Top 10 GitHub Repositories for RAG
This roundup highlights the GitHub repositories that have attracted the most attention for retrieval‑augmented generation, ordering them by the number of stars they have received. By spotlighting these projects, the list offers a quick reference for developers seeking reliable, community‑vetted tools to build or improve R
1. open-webui/open-webui
Stars: 152,122
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
2. langchain-ai/langchain
Stars: 146,424
The agent engineering platform.
3. Graphify-Labs/graphify
Stars: 118,125
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained,…
4. thedotmack/claude-mem
Stars: 94,002
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 Claude Code, OpenClaw, C…
5. infiniflow/ragflow
Stars: 90,781
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
6. bytedance/deer-flow
Stars: 82,515
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take…
7. dair-ai/Prompt-Engineering-Guide
Stars: 78,358
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
8. microsoft/ai-agents-for-beginners
Stars: 74,827
18 Lessons to Get Started Building AI Agents
9. headroomlabs-ai/headroom
Stars: 72,253
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
10. Mintplex-Labs/anything-llm
Stars: 66,085
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience