: +523 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-harness agentic-ai agentic-retrieval agentic-search ai ai-agents
Something wrong? Category · Trend · Risk
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
- Category
- rag and search
- Stars
- 32,982
- Readiness
- ready (94/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · high confidence
Why: +1,429 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-tutor clawdbot cli-tool deepresearch interactive-learning
Something wrong? Category · Trend · Risk
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, m
- Category
- rag and search
- Stars
- 26,142
- Readiness
- ready (93/100 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.
agent-framework agentic-ai agentic-rag agents ai ai-agents
Something wrong? Category · Trend · Risk
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
- Category
- rag and search
- Stars
- 77,336
- Readiness
- needs review (52/100 heuristic points; not a probability)
- Data confidence
- medium
- Maintainer health
- risky
- Maintenance risk
- 0/100 · high confidence
Why: +172 stars in 7 days; 100+ lifetime contributors
Why it may be a gem: limited evidence; inspect maintenance signals before adopting
Strongest signals: contributor breadth, issue load, documentation. Risks: None identified. Missing inputs: release recency.
Capped lower bounds: lifetime contributors.
agent agents ai-agents chatgpt deep-learning generative-ai
Something wrong? Category · Trend · Risk
A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp
- Category
- rag and search
- Stars
- 3,302
- 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.
agentic-ai agents ai ai-agents aichat chatbot
Something wrong? Category · Trend · Risk
🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents
- Category
- rag and search
- Stars
- 3,214
- 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 rag and search 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 ai ai-agents llms memory multi-agent-systems
Something wrong? Category · Trend · Risk
The universal tool suite for vector database management. Manage Pinecone, Chroma, Qdrant, Weaviate and more vector databases with ease.
- Category
- rag and search
- Stars
- 2,243
- 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 rag and search 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 479 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai ai-agents aitools chroma database-management document-retrieval
Something wrong? Category · Trend · Risk
Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.
- Category
- rag and search
- Stars
- 1,520
- Readiness
- needs review (56/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- 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: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agents ai-agents educational llm node-llama-cpp nodejs
Something wrong? Category · Trend · Risk
Semantic Search & Call Graphs for AI Agents (100% Local)
- Category
- rag and search
- Stars
- 1,809
- Readiness
- needs review (61/100 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, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai claude-code cli code-search cursor developer-tools
Something wrong? Category · Trend · Risk
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
- Category
- rag and search
- Stars
- 2,564
- Readiness
- ready (95/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +199 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 ast claude-code code-analysis code-understanding codebase-search
Something wrong? Category · Trend · Risk
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
- Category
- rag and search
- Stars
- 131,332
- Readiness
- ready (91/100 heuristic points; not a probability)
- Data confidence
- medium
- Maintainer health
- healthy
- Maintenance risk
- 8/100 · high confidence
Why: +2,015 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: no pull-request review responses in 30 days. Missing inputs: release recency.
Capped lower bounds: 30-day commits, response activity.
agents llms python rag
Something wrong? Category · Trend · Risk
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
- Category
- rag and search
- Stars
- 87,217
- Readiness
- ready (73/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- healthy
- Maintenance risk
- 26/100 · high confidence
Why: +551 stars in 7 days; 100+ lifetime contributors
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: push recency, contributor breadth, issue load. Risks: recent commit cadence is 2/19.6 of its monthly baseline, no pull-request review responses in 30 days. Missing inputs: None.
Capped lower bounds: lifetime contributors, response activity.
ai4science chineseocr document-parsing document-translation kie ocr
Something wrong? Category · Trend · Risk
Build AI Agents, Visually
- Category
- rag and search
- Stars
- 55,241
- Readiness
- ready (87/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · high confidence
Why: +172 stars in 7 days; 21 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.
agentic-ai agentic-workflow agents artificial-intelligence chatbot chatgpt
Something wrong? Category · Trend · Risk
Build Real-Time Knowledge Graphs for AI Agents
- Category
- rag and search
- Stars
- 29,662
- Readiness
- ready (90/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +258 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 graph llms rag
Something wrong? Category · Trend · Risk
Build, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.
- Category
- rag and search
- Stars
- 29,368
- Readiness
- ready (93/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +125 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-workflow agentic-workflow agents ai aiagents anthropic
Something wrong? Category · Trend · Risk
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
- Category
- rag and search
- Stars
- 28,255
- Readiness
- ready (92/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +212 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.
a11y accessibility ai bounding-box document-parsing eaa
Something wrong? Category · Trend · Risk
An open-source RAG-based tool for chatting with your documents.
- Category
- rag and search
- Stars
- 25,691
- Readiness
- ready (74/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- 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, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
chatbot llms open-source rag
Something wrong? Category · Trend · Risk
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.
- Category
- rag and search
- Stars
- 21,398
- Readiness
- ready (88/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +98 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-platform ai-plugins chatbot chatbot-framework coze
Something wrong? Category · Trend · Risk
open-source agentic AI data assistant for the next generation of AI + Data products.
- Category
- rag and search
- Stars
- 19,662
- Readiness
- ready (94/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- 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: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agents bgi database deepseek gpt gpt-4
Something wrong? Category · Trend · Risk
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
- Category
- rag and search
- Stars
- 19,506
- Readiness
- ready (85/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +300 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 chatbot embeddings evaluation
Something wrong? Category · Trend · Risk
Open source agentic operating system
- Category
- rag and search
- Stars
- 18,932
- Readiness
- ready (100/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +76 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 ai autonomous chatbot crypto
Something wrong? Category · Trend · Risk
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
- Category
- rag and search
- Stars
- 18,199
- Readiness
- ready (93/100 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-builder agents ai chatgpt docsgpt hacktoberfest
Something wrong? Category · Trend · Risk
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
- Category
- rag and search
- Stars
- 16,189
- Readiness
- ready (76/100 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: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai context embedded faiss knowledge-base knowledge-graph
Something wrong? Category · Trend · Risk
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori wo
- Category
- rag and search
- Stars
- 15,693
- Readiness
- ready (84/100 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.
agent agent-memory agenticai ai ai-memory claude-code
Something wrong? Category · Trend · Risk
A lightweight, lightning-fast, in-process vector database
- Category
- rag and search
- Stars
- 15,403
- Readiness
- ready (90/100 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, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agent-skills db embedded faiss hnsw llm-memory
Something wrong? Category · Trend · Risk
A vector index built on TurboQuant, written in Rust with Python bindings
- Category
- rag and search
- Stars
- 14,667
- Readiness
- ready (91/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +129 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.
ann avx512 embedding embeddings faiss nearest-neighbor
Something wrong? Category · Trend · Risk
本项目是一个面向小白开发者的大模型应用开发教程，在线阅读地址：https://datawhalechina.github.io/llm-universe/
- Category
- rag and search
- Stars
- 13,737
- Readiness
- needs review (67/100 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. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
langchain rag
Something wrong? Category · Trend · Risk
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
- Category
- rag and search
- Stars
- 12,812
- Readiness
- ready (88/100 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.
agents ai ai-agents embeddings information-retrieval language-model
Something wrong? Category · Trend · Risk
[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
- Category
- rag and search
- Stars
- 12,776
- Readiness
- ready (87/100 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, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai faiss gpt-oss langchain llama-index llm
Something wrong? Category · Trend · Risk
BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SF
- Category
- rag and search
- Stars
- 11,835
- Readiness
- ready (95/100 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: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agent ai chatbot enterprise finetune genai
Something wrong? Category · Trend · Risk
🔍大模型应用开发实战一：RAG 技术全栈指南，在线阅读地址：https://datawhalechina.github.io/all-in-rag/
- Category
- rag and search
- Stars
- 10,161
- Readiness
- ready (82/100 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, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai deepseek embedding kimi-k2 langchain llama-index
Something wrong? Category · Trend · Risk
ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more.
- Category
- rag and search
- Stars
- 10,149
- Readiness
- ready (77/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +191 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 claude gpt-image-2 rag skills web-design
Something wrong? Category · Trend · Risk
The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
- Category
- rag and search
- Stars
- 9,345
- Readiness
- ready (87/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +691 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 memory multimodal rag search
Something wrong? Category · Trend · Risk
High accuracy RAG for answering questions from scientific documents with citations
- Category
- rag and search
- Stars
- 9,005
- Readiness
- ready (85/100 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.
ai rag science search
Something wrong? Category · Trend · Risk
A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured data from 101 formats (115 file extensions) plus code intelligence for 371 code languages. 1
- Category
- rag and search
- Stars
- 8,928
- Readiness
- ready (90/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +206 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.
bun csharp document-intelligence elixir ffi golang
Something wrong? Category · Trend · Risk
🧑🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.
- Category
- rag and search
- Stars
- 8,820
- Readiness
- ready (92/100 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.
awesome-list book course large-language-models llama llm
Something wrong? Category · Trend · Risk
🔥 基于大模型和 RAG 的智能问数系统，对话式数据分析神器。Text-to-SQL Generation via LLMs using RAG.
- Category
- rag and search
- Stars
- 6,561
- Readiness
- ready (85/100 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.
chatbi deepseek llm nl2sql rag sqlbot
Something wrong? Category · Trend · Risk
Memory library for building stateful agents
- Category
- rag and search
- Stars
- 6,506
- Readiness
- ready (84/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +160 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 ai ai-agents ai-memory anthropic context-engineering
Something wrong? Category · Trend · Risk
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
- Category
- rag and search
- Stars
- 6,427
- Readiness
- ready (88/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +48 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.
article-extractor corpus-builder corpus-tools crawler html-to-markdown html2text
Something wrong? Category · Trend · Risk
结合知识库、知识图谱管理的 多租户 Agent Harness 平台。 An agent harness that integrates a LightRAG knowledge base and knowledge graphs. Build with LangChain + Vue + FastAPI, support DeepAgents、MinerU PDF、Neo4j 、MCP.
- Category
- rag and search
- Stars
- 6,407
- Readiness
- ready (94/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +68 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.
docker fastapi harness kbqa kgqa llms
Something wrong? Category · Trend · Risk
Context Graph for AI Native SDLC
- Category
- rag and search
- Stars
- 5,564
- Readiness
- ready (93/100 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.
agents ai-agents ai-agents-framework artificial-intelligence context-graph developer-tools
Something wrong? Category · Trend · Risk
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
- Category
- rag and search
- Stars
- 25,134
- Readiness
- high risk (40/100 heuristic points; not a probability)
- Data confidence
- medium
- Maintainer health
- risky
- Maintenance risk
- 38/100 · high confidence
Why: +139 stars in 7 days; 15 lifetime contributors
Why it may be a gem: open issue backlog is stable or shrinking
Strongest signals: contributor breadth, issue load, documentation. Risks: no push in 320 days, no pull-request review responses in 30 days. Missing inputs: release recency.
12-factor 12-factor-agents agents ai context-window framework
Something wrong? Category · Trend · Risk
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
- Category
- rag and search
- Stars
- 7,950
- Readiness
- needs review (53/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: +29 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 274 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
artificial-intelligence large-language-models python question-answering rag retrieval-augmented-generation
Something wrong? Category · Trend · Risk
A suite of tools to develop RAG, semantic search, and other AI applications more easily with PostgreSQL
- Category
- rag and search
- Stars
- 5,811
- 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 rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation. Risks: repository is archived. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai llm postgresql rag
Something wrong? Category · Trend · Risk
The open source platform for AI-native application development.
- Category
- rag and search
- Stars
- 5,396
- Readiness
- needs review (52/100 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 613 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agent ai ai-native function-call generative-ai gpt
Something wrong? Category · Trend · Risk
《大模型白盒子构建指南》：一个全手搓的Tiny-Universe
- Category
- rag and search
- Stars
- 5,001
- Readiness
- high risk (42/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 29/100 · low confidence
Why: +8 stars in 7 days
Why it may be a gem: limited evidence; inspect maintenance signals before adopting
Strongest signals: issue load, documentation. Risks: no push in 176 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agent diffusion evaluation-metrics llama qwen rag
Something wrong? Category · Trend · Risk
The easiest way to use Agentic RAG in any enterprise
- Category
- rag and search
- Stars
- 4,441
- 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, documentation, license. Risks: no push in 562 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agentic agents ai docker llamaindex rag
Something wrong? Category · Trend · Risk
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
- Category
- rag and search
- Stars
- 4,414
- Readiness
- high risk (0/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 95/100 · low confidence
Why: High-signal rag and search 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 147 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agent ai application data deep-learning fine-tuning
Something wrong? Category · Trend · Risk
AdalFlow: The library to build & auto-optimize LLM applications.
- Category
- rag and search
- Stars
- 4,196
- Readiness
- needs review (54/100 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.
agent ai auto-prompting bm25 chatbot faiss
Something wrong? Category · Trend · Risk
A simple, easy-to-hack GraphRAG implementation
- Category
- rag and search
- Stars
- 3,962
- Readiness
- needs review (54/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: +10 stars in 7 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 192 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
gpt gpt-4o graphrag learning-by-doing llm rag
Something wrong? Category · Trend · Risk
Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️、Vue 生态搭建前端🍍、FastAPI 搭建后端
- Category
- rag and search
- Stars
- 3,752
- Readiness
- needs review (49/100 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. Risks: no push in 518 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
asr chat chat-application chatbot chatgpt digital-human
Something wrong? Category · Trend · Risk
Interact with your SQL database, Natural Language to SQL using LLMs
- Category
- rag and search
- Stars
- 3,644
- 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 7 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 744 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai database finetuning llm nl-to-sql rag
Something wrong? Category · Trend · Risk
🔥 Comprehensive survey on Context Engineering: from prompt engineering to production-grade AI systems. hundreds of papers, frameworks, and implementation guides for LLMs and AI agents.
- Category
- rag and search
- Stars
- 3,269
- Readiness
- needs review (53/100 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.
agent agentic-ai agi awesome-list cognitive-science context-engineering
Something wrong? Category · Trend · Risk
[KDD'2026] "VideoRAG: Chat with Your Videos"
- Category
- rag and search
- Stars
- 3,257
- Readiness
- needs review (48/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 24/100 · low confidence
Why: +32 stars in 7 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation. Risks: no push in 142 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
large-language-models llms long-video-understanding multi-modal-llms rag retrieval-augmented-generation
Something wrong? Category · Trend · Risk
User Profile-Based Long-Term Memory for AI Chatbot Applications.
- Category
- rag and search
- Stars
- 2,834
- Readiness
- needs review (53/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · 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: no push in 208 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai-companion ai-memory chatgpt llm-application llm-memory long-term-memory
Something wrong? Category · Trend · Risk
All-in-one platform for search, recommendations, RAG, and analytics offered via API
- Category
- rag and search
- Stars
- 2,712
- Readiness
- needs review (54/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · 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: no push in 194 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
actix actix-web ai artificial-intelligence diesel embedding
Something wrong? Category · Trend · Risk
The Open Source Memory Layer For Autonomous Agents
- Category
- rag and search
- Stars
- 2,636
- Readiness
- needs review (53/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · 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: no push in 655 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agents knowledge-graph memory multiagent-systems rag self-improvement
Something wrong? Category · Trend · Risk
Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.
- Category
- rag and search
- Stars
- 2,577
- Readiness
- needs review (54/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- 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.
graphrag graphrag-paper graphrag-survey knowledge-graph large-language-models rag
Something wrong? Category · Trend · Risk
This repository contains various advanced techniques for Retrieval-Augmented Generation (RAG) systems.
- Category
- rag and search
- Stars
- 2,561
- 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 7 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 536 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai chromadb cookbooks faiss langchain llm
Something wrong? Category · Trend · Risk
HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
- Category
- rag and search
- Stars
- 2,498
- Readiness
- needs review (53/100 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 256 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
application assistant assistant-chat-bots chatbot dsl group-chat
Something wrong? Category · Trend · Risk
PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
- Category
- rag and search
- Stars
- 2,480
- 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, documentation, license. Risks: no push in 331 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
domain-specific industrial-ai knowledge-extraction rag
Something wrong? Category · Trend · Risk
Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.
- Category
- rag and search
- Stars
- 2,442
- Readiness
- needs review (62/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- Maintenance risk
- 18/100 · 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 109 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
audio-search deep-learning embeddings image-classification image-recognition image-search
Something wrong? Category · Trend · Risk
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
- Category
- rag and search
- Stars
- 2,266
- 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 295 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
benchmark bert colbert dataset deep-learning dpr
Something wrong? Category · Trend · Risk
Empowering RAG with a memory-based data interface for all-purpose applications!
- Category
- rag and search
- Stars
- 2,263
- Readiness
- needs review (48/100 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, license. Risks: no push in 330 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
long-llm memory rag
Something wrong? Category · Trend · Risk
Research project. A Memory solution for users, teams, and applications.
- Category
- rag and search
- Stars
- 2,174
- Readiness
- needs review (59/100 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.
indexing llm memory rag semantic-search
Something wrong? Category · Trend · Risk
An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
- Category
- rag and search
- Stars
- 2,035
- Readiness
- needs review (53/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 24/100 · 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 143 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
document document-analysis document-data-extraction document-information-extraction extraction llm-ocr
Something wrong? Category · Trend · Risk
[ACL2026] "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"
- Category
- rag and search
- Stars
- 1,996
- Readiness
- needs review (51/100 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, license. Risks: no push in 295 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
large-language-models rag retrieval-augmented-generation
Something wrong? Category · Trend · Risk
Text-To-Speech, RAG, and LLMs. All local!
- Category
- rag and search
- Stars
- 1,909
- Readiness
- high risk (43/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation. Risks: no push in 606 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
document-chat embeddings faiss langchain llamacpp llm
Something wrong? Category · Trend · Risk
制作懂人情世故的大语言模型 | 涵盖提示词工程、RAG、Agent、LLM微调教程
- Category
- rag and search
- Stars
- 1,817
- 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 465 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
finetuning gpt llm prompt qwen rag
Something wrong? Category · Trend · Risk
YouTube Full Text Search - Search all of YouTube from the command line
- Category
- rag and search
- Stars
- 1,811
- Readiness
- needs review (52/100 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 197 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
chromadb cli click full-text-search llm rag
Something wrong? Category · Trend · Risk
Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".
- Category
- rag and search
- Stars
- 1,790
- Readiness
- high risk (40/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 29/100 · 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: no push in 717 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
aigc diffusion-models llm multimodality rag survey
Something wrong? Category · Trend · Risk
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
- Category
- rag and search
- Stars
- 1,739
- Readiness
- needs review (56/100 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 703 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agents clustering framework language-model llm machine-learning
Something wrong? Category · Trend · Risk
Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.
- Category
- rag and search
- Stars
- 1,713
- Readiness
- high risk (42/100 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. Risks: no push in 292 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agentic agentic-ai agentic-framework agentic-pattern agentic-rag agentic-workflow
Something wrong? Category · Trend · Risk
PageLM is a community driven version of NotebookLM & a education platform that transforms study materials into interactive resources like quizzes, flashcards, notes, and podcasts.
- Category
- rag and search
- Stars
- 1,699
- Readiness
- needs review (49/100 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.
ai docker edtech education flashcards javascript
Something wrong? Category · Trend · Risk
Trench — Open-Source Analytics Infrastructure. A single production-ready Docker image built on ClickHouse, Kafka, and Node.js for tracking events. Easily build product analytics dashboards, LLM RAGs,
- Category
- rag and search
- Stars
- 1,652
- Readiness
- needs review (51/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 21/100 · 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 123 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
analytics clickhouse clickhouse-database clickhouse-server dashboard dashboards
Something wrong? Category · Trend · Risk
This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks.
- Category
- rag and search
- Stars
- 1,618
- 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, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
advanced-rag agent genai langchain langgraph llm
Something wrong? Category · Trend · Risk
WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.
- Category
- rag and search
- Stars
- 1,609
- 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 30 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 188 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
chatbot emnlp2023 factuality llm natural-language-processing nlp
Something wrong? Category · Trend · Risk
[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.
- Category
- rag and search
- Stars
- 1,545
- Readiness
- ready (72/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +44 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 language-model llm long-term-memory operating-system personalization
Something wrong? Category · Trend · Risk
A toolkit to create optimal Production-readyRetrieval Augmented Generation(RAG) setup for your data
- Category
- rag and search
- Stars
- 1,541
- 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, license. Risks: no push in 444 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
developer-tools genai rag
Something wrong? Category · Trend · Risk
Cache-Augmented Generation: A Simple, Efficient Alternative to RAG
- Category
- rag and search
- Stars
- 1,534
- 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, license. Risks: no push in 438 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
cag llm rag
Something wrong? Category · Trend · Risk
When Philosophy meets AI
- Category
- rag and search
- Stars
- 1,532
- Readiness
- needs review (60/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 16/100 · 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 291 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agent agent-based-simulation agentic-workflow groq langgraph mongodb
Something wrong? Category · Trend · Risk
Official Repo for "TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding" [ACL 2025 oral]
- Category
- rag and search
- Stars
- 1,502
- 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 7 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 376 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
llm-agents manim manim-animations manim-video rag
Something wrong? Category · Trend · Risk
A conversational Q&A agent configuration system, self-hosted deployment solutions, and a convenient all-in-one application SDK, allowing you to create intelligent Q&A bots for your GitHub repositories
- Category
- rag and search
- Stars
- 1,493
- Readiness
- needs review (52/100 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 422 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai assistant assistant-chat-bots assistants github-apps llm
Something wrong? Category · Trend · Risk
Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.
- Category
- rag and search
- Stars
- 1,472
- Readiness
- needs review (51/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · 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: no push in 554 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai embeddings javascript llm ml python
Something wrong? Category · Trend · Risk
OpenSource Production ready Customer service with built in Evals and monitoring
- Category
- rag and search
- Stars
- 1,452
- Readiness
- needs review (59/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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.
customer-service evals knowledge-base llm rag
Something wrong? Category · Trend · Risk
An AI knowledge base/agent built with .Net 9, AntBlazor, Semantic Kernel, and Kernel Memory, supporting local offline AI large models. It can run offline without an internet connection. Supports Aspir
- Category
- rag and search
- Stars
- 1,323
- Readiness
- needs review (49/100 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. Risks: no push in 274 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agnet ai dotnet rag sk
Something wrong? Category · Trend · Risk
TrustRAG：The RAG Framework within Reliable input,Trusted output
- Category
- rag and search
- Stars
- 1,276
- Readiness
- high risk (40/100 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. Risks: no push in 212 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
deep-research deep-search rag retrieval-augmented-generation
Something wrong? Category · Trend · Risk
🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]
- Category
- rag and search
- Stars
- 1,240
- 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 30 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 263 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
aimo amc gpqa livecode math o1
Something wrong? Category · Trend · Risk
[ICLR 2026] Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning
- Category
- rag and search
- Stars
- 1,234
- Readiness
- needs review (48/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 27/100 · 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 162 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agent graph graphrag llm rag
Something wrong? Category · Trend · Risk
RAG Search API
- Category
- rag and search
- Stars
- 1,178
- Readiness
- needs review (49/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, license. Risks: no push in 739 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai-search-engine rag
Something wrong? Category · Trend · Risk
The open-source alternative to Carbon.ai. Build powerful RAG applications with any data source, at any scale.
- Category
- rag and search
- Stars
- 1,154
- Readiness
- needs review (54/100 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, documentation, license. Risks: no push in 222 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai nextjs rag tailwindcss typescript
Something wrong? Category · Trend · Risk
Neo4j graph construction from unstructured data using LLMs
- Category
- rag and search
- Stars
- 5,017
- Readiness
- ready (96/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +41 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.
data-import genai graph graph-rag graph-search graphdb
Something wrong? Category · Trend · Risk
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
- Category
- rag and search
- Stars
- 3,866
- Readiness
- ready (85/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- 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: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agent agentic-ai agentic-rag agents ai-agents bm25
Something wrong? Category · Trend · Risk
The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in-one database makes agents smarter, easier to run,
- Category
- rag and search
- Stars
- 2,858
- 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
Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai-agents copy-on-write embedded-database full-text-search hnsw hybrid-search
Something wrong? Category · Trend · Risk
Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.
- Category
- rag and search
- Stars
- 2,286
- Readiness
- ready (91/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +149 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 chromadb claude claude-code cursor
Something wrong? Category · Trend · Risk
A project-based course repository for developing AI agents using LangChain v1+ and LangGraph: search agents, RAG systems, reflection agents, and code interpreters.
- Category
- rag and search
- Stars
- 1,561
- Readiness
- ready (95/100 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.
agents langchain langgraph langsmith python rag
Something wrong? Category · Trend · Risk
This repository contains examples for customers to get started using the Amazon Bedrock Service. This contains examples for all available foundational models
- Category
- rag and search
- Stars
- 1,485
- Readiness
- ready (88/100 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.
amazon-bedrock amazon-titan bedrock embeddings generative-ai knowledge-base
Something wrong? Category · Trend · Risk
ID-based RAG FastAPI: Integration with Langchain and PostgreSQL/pgvector
- Category
- rag and search
- Stars
- 878
- Readiness
- ready (99/100 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.
api api-rest embeddings fastapi langchain pgvector
Something wrong? Category · Trend · Risk
A modular and comprehensive solution to deploy a Multi-LLM and Multi-RAG powered chatbot (Amazon Bedrock, Anthropic, HuggingFace, OpenAI, Meta, AI21, Cohere, Mistral) using AWS CDK on AWS
- Category
- rag and search
- Stars
- 1,401
- Readiness
- needs review (67/100 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.
amazon-bedrock aurora aws bedrock cdk chatbot
Something wrong? Category · Trend · Risk
An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.
- Category
- rag and search
- Stars
- 1,024
- 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 7 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 592 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agent chatglm chatgpt chatgpt-api gpt gpt-4
Something wrong? Category · Trend · Risk
Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs
- Category
- rag and search
- Stars
- 969
- 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 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.
agents ai deep-learning embeddings fine-tuning gpt
Something wrong? Category · Trend · Risk
⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients.
- Category
- rag and search
- Stars
- 948
- Readiness
- needs review (61/100 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, documentation. Risks: no push in 461 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agent agentic-ai agents chatbot computer-vision disease-detection
Something wrong? Category · Trend · Risk
Believe in AI democratization. llama for nodejs backed by llama-rs, llama.cpp and rwkv.cpp, work locally on your laptop CPU. support llama/alpaca/gpt4all/vicuna/rwkv model.
- Category
- rag and search
- Stars
- 859
- 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 rag and search 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 1100 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai embeddings gpt langchain large-language-models llama
Something wrong? Category · Trend · Risk
Embeds text files into vectors, stores them on Pinecone, and enables semantic search using GPT3 and Langchain in a Next.js UI
- Category
- rag and search
- Stars
- 762
- Readiness
- high risk (42/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 27/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation. Risks: no push in 163 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
langchain nextjs openai pinecone
Something wrong? Category · Trend · Risk
Unified Agentic AI and Business Intelligence Platform
- Category
- rag and search
- Stars
- 129
- Readiness
- ready (87/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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.
agentic-ai agentic-bi agentic-workflow agents ai ai-workflows
Something wrong? Category · Trend · Risk
YT Navigator: AI-powered YouTube content explorer that lets you search and chat with channel videos using AI agents. Extract insights from hours of content in seconds with semantic search and precise
- Category
- rag and search
- Stars
- 601
- Readiness
- needs review (55/100 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 498 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agentic-ai agentic-rag ai django langchain langgraph
Something wrong? Category · Trend · Risk
Production-grade RAG toolkit - ingest PDFs, DOCX, XLSX into Qdrant with LLM metadata extraction, hybrid search, and SHA256 deduplication.
- Category
- rag and search
- Stars
- 20
- Readiness
- ready (92/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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.
crewai kgptalkie langchain qdrant rag rag-pipeline
Something wrong? Category · Trend · Risk
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a c
- Category
- rag and search
- Stars
- 16,703
- Readiness
- ready (90/100 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.
approximate-nearest-neighbor-search generative-search grpc hnsw hybrid-search image-search
Something wrong? Category · Trend · Risk
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
- Category
- rag and search
- Stars
- 4,415
- Readiness
- ready (86/100 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.
ai ai-agents ai-infrastructure ai-memory artificial-intelligence cognitive-architecture
Something wrong? Category · Trend · Risk
Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-fl
- Category
- rag and search
- Stars
- 3,211
- Readiness
- ready (84/100 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.
ai ai-assistant ast claude claude-code code-graph
Something wrong? Category · Trend · Risk
Jupyter Notebooks to help you get hands-on with Pinecone vector databases
- Category
- rag and search
- Stars
- 3,035
- Readiness
- ready (98/100 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.
ai jupyter-notebook llm pinecone python rag
Something wrong? Category · Trend · Risk
Distributed vector search for AI-native applications
- Category
- rag and search
- Stars
- 2,319
- 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
Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai-native ai-native-database cloud-native document-retrieval embeddings hybrid-search
Something wrong? Category · Trend · Risk
Local-first AI job intelligence workbench for scraping roles, ranking fit, and generating tailored application materials.
- Category
- rag and search
- Stars
- 2,220
- 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 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 hireme hiring job jobs
Something wrong? Category · Trend · Risk
SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.
- Category
- rag and search
- Stars
- 1,904
- 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, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai-search bm25 dense-retrieval enterprise-search faceting full-text-search
Something wrong? Category · Trend · Risk
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & C
- Category
- rag and search
- Stars
- 999
- 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: 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.
cross-encoder full-text-search hybrid-search lexical-search rag ranking
Something wrong? Category · Trend · Risk
Program that lets you ask questions about your documents, audio, and video files.
- Category
- rag and search
- Stars
- 369
- 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: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
bark database-management embedding-models embedding-vectors embeddings gtts
Something wrong? Category · Trend · Risk
Embeddable vector database for Go with Chroma-like interface and zero third-party dependencies. In-memory with optional persistence.
- Category
- rag and search
- Stars
- 1,044
- Readiness
- high risk (44/100 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.
chroma chromadb cosine-similarity embedded embeddings go
Something wrong? Category · Trend · Risk
Retrieval Augmented Generation (RAG) framework and context engine powered by Pinecone
- Category
- rag and search
- Stars
- 1,033
- 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 rag and search 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 632 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
generative-ai llm rag vector-database
Something wrong? Category · Trend · Risk
Epsilla is a high performance Vector Database Management System
- Category
- rag and search
- Stars
- 875
- Readiness
- high risk (43/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation. Risks: no push in 251 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai chatgpt data data-science database embeddings
Something wrong? Category · Trend · Risk
An LLM-powered advanced RAG pipeline built from scratch
- Category
- rag and search
- Stars
- 858
- 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 rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 924 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai chatgpt gpt llm question-answering rag
Something wrong? Category · Trend · Risk
RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connec
- Category
- rag and search
- Stars
- 670
- Readiness
- needs review (67/100 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: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agentic-ai agentic-rag agentic-workflow artificial-intelligence data-science framework
Something wrong? Category · Trend · Risk
A NodeJS RAG framework to easily work with LLMs and embeddings
- Category
- rag and search
- Stars
- 602
- 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 rag and search 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 chatgpt claude cohere embedding embeddings
Something wrong? Category · Trend · Risk
A simple example implementation of the VoiceRAG pattern to power interactive voice generative AI experiences using RAG with Azure AI Search and Azure OpenAI's gpt-4o-realtime-preview model.
- Category
- rag and search
- Stars
- 562
- Readiness
- needs review (61/100 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 261 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai-azd-templates azd-templates azure azure-ai-search generative-ai gpt
Something wrong? Category · Trend · Risk
Use ArXiv ChatGuru to talk to research papers. This app uses LangChain, OpenAI, Streamlit, and Redis as a vector database/semantic cache.
- Category
- rag and search
- Stars
- 562
- Readiness
- needs review (56/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 24/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 142 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai arxiv langchain machine-learning openai python
Something wrong? Category · Trend · Risk
Super performant RAG pipelines for AI apps. Summarization, Retrieve/Rerank and Code Interpreters in one simple API.
- Category
- rag and search
- Stars
- 393
- Readiness
- needs review (57/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 829 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agents ai embeddings inference rag vector-database
Something wrong? Category · Trend · Risk
Radient turns many data types (not just text) into vectors for similarity search, RAG, regression analysis, and more.
- Category
- rag and search
- Stars
- 281
- Readiness
- needs review (51/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 26/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 158 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
audio embeddings etl fraud-detection graphs image-search
Something wrong? Category · Trend · Risk
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.
- Category
- rag and search
- Stars
- 277
- 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 rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 186 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agent ai ai-infrastructure context-management developer-tools embedded
Something wrong? Category · Trend · Risk
A modern desktop application for exploring, managing, and analyzing vector databases
- Category
- rag and search
- Stars
- 252
- Readiness
- needs review (52/100 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 aitools chroma database-management embeddings milvus
Something wrong? Category · Trend · Risk
High performance embedded vector database
- Category
- rag and search
- Stars
- 240
- 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 7 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 195 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai database document-retrieval embeddings fuzzy-search llm
Something wrong? Category · Trend · Risk
A lightweight, production-ready RAG (Retrieval Augmented Generation) library in Go.
- Category
- rag and search
- Stars
- 222
- Readiness
- needs review (52/100 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; strong signals despite limited visibility
Strongest signals: issue load, documentation, license. Risks: no push in 395 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai chromadb document-search embeddings golang llm
Something wrong? Category · Trend · Risk
Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).
- Category
- rag and search
- Stars
- 28
- 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 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.
adapter ai embeddings fine-tuning information-retrieval machine-learning
Something wrong? Category · Trend · Risk
A complete guide to start and improve your LLM skills in 2026 with little background in the field and stay up-to-date with the latest news and state-of-the-art techniques!
- Category
- rag and search
- Stars
- 979
- Readiness
- needs review (56/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 16/100 · 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 196 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai fine-tuning gpt gpt-4 language-model large-language-models
Something wrong? Category · Trend · Risk
Framework for enhancing LLMs for RAG tasks using fine-tuning.
- Category
- rag and search
- Stars
- 769
- 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.
evaluation fine-tuning information-retrieval llm nlp question-answering
Something wrong? Category · Trend · Risk
This repository provides programs to build Retrieval Augmented Generation (RAG) code for Generative AI with LlamaIndex, Deep Lake, and Pinecone leveraging the power of OpenAI and Hugging Face models f
- Category
- rag and search
- Stars
- 618
- Readiness
- needs review (62/100 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, fork interest, documentation. Risks: no push in 318 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
advanced-rag chroma chromadb embedding-models fine-tuning gpt-4o-mini
Something wrong? Category · Trend · Risk
21 Lessons, Get Started Building with Generative AI
- Category
- rag and search
- Stars
- 116,935
- Readiness
- ready (99/100 heuristic points; not a probability)
- Data confidence
- medium
- Maintainer health
- healthy
- Maintenance risk
- 8/100 · high confidence
Why: +3,110 stars in 7 days; 41 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: release recency.
Capped lower bounds: lifetime contributors.
ai azure chatgpt dall-e generative-ai generativeai
Something wrong? Category · Trend · Risk
Technical resources for AI developers to build applications, agents, and systems using Oracle AI Database and OCI services
- Category
- rag and search
- Stars
- 4,319
- Readiness
- ready (84/100 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.
agentmemory agents ai ai-developer artificial-intelligence generative-ai
Something wrong? Category · Trend · Risk
GenAI Cookbook
- Category
- rag and search
- Stars
- 4,258
- Readiness
- ready (96/100 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.
agents artificial-intelligence generative-ai llms rag
Something wrong? Category · Trend · Risk
A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Co
- Category
- rag and search
- Stars
- 3,329
- Readiness
- ready (90/100 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, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai-agent ai-tools automation claude-code codex gemini
Something wrong? Category · Trend · Risk
A curated list of Generative AI tools, works, models, and references
- Category
- rag and search
- Stars
- 3,516
- Readiness
- needs review (52/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- 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-art awesome awesome-list chatgpt dall-e dalle2
Something wrong? Category · Trend · Risk
Efficient Retrieval Augmentation and Generation Framework
- Category
- rag and search
- Stars
- 1,784
- 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 rag and search 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 207 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
benchmark colbert diffusion generative-ai information-retrieval knowledge-graph
Something wrong? Category · Trend · Risk
Comprehensive guide to learn RAG from basics to advanced.
- Category
- rag and search
- Stars
- 1,394
- Readiness
- needs review (62/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · 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: no push in 496 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai-engineer generative-ai large-language-models llm-engineer llm-rag llms
Something wrong? Category · Trend · Risk
📚 Process PDFs, Word documents and more with spaCy
- Category
- rag and search
- Stars
- 912
- 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 133 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
document-layout document-layout-analysis docx generative-ai natural-language-processing nlp
Something wrong? Category · Trend · Risk
RAG Time: A 5-week Learning Journey to Mastering RAG
- Category
- rag and search
- Stars
- 898
- Readiness
- needs review (62/100 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 416 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai azure binary-quantization generative-ai gpt hnsw
Something wrong? Category · Trend · Risk
Build your own serverless AI Chat with Retrieval-Augmented-Generation using LangChain.js, TypeScript and Azure
- Category
- rag and search
- Stars
- 859
- Readiness
- needs review (62/100 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.
ai-azd-templates azd-templates azure azure-functions chatbot generative-ai
Something wrong? Category · Trend · Risk
Rust-powered code intelligence CLI for AI coding agents. Builds call graphs and hybrid semantic search indexes (Dense + Sparse + RRF + Reranker) across 7 languages. Ships as native MCP tools for Claud
- Category
- rag and search
- Stars
- 816
- Readiness
- ready (86/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +209 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-tools ai-development-tools ai-tools bm25 call-graph claude-code
Something wrong? Category · Trend · Risk
Give Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single .mv2 file you can git commit, scp, or share. Native Rust core with sub-ms operations.
- Category
- rag and search
- Stars
- 544
- Readiness
- needs review (55/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · 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: no push in 200 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai-tools anthropic claude claude-agents claude-ai claude-code
Something wrong? Category · Trend · Risk
List of software that allows searching the web with the assistance of AI: https://hf.co/spaces/felladrin/awesome-ai-web-search
- Category
- rag and search
- Stars
- 1,408
- Readiness
- ready (77/100 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, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai ai-search-engine artificial-intelligence artificial-intelligence-projects awesome awesome-list
Something wrong? Category · Trend · Risk
Minimalist web-searching platform with an AI assistant that runs directly from your browser. Demo: https://felladrin-minisearch.hf.space
- Category
- rag and search
- Stars
- 579
- Readiness
- ready (92/100 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
Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai ai-search-engine artificial-intelligence generative-ai gpu-accelerated information-retrieval
Something wrong? Category · Trend · Risk
Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).
- Category
- rag and search
- Stars
- 3,046
- Readiness
- needs review (53/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 29/100 · 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 177 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
deep-learning developer-tools embeddings large-language-models llms machine-learning
Something wrong? Category · Trend · Risk
Empower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks
- Category
- rag and search
- Stars
- 943
- Readiness
- needs review (55/100 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 636 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
bert-models bioinformatics bioinformatics-algorithms biomedical-applications biomedical-informatics context-aware
Something wrong? Category · Trend · Risk
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
- Category
- rag and search
- Stars
- 11,084
- Readiness
- ready (85/100 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.
agentic-ai agentic-framework agentic-workflow agents ai-framework ai-frameworks
Something wrong? Category · Trend · Risk
Persistent memory & RAG engine for AI agents — SQLite + FTS5 + embeddings, multi-stage recall, sleep maintenance, multi-host hooks
- Category
- rag and search
- Stars
- 20
- 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 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 ai-agent ai-framework ai-harness ai-tools rag
Something wrong? Category · Trend · Risk
RAPTOR (Robust AI-Powered Toolkit for Operational Robots) is an AI-native Content Insight Engine that transforms passive media storage into an intelligent knowledge platform through automated analysis
- Category
- rag and search
- Stars
- 19
- Readiness
- ready (82/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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.
ai ai-automation ai-framework ai-governance ai-orchestration artificial-intelligence
Something wrong? Category · Trend · Risk
🤖 Build a smart AI assistant that learns from any website using a Retrieval-Augmented Generation framework with local models powered by Ollama.
- Category
- rag and search
- Stars
- 6
- Readiness
- ready (96/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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-framework beautifulsoup chromadb gemma-2b knowledge-base langchain
Something wrong? Category · Trend · Risk
The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.
- Category
- rag and search
- Stars
- 107,675
- Readiness
- ready (96/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · high confidence
Why: +345 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 alternative auth database deno embeddings
Something wrong? Category · Trend · Risk
The all-in-one, open-source backend platform for agentic coding. InsForge gives your coding agent database, auth, storage, compute, hosting, and AI gateway to ship full-stack apps end-to-end.
- Category
- rag and search
- Stars
- 12,669
- Readiness
- ready (91/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +64 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 coding deno embeddings insforge
Something wrong? Category · Trend · Risk
SeaTunnel is a multimodal, high-performance, distributed, massive data integration tool.
- Category
- rag and search
- Stars
- 9,542
- Readiness
- ready (99/100 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.
apache batch cdc change-data-capture data-ingestion data-integration
Something wrong? Category · Trend · Risk
Find related notes and excerpts while writing. Your link building copilot displays relevant content in graph + list view. A local embedding model powers semantic search. Zero setup. No API key.
- Category
- rag and search
- Stars
- 5,343
- Readiness
- ready (79/100 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, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
chatgpt claude embeddings gemini obsidian obsidian-md
Something wrong? Category · Trend · Risk
A blazing fast inference solution for text embeddings models
- Category
- rag and search
- Stars
- 4,983
- Readiness
- ready (82/100 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.
ai embeddings huggingface llm ml
Something wrong? Category · Trend · Risk
AutoRAG: Now your agent can find anything in your computer. It gets smarter if you are using it frequently.
- Category
- rag and search
- Stars
- 4,968
- Readiness
- ready (81/100 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.
analysis automl benchmarking document-parser embeddings evaluation
Something wrong? Category · Trend · Risk
A python library for self-supervised learning on images.
- Category
- rag and search
- Stars
- 3,792
- Readiness
- ready (91/100 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.
computer-vision contrastive-learning contributions-welcome deep-learning embeddings hacktoberfest
Something wrong? Category · Trend · Risk
MTEB: State-of-the-art evaluation of embeddings across languages and modalities
- Category
- rag and search
- Stars
- 3,386
- Readiness
- ready (95/100 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.
benchmark bitext-mining clustering embeddings evaluation information-retrieval
Something wrong? Category · Trend · Risk
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
- Category
- rag and search
- Stars
- 3,130
- Readiness
- ready (88/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +15 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.
embeddings openai rag retrieval retrieval-augmented-generation vector-search
Something wrong? Category · Trend · Risk
Open-source inference server and production cluster for all the models your agent needs.
- Category
- rag and search
- Stars
- 2,672
- Readiness
- ready (92/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +287 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.
bge colbert data-pipeline deep-learning embeddings inference
Something wrong? Category · Trend · Risk
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex), backed by Markdown and Milvus.
- Category
- rag and search
- Stars
- 2,433
- Readiness
- ready (85/100 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.
agent agent-memory ai-agents claude-code claude-code-plugin codex
Something wrong? Category · Trend · Risk
The collection of pre-trained, state-of-the-art AI models for ailia SDK
- Category
- rag and search
- Stars
- 2,362
- 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: 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.
action-recognition anomaly-detection audio-processing background-removal crowd-counting deep-learning
Something wrong? Category · Trend · Risk
Fast State-of-the-Art Static Embeddings
- Category
- rag and search
- Stars
- 2,174
- Readiness
- ready (88/100 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 embeddings machine-learning model2vec nlp python
Something wrong? Category · Trend · Risk
AI-powered cross-platform e-book reader with semantic search, RAG chat, local vector store, notes, TTS, and WebDAV sync.
- Category
- rag and search
- Stars
- 2,158
- Readiness
- ready (79/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +52 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 anthropic ebook-reader embeddings epub-reader expo
Something wrong? Category · Trend · Risk
The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.
- Category
- rag and search
- Stars
- 2,042
- 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
Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
agentic-rag ai ai-agents ai-sdk chatbots embeddings
Something wrong? Category · Trend · Risk
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
- Category
- rag and search
- Stars
- 1,636
- Readiness
- ready (81/100 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.
computer-vision contrastive-learning deep-learning depth-estimation dinov2 dinov3
Something wrong? Category · Trend · Risk
Hivemind turns your traces into reusable skills across agents
- Category
- rag and search
- Stars
- 1,538
- Readiness
- ready (85/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- 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: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai ai-agents ai-memory anthropic artificial-intelligence claude
Something wrong? Category · Trend · Risk
Awesome-LLM-RAG: a curated list of advanced retrieval augmented generation (RAG) in Large Language Models
- Category
- rag and search
- Stars
- 1,340
- Readiness
- needs review (68/100 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.
embeddings large-language-models llm rag rag-embeddings retrieval-augmented-generation
Something wrong? Category · Trend · Risk
GPU-accelerated force graph layout and rendering
- Category
- rag and search
- Stars
- 1,235
- Readiness
- ready (89/100 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.
embeddings force graph network simulation visualization
Something wrong? Category · Trend · Risk
An Obsidian plugin to interact with your privacy focused AI-Assistant making your second brain even smarter!
- Category
- rag and search
- Stars
- 1,210
- Readiness
- ready (91/100 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.
ai chatgpt embeddings obsidian-md obsidian-plugin ollama
Something wrong? Category · Trend · Risk
Rust library for generating vector embeddings, reranking locally!
- Category
- rag and search
- Stars
- 983
- Readiness
- ready (92/100 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.
embeddings fastembed rag reranker reranking retrieval
Something wrong? Category · Trend · Risk
A repository of code samples for Vector search capabilities in Azure AI Search.
- Category
- rag and search
- Stars
- 911
- Readiness
- ready (97/100 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, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
azure azurecognitivesearch embeddings vector vector-search
Something wrong? Category · Trend · Risk
🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and
- Category
- rag and search
- Stars
- 858
- Readiness
- ready (91/100 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.
ai artificial-intelligence csharp embeddings machine-learning natural-language-processing
Something wrong? Category · Trend · Risk
Samples showing how to build Java applications powered by Generative AI and LLMs using Spring AI and Spring Boot.
- Category
- rag and search
- Stars
- 768
- Readiness
- ready (98/100 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.
embeddings generative-ai large-language-models llm ollama openai
Something wrong? Category · Trend · Risk
Microsoft Foundry (demos, documentation, accelerators).
- Category
- rag and search
- Stars
- 755
- Readiness
- ready (90/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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.
azure azure-cognitive-services azure-openai chatgpt dalle-3 embeddings
Something wrong? Category · Trend · Risk
Embedded relational database and native Rust data API.
- Category
- rag and search
- Stars
- 738
- Readiness
- ready (80/100 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.
data database embeddings myrocks oltp query-engine
Something wrong? Category · Trend · Risk
A prior-art search for your code ideas — has this dev tool already been shipped?
- Category
- rag and search
- Stars
- 520
- Readiness
- ready (85/100 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.
ai cli command-line-tool developer-tools embeddings llm
Something wrong? Category · Trend · Risk
RESTai is an AIaaS (AI as a Service) open-source platform. Supports many public and local LLM suported by Ollama/vLLM/etc. Precise embeddings usage, tuning, analytics etc. Built-in image/audio generat
- Category
- rag and search
- Stars
- 513
- Readiness
- ready (96/100 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: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
blocky embeddings fastapi langchain llama llamaindex
Something wrong? Category · Trend · Risk
Semantic code searcher and codebase utility
- Category
- rag and search
- Stars
- 443
- Readiness
- ready (84/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · high confidence
Why: +5 stars in 7 days; 50 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, issue load. Risks: None identified. Missing inputs: None.
ai ai-tools cli cli-app code-search developer-tool
Something wrong? Category · Trend · Risk
Knowledge Graph Toolkit
- Category
- rag and search
- Stars
- 422
- Readiness
- needs review (55/100 heuristic points; not a probability)
- Data confidence
- high
- Maintainer health
- watch
- Maintenance risk
- 46/100 · high confidence
Why: +1 stars in 7 days; 23 lifetime contributors
Why it may be a gem: healthy maintenance and project fundamentals; open issue backlog is stable or shrinking
Strongest signals: contributor breadth, documentation, license. Risks: latest release is 1135 days old, 201 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.
embeddings etl-framework graphs kg knowledge-graphs rdf
Something wrong? Category · Trend · Risk
QVAC - Local AI SDK and libraries for building private, cross-platform, peer-to-peer AI applications. Run LLMs, speech-to-text, translation, and more locally on Linux, macOS, Windows, Android, and iOS
- Category
- rag and search
- Stars
- 395
- Readiness
- ready (95/100 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, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai bare-runtime cross-platform embeddings llm local-ai
Something wrong? Category · Trend · Risk
RushDB is a graph + vector database and memory layer for AI agents. Push any JSON, get typed, searchable, relationship-aware records back — no schema, no migrations. Built on Neo4j.
- Category
- rag and search
- Stars
- 319
- Readiness
- needs review (69/100 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
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-memory ai-tools app-backend cloud
Something wrong? Category · Trend · Risk
Automatic news aggregator in Telegram / Автоматический агрегатор новостей в Телеграме
- Category
- rag and search
- Stars
- 318
- 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
Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
aggregator clustering embeddings news news-aggregator newsfeed
Something wrong? Category · Trend · Risk
Shows similar repositories in the sidebar
- Category
- rag and search
- Stars
- 314
- Readiness
- ready (79/100 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.
embeddings git github machine-learning recommendations repositories
Something wrong? Category · Trend · Risk
Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP exits.
- Category
- rag and search
- Stars
- 288
- Readiness
- ready (77/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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-rag embeddings fastapi hybrid-search knowledge-base llm
Something wrong? Category · Trend · Risk
Running local Language Language Models (LLM) to perform Retrieval-Augmented Generation (RAG)
- Category
- rag and search
- Stars
- 286
- Readiness
- ready (80/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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.
agentic agentic-ai agentic-rag chatbot embeddings langchain
Something wrong? Category · Trend · Risk
A Redis-compatable key-value store. Up to 10x faster. Native vector support.
- Category
- rag and search
- Stars
- 275
- 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 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.
database dragonflydb embeddings lux postgres redis
Something wrong? Category · Trend · Risk
A pure-Go, single-file AI memory and knowledge graph library and plugin.
- Category
- rag and search
- Stars
- 246
- 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 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.
embeddings hindsight llm rag sqlite vector-database
Something wrong? Category · Trend · Risk
A semantic search engine for files and code.
- Category
- rag and search
- Stars
- 234
- 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, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai claude cli codex embeddings mcp-server
Something wrong? Category · Trend · Risk
A unified interface for various AI model providers
- Category
- rag and search
- Stars
- 209
- Readiness
- ready (90/100 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.
anthropic embeddings gemini langchain language-model openai
Something wrong? Category · Trend · Risk
On-device memory layer for AI agents. Claude Code, Hermes and OpenClaw. Hooks + MCP server + hybrid RAG search.
- Category
- rag and search
- Stars
- 197
- 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; 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-memory ai-agents bun claude-code embeddings hermes
Something wrong? Category · Trend · Risk
The AI Operating System for Delphi. 100% native framework with RAG 2.0, autonomous agents, MCP protocol, and universal LLM connector. Supports OpenAI, Claude, Gemini, Ollama, and more. Delphi 10.4+ (l
- Category
- rag and search
- Stars
- 196
- Readiness
- ready (100/100 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.
ai-agents claude delphi embeddings fpc free-pascal
Something wrong? Category · Trend · Risk
🧠 The Brain for Your AI — Local-first memory engine for AI agents. Store, recall, and search memories with semantic embeddings. Single Rust binary, zero config, fully offline.
- Category
- rag and search
- Stars
- 193
- Readiness
- ready (92/100 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; 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-memory ai ai-agents cli cli-tool embeddings
Something wrong? Category · Trend · Risk
A curated list of battle-tested tools, frameworks, and best practices for building scalable, production-grade Retrieval-Augmented Generation (RAG) systems.
- Category
- rag and search
- Stars
- 188
- 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; 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-engineering artificial-intelligence awesome awesome-list curated-list
Something wrong? Category · Trend · Risk
Pure Rust PDF library for AI/RAG: structure-aware chunking, no ML, no C deps.
- Category
- rag and search
- Stars
- 185
- Readiness
- ready (90/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: +5 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 chunking data-extraction digital-signatures document-processing embeddings
Something wrong? Category · Trend · Risk
📚🧙♂️ Wisdom indexer — use AI to organize text snippets so you can actually remember & learn from what you read
- Category
- rag and search
- Stars
- 179
- Readiness
- needs review (64/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility
Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai books ebook ebooks elm embeddings
Something wrong? Category · Trend · Risk
All Jina AI APIs as Unix CLI commands. Search, read, embed, rerank - with pipes.
- Category
- rag and search
- Stars
- 169
- Readiness
- ready (87/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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 ai cli embeddings jina llm-tools
Something wrong? Category · Trend · Risk
Semantic codebase indexing and search for OpenCode, Claude, Codex, Pi, Jcode, and MCP hosts. Powered by Rust and tree-sitter.
- Category
- rag and search
- Stars
- 161
- Readiness
- ready (96/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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.
claude-code code-search codebase-indexing codex embeddings mcp
Something wrong? Category · Trend · Risk
Voice notes for iPhone and macOS - 100% Rust, Dioxus, local-first (SQLite + LanceDB + RIG)
- Category
- rag and search
- Stars
- 161
- 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: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
dioxus embeddings ios lancedb llm p2p
Something wrong? Category · Trend · Risk
One line code to get any remote sensing foundation model embeddings for any place and any time
- Category
- rag and search
- Stars
- 144
- 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; 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.
earth-observation embeddings geospatial geospatial-foundation-model remote-sensing remote-sensing-foundation-model
Something wrong? Category · Trend · Risk
100+ Chinese Word Vectors 上百种预训练中文词向量
- Category
- rag and search
- Stars
- 12,228
- Readiness
- needs review (59/100 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 1012 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
chinese chinese-word-segmentation embedding embeddings vectors-trained word-embeddings
Something wrong? Category · Trend · Risk
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
- Category
- rag and search
- Stars
- 6,337
- 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 30 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 355 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
computer-vision contrastive-learning deep-learning deep-metric-learning embeddings image-retrieval
Something wrong? Category · Trend · Risk
text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。
- Category
- rag and search
- Stars
- 4,977
- Readiness
- needs review (54/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 29/100 · 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: no push in 174 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings nlp sentence-embeddings similarity text-similarity text2vec
Something wrong? Category · Trend · Risk
A library for transfer learning by reusing parts of TensorFlow models.
- Category
- rag and search
- Stars
- 3,523
- Readiness
- needs review (62/100 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, fork interest, documentation. Risks: no push in 567 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings image-classification machine-learning ml python tensorflow
Something wrong? Category · Trend · Risk
Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
- Category
- rag and search
- Stars
- 3,455
- 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 659 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
computer-vision convolutional-networks embedding-vectors embeddings feature-extraction feature-vector
Something wrong? Category · Trend · Risk
📋 Survey papers summarizing advances in deep learning, NLP, CV, graphs, reinforcement learning, recommendations, graphs, etc.
- Category
- rag and search
- Stars
- 2,905
- 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 1239 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
computer-vision deep-learning embeddings machine-learning nlp recommender-system
Something wrong? Category · Trend · Risk
This repository is deprecated and will be archived
- Category
- rag and search
- Stars
- 2,253
- Readiness
- needs review (62/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 16/100 · 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 193 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai chatbot documentation embeddings gemini gemini-api
Something wrong? Category · Trend · Risk
Basic Utilities for PyTorch Natural Language Processing (NLP)
- Category
- rag and search
- Stars
- 2,223
- 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 rag and search 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 1130 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
data-loader dataset deep-learning embeddings machine-learning metrics
Something wrong? Category · Trend · Risk
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
- Category
- rag and search
- Stars
- 2,023
- 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 rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 569 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings information-retrieval language-model prompt-retrieval text-classification text-clustering
Something wrong? Category · Trend · Risk
Predict stock market prices using RNN model with multilayer LSTM cells + optional multi-stock embeddings.
- Category
- rag and search
- Stars
- 1,988
- Readiness
- needs review (48/100 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 1471 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings lstm rnn-tensorflow stock-price-prediction
Something wrong? Category · Trend · Risk
Nomic Developer API SDK
- Category
- rag and search
- Stars
- 1,879
- Readiness
- high risk (42/100 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: limited evidence; inspect maintenance signals before adopting
Strongest signals: issue load, documentation. Risks: no push in 269 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
clustering duplicate-detection embeddings python text topic-modeling
Something wrong? Category · Trend · Risk
A robust, all-in-one GPT interface for Discord. ChatGPT-style conversations, image generation, AI-moderation, custom indexes/knowledgebase, youtube summarizer, and more!
- Category
- rag and search
- Stars
- 1,855
- Readiness
- needs review (57/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · 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: no push in 182 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
artificial-intelligence asyncio chatbot code-interpreter collaborate dalle2
Something wrong? Category · Trend · Risk
A curated list of awesome embedding models tutorials, projects and communities.
- Category
- rag and search
- Stars
- 1,850
- 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 7 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 2679 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
awesome embedding-models embeddings machine-learning natural-language-processing papers
Something wrong? Category · Trend · Risk
Semantic search and document parsing tools for the command line
- Category
- rag and search
- Stars
- 1,845
- Readiness
- needs review (53/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 25/100 · 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: no push in 149 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
cli embeddings parser rust search semantic
Something wrong? Category · Trend · Risk
中文长文本分类、短句子分类、多标签分类、两句子相似度（Chinese Text Classification of Keras NLP, multi-label classify, or sentence classify, long or short），字词句向量嵌入层（embeddings）和网络层（graph）构建基类，FastText，TextCNN，CharCNN，TextRNN, R
- Category
- rag and search
- Stars
- 1,811
- Readiness
- needs review (61/100 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 781 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
albert bert capsule charcnn crnn dcnn
Something wrong? Category · Trend · Risk
Bringing BERT into modernity via both architecture changes and scaling
- Category
- rag and search
- Stars
- 1,707
- Readiness
- needs review (50/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 27/100 · 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 159 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
bert embeddings llm nlp
Something wrong? Category · Trend · Risk
A fast, efficient universal vector embedding utility package.
- Category
- rag and search
- Stars
- 1,666
- 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 30 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 1101 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings fast fasttext gensim glove machine-learning
Something wrong? Category · Trend · Risk
Data augmentation for NLP, presented at EMNLP 2019
- Category
- rag and search
- Stars
- 1,651
- 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 rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, fork interest, documentation. Risks: no push in 1237 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
classification cnn data-augmentation embeddings nlp position
Something wrong? Category · Trend · Risk
Persian NLP Toolkit
- Category
- rag and search
- Stars
- 1,415
- Readiness
- needs review (57/100 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 128 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
dependency-parser embeddings farsi lemmatization natural-language-processing nlp
Something wrong? Category · Trend · Risk
Solves basic Russian NLP tasks, API for lower level Natasha projects
- Category
- rag and search
- Stars
- 1,346
- Readiness
- needs review (53/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- Maintenance risk
- 19/100 · 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 116 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings morphology ner nlp python russian
Something wrong? Category · Trend · Risk
Implementation of the node2vec algorithm.
- Category
- rag and search
- Stars
- 1,300
- 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 rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, fork interest, license. Risks: no push in 305 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
deep-learning embeddings machine-learning-algorithms
Something wrong? Category · Trend · Risk
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021 (Bianchi et al.).
- Category
- rag and search
- Stars
- 1,271
- Readiness
- needs review (55/100 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 379 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
bert embeddings multilingual-models multilingual-topic-models neural-topic-models nlp
Something wrong? Category · Trend · Risk
GPT-vup BIliBili | 抖音 | AI | 虚拟主播
- Category
- rag and search
- Stars
- 1,268
- Readiness
- high risk (44/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: limited evidence; inspect maintenance signals before adopting
Strongest signals: issue load, documentation. Risks: no push in 1029 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
bilibili chatgpt douyin embeddings vtuber
Something wrong? Category · Trend · Risk
Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)
- Category
- rag and search
- Stars
- 1,222
- 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 675 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings multilingual natural-language-processing nlp subword-embeddings
Something wrong? Category · Trend · Risk
Open Source Semantic Search for your AI Agent
- Category
- rag and search
- Stars
- 1,140
- Readiness
- needs review (50/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 202 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
colbert embeddings grep grep-search
Something wrong? Category · Trend · Risk
Implementation of triplet loss in TensorFlow
- Category
- rag and search
- Stars
- 1,126
- Readiness
- needs review (59/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, fork interest, documentation. Risks: no push in 2647 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings online-triplet-mining tensorflow triplet-loss
Something wrong? Category · Trend · Risk
A deep dive into embeddings starting from fundamentals
- Category
- rag and search
- Stars
- 1,092
- Readiness
- high risk (39/100 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. Risks: no push in 203 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings machine-learning machine-learning-algorithms nlp-machine-learning
Something wrong? Category · Trend · Risk
A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.
- Category
- rag and search
- Stars
- 1,056
- Readiness
- high risk (40/100 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 526 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embedding-similarity embedding-vectors embeddings llama2 llamacpp semantic-search
Something wrong? Category · Trend · Risk
A tool for learning vector representations of words and entities from Wikipedia
- Category
- rag and search
- Stars
- 969
- Readiness
- needs review (46/100 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 826 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings natural-language-processing nlp python text-classification wikipedia
Something wrong? Category · Trend · Risk
Curated list of 2vec-type embedding models
- Category
- rag and search
- Stars
- 934
- Readiness
- high risk (42/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, fork interest. Risks: no push in 1338 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
awesome embeddings list
Something wrong? Category · Trend · Risk
PostgreSQL vector database extension for building AI applications
- Category
- rag and search
- Stars
- 888
- Readiness
- high risk (44/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation. Risks: no push in 603 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai ann approximate-nearest-neighbor-search data-science database embeddings
Something wrong? Category · Trend · Risk
unified embedding model
- Category
- rag and search
- Stars
- 876
- 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 rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 1071 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings huggingface nlp sentence-embeddings sentence-transformers
Something wrong? Category · Trend · Risk
🪿 LinGoose is a Go framework for building awesome AI/LLM applications.
- Category
- rag and search
- Stars
- 834
- Readiness
- needs review (54/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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 chatgpt embeddings go golang index
Something wrong? Category · Trend · Risk
Fuzzy string matching, grouping, and evaluation.
- Category
- rag and search
- Stars
- 801
- 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 393 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
bert edit-distance embeddings levenshtein-distance string-matching tf-idf
Something wrong? Category · Trend · Risk
Train Models Contrastively in Pytorch
- Category
- rag and search
- Stars
- 800
- 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 499 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
contrastive-learning deep-learning dense-retrieval embeddings image-embeddings multimodal
Something wrong? Category · Trend · Risk
Transform audio-visual content into navigable knowledge.
- Category
- rag and search
- Stars
- 774
- 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 rag and search 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 1017 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings package python search semantic-search speech-to-text
Something wrong? Category · Trend · Risk
Curated List of Persian Natural Language Processing and Information Retrieval Tools and Resources
- Category
- rag and search
- Stars
- 768
- Readiness
- needs review (45/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation. Risks: no push in 1004 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
corpus dependency-parser embeddings information-retrieval language-detection morphological-analysis
Something wrong? Category · Trend · Risk
Library for faster pinned CPU <-> GPU transfer in Pytorch
- Category
- rag and search
- Stars
- 682
- 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 rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 2359 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
cpu-gpu-transfer cpu-pinned-tensors cuda cuda-tensors cuda-variables cupy
Something wrong? Category · Trend · Risk
Compute Sentence Embeddings Fast!
- Category
- rag and search
- Stars
- 625
- Readiness
- needs review (47/100 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. Risks: no push in 1254 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
cython document-similarity embeddings fasttext fse gensim
Something wrong? Category · Trend · Risk
The Clay Foundation Model - An open source AI model and interface for Earth
- Category
- rag and search
- Stars
- 603
- Readiness
- needs review (57/100 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, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
digital-elevation-model earth-observation embeddings foundation-model sentinel-1 sentinel-2
Something wrong? Category · Trend · Risk
Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN (GRU and LSTM) and Word Embeddings on Tensorflow.
- Category
- rag and search
- Stars
- 602
- Readiness
- needs review (61/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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.
cnn embeddings kaggle lstm rnn tensorflow
Something wrong? Category · Trend · Risk
Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard
- Category
- rag and search
- Stars
- 573
- Readiness
- needs review (52/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 23/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 138 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
dense-retrieval embeddings information-retrieval llama llama2 llm
Something wrong? Category · Trend · Risk
A flexible, adaptive classification system for dynamic text classification
- Category
- rag and search
- Stars
- 568
- 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
Strongest signals: issue load, documentation, license. Risks: no push in 304 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
adaptive-learning adaptive-neural-network bert classifier continous-learning distilbert
Something wrong? Category · Trend · Risk
Natural Language Processing Pipeline - Sentence Splitting, Tokenization, Lemmatization, Part-of-speech Tagging and Dependency Parsing
- Category
- rag and search
- Stars
- 562
- Readiness
- needs review (58/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 642 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
dependency-parser dependency-parsing embeddings information-extraction language-pipeline lemmatization
Something wrong? Category · Trend · Risk
Nimfa: Nonnegative matrix factorization in Python
- Category
- rag and search
- Stars
- 560
- 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 rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, fork interest, documentation. Risks: no push in 2002 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings latent-features latent-variable-models matrix-factorization nonnegative-matrix-factorization
Something wrong? Category · Trend · Risk
Vector Hub - Library for easy discovery, and consumption of State-of-the-art models to turn data into vectors. (text2vec, image2vec, video2vec, graph2vec, bert, inception, etc)
- Category
- rag and search
- Stars
- 560
- 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 rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation. Risks: repository is archived, no push in 717 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
artificial-intelligence audio-processing deep-learning deeplearning embeddings encodings
Something wrong? Category · Trend · Risk
Go library for embedded vector search and semantic embeddings using llama.cpp
- Category
- rag and search
- Stars
- 556
- Readiness
- needs review (51/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 26/100 · 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 154 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai bert embeddings gguf gpu llamacpp
Something wrong? Category · Trend · Risk
Cleora AI is a general-purpose open-source model for efficient, scalable learning of stable and inductive entity embeddings for heterogeneous relational data. Created by Synerise.com team.
- Category
- rag and search
- Stars
- 540
- Readiness
- needs review (46/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 21/100 · low confidence
Why: High-signal rag and search project
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 cleora-embeddings datasets deepwalk embeddings entity
Something wrong? Category · Trend · Risk
Named Entity Recognition using multilayered bidirectional LSTM
- Category
- rag and search
- Stars
- 538
- Readiness
- needs review (50/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, fork interest, documentation. Risks: no push in 2707 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
deep-neural-networks embeddings lstm named-entity-recognition natural-language-processing recurrent-neural-networks
Something wrong? Category · Trend · Risk
Explore and interpret large embeddings in your browser with interactive visualization! 📍
- Category
- rag and search
- Stars
- 535
- 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 30 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 197 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings interactive-visualizations machine-learning visualization webgl
Something wrong? Category · Trend · Risk
An open-source intelligence (OSINT) analysis tool leveraging GPT-powered embeddings and vector search engines for efficient data processing
- Category
- rag and search
- Stars
- 523
- 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 970 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings gpt-3-5-turbo gpt-4 osint osint-python osint-tool
Something wrong? Category · Trend · Risk
GraphRAG-rs is a high-performance, state-of-the-art Rust implementation of GraphRAG (Graph-based Retrieval Augmented Generation) that builds knowledge graphs from documents and enables natural languag
- Category
- rag and search
- Stars
- 522
- Readiness
- needs review (54/100 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.
ai embeddings entity-extraction graphrag knowledge-graph llama-cpp
Something wrong? Category · Trend · Risk
Analyze the unstructured data with Towhee, such as reverse image search, reverse video search, audio classification, question and answer systems, molecular search, etc.
- Category
- rag and search
- Stars
- 520
- Readiness
- needs review (60/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, fork interest, documentation. Risks: no push in 910 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
audio-classification cross-modal embeddings image-classification machine-learning nlp
Something wrong? Category · Trend · Risk
Production-ready MVP for securely chatting with your documents using pgvector
- Category
- rag and search
- Stars
- 514
- Readiness
- needs review (49/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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 db embeddings ml rag supabase
Something wrong? Category · Trend · Risk
Toolkit to help understand "what lies" in word embeddings. Also benchmarking!
- Category
- rag and search
- Stars
- 481
- 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 rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, license. Risks: repository is archived, no push in 1278 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings nlp visualisations
Something wrong? Category · Trend · Risk
Graph convolutional neural network for multirelational link prediction
- Category
- rag and search
- Stars
- 474
- Readiness
- needs review (61/100 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 1355 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
deep-learning embeddings graph-convolutional-networks graph-neural-networks pharmacology representation-learning
Something wrong? Category · Trend · Risk
memX: self-learning, self-maintaining memory plugin for AI agents; native support for claude code, codex, and openclaw
- Category
- rag and search
- Stars
- 468
- Readiness
- needs review (49/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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 agent-memory claude-code codex embeddings graph-memory
Something wrong? Category · Trend · Risk
Recommender Systems Paperlist that I am interested in
- Category
- rag and search
- Stars
- 447
- Readiness
- needs review (48/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, fork interest, documentation. Risks: no push in 1835 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
collaborative-filtering ctr-prediction embeddings graph-embedding industry-recommendations knowledge-graph-for-recommendation
Something wrong? Category · Trend · Risk
Vision AI Solution Accelerator
- Category
- rag and search
- Stars
- 434
- Readiness
- needs review (62/100 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 446 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
azure-computer-vision cognitive-search-vector-store dalle-3 embeddings florence foundation-models
Something wrong? Category · Trend · Risk
A curated list of retrieval-augmented generation (RAG) in large language models
- Category
- rag and search
- Stars
- 431
- Readiness
- needs review (46/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- 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. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
awesome-list awesome-resources embeddings large-language-models llm rag
Something wrong? Category · Trend · Risk
Classify Kaggle Consumer Finance Complaints into 11 classes. Build the model with CNN (Convolutional Neural Network) and Word Embeddings on Tensorflow.
- Category
- rag and search
- Stars
- 425
- Readiness
- needs review (61/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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.
cnn convolutional-neural-networks embeddings keras multi sentence-classification
Something wrong? Category · Trend · Risk
MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.
- Category
- rag and search
- Stars
- 425
- Readiness
- needs review (47/100 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. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
chatbot embeddings llms rag retrieval-augmented-generation
Something wrong? Category · Trend · Risk
A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks"
- Category
- rag and search
- Stars
- 423
- Readiness
- needs review (59/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, fork interest, documentation. Risks: no push in 743 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
dynamic-networks embedding-trajectories embeddings kdd2019 machine-learning network-embedding
Something wrong? Category · Trend · Risk
Fast word vectors with little memory usage in Python
- Category
- rag and search
- Stars
- 416
- Readiness
- high risk (44/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation. Risks: no push in 1868 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
embeddings fasttext gensim glove lmdb magnitude
Something wrong? Category · Trend · Risk
Elasticsearch plugin for nearest neighbor search. Store vectors and run similarity search using exact and approximate algorithms.
- Category
- rag and search
- Stars
- 395
- 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.
elasticsearch elasticsearch-plugin embeddings locality-sensitive-hashing lucene nearest-neighbor-search
Something wrong? Category · Trend · Risk
Provide best practices for LMOps, as well as elegant and convenient access to the features of the Qianfan MaaS Platform. (提供大模型工具链最佳实践，以及优雅且便捷地访问千帆大模型平台）
- Category
- rag and search
- Stars
- 384
- 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 rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 238 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
baidu bce chat embeddings ernie-bot finetuning
Something wrong? Category · Trend · Risk
Production-ready K-Means clustering for Apache Spark with pluggable Bregman divergences (KL, Itakura-Saito, L1, etc). 6 algorithms, 740 tests, cross-version persistence. Drop-in replacement for M
- Category
- rag and search
- Stars
- 342
- Readiness
- needs review (57/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 29/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 174 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
bregman-divergence clustering cosine-similarity embeddings entropy euclidean-distance
Something wrong? Category · Trend · Risk
Reliable and Efficient Semantic Prompt Caching with vCache
- Category
- rag and search
- Stars
- 76
- Readiness
- ready (75/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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.
cache chatbot consistency correctness gpt guarantees
Something wrong? Category · Trend · Risk
Setup and run a local LLM and Chatbot using consumer grade hardware.
- Category
- rag and search
- Stars
- 346
- Readiness
- needs review (55/100 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 257 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
artificial-intelligence chatbot large-language-models llama-cpp-python llm openai
Something wrong? Category · Trend · Risk
A full-stack demo showcasing a local RAG (Retrieval Augmented Generation) pipeline to chat with your PDFs.
- Category
- rag and search
- Stars
- 533
- Readiness
- needs review (61/100 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, fork interest, documentation. Risks: no push in 113 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
langchain nextjs ollama pdf rag vercel-ai-sdk
Something wrong? Category · Trend · Risk
基于LangChain、FastAPI和React的RAG项目，主分支为基于RAG的智能笔记助手，base-rag分支为开箱即用的基础RAG项目供学习使用
- Category
- rag and search
- Stars
- 417
- Readiness
- ready (79/100 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.
chromadb fastapi langchain mysql rag react
Something wrong? Category · Trend · Risk
The data scientist's open-source choice to scale, assess and maintain natural language data. Treat training data like a software artifact.
- Category
- rag and search
- Stars
- 1,470
- Readiness
- needs review (51/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- risky
- Maintenance risk
- 30/100 · low confidence
Why: High-signal rag and search project
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 606 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
active-learning annotations artificial-intelligence data-centric-ai data-labeling data-science
Something wrong? Category · Trend · Risk
🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.
- Category
- rag and search
- Stars
- 291
- Readiness
- needs review (55/100 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 256 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai ai-safety caching cargo coding-assistant context-aware
Something wrong? Category · Trend · Risk
A curated collection of resources for 🌌 Azure OpenAI, 🦙 LLMs (+RAG, Agents). Monthly Updates.
- Category
- rag and search
- Stars
- 405
- Readiness
- ready (81/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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 agent-framework agent-skills ai-engineering ai-tools awesome
Something wrong? Category · Trend · Risk
LLM and agent evaluation for Java & Kotlin. Runs in JUnit and CI. Spring AI, LangChain4j, Koog, Embabel, and any LLM client.
- Category
- rag and search
- Stars
- 50
- Readiness
- ready (86/100 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-evaluation agentic-ai embabel evaluation evaluation-framework evaluation-metrics
Something wrong? Category · Trend · Risk
Data-Driven Evaluation for LLM-Powered Applications
- Category
- rag and search
- Stars
- 514
- 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 rag and search project
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.
evaluation-framework evaluation-metrics information-retrieval llm-evaluation llmops rag
Something wrong? Category · Trend · Risk
Dataset and benchmark for RAG on company internal documents.
- Category
- rag and search
- Stars
- 502
- Readiness
- needs review (54/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- watch
- Maintenance risk
- 15/100 · low confidence
Why: +10 stars in 7 days
Why it may be a gem: healthy maintenance and project fundamentals
Strongest signals: issue load, documentation, license. Risks: no push in 91 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
benchmark dataset enterprise enterprise-search evaluation generative-ai
Something wrong? Category · Trend · Risk
Harness LLMs with Multi-Agent Programming
- Category
- rag and search
- Stars
- 4,090
- Readiness
- ready (86/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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.
agents ai chatgpt function-calling gpt gpt-4
Something wrong? Category · Trend · Risk
AI Client for chat, RAG, plans, MCP tools, and agents. Support multiple LLMs (Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM, Gemini, OpenRouter)
- Category
- rag and search
- Stars
- 298
- Readiness
- ready (88/100 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.
agentic-workflow ai ai-assistant artificial-intelligence chat-client chatgpt
Something wrong? Category · Trend · Risk
A local-first second brain for scientists, researchers, coders, and nerds.
- Category
- rag and search
- Stars
- 24
- Readiness
- ready (77/100 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.
academic-writing ai desktop-app embeddings knowledge-graph knowledge-management
Something wrong? Category · Trend · Risk
n2-QLN: Intelligent Tool Router & Semantic Search Layer for MCP. Connect 1,000+ tools through 1 interface. Prevent AI model confusion and maximize context window efficiency
- Category
- rag and search
- Stars
- 42
- Readiness
- ready (85/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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-agent-orchestration efficiency llm-gateway mcp semantic-search sqlite-vss
Something wrong? Category · Trend · Risk
A modular, skill-based autonomous Security Operations Center (SOC) agent that monitors OpenSearch/Elasticsearch data, builds RAG-based behavioral memory, and validates real-time anomalies using LLMs.
- Category
- rag and search
- Stars
- 263
- Readiness
- ready (91/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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-agents ai-security anomaly-detection autonomous-agents cybersecurity llm
Something wrong? Category · Trend · Risk
A Fork of Rikkahub with an overhauled UI and feature additions
- Category
- rag and search
- Stars
- 324
- Readiness
- ready (83/100 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, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.
ai ai-assistant ai-roleplay android android-app android-application
Something wrong? Category · Trend · Risk
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated r
- Category
- rag and search
- Stars
- 1,784
- Readiness
- ready (88/100 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.
computer-vision generative-ai long-video-understanding model-context-protocol multimodal-ai natural-language-search
Something wrong? Category · Trend · Risk
MODA: open-source fashion retrieval benchmark and models. Beats Marqo FashionSigLIP on image-to-image (LookBench Fine R@1 67.68) and on 4 of 6 public text-to-image benchmarks at equal parameters. MIT
- Category
- rag and search
- Stars
- 41
- Readiness
- ready (92/100 heuristic points; not a probability)
- Data confidence
- low
- Maintainer health
- healthy
- Maintenance risk
- 0/100 · low confidence
Why: High-signal rag and search 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.
benchmark clip cross-encoder ecommerce embeddings fashion
Something wrong? Category · Trend · Risk