Data / Repositories / RAG / Python
Python RAG repositories on GitHub: 32 ranked by stars
32 public Python repositories tagged RAG are on GitHub, with 642,453 stars between them; 24 had a push in the last 30 days. The most starred: Shubhamsaboo/awesome-llm-apps (141,709), Graphify-Labs/graphify (126,431), unclecode/crawl4ai (85,530).
SpecStream is the live web data engine for teams and agents. It reads open-source repositories on GitHub and keeps what it reads, and this page groups that reading by topic. Ask for the repositories you track by topic, language, license or activity, and new ones and changes arrive in your sheet, CRM, Slack or agent.
Every repository, most starred first
| Repository | What it is | Stars | Forks | License | Last push | Read |
|---|---|---|---|---|---|---|
| Shubhamsaboo/awesome-llm-apps | 100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source. | 141,709 | 20,831 | Apache-2.0 | Oct 13 | Oct 14 |
| Graphify-Labs/graphify | 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… | 126,431 | 12,200 | Apache-2.0 | Oct 14 | Oct 14 |
| unclecode/crawl4ai | Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key. | 85,530 | 8,879 | Apache-2.0 | Oct 14 | Oct 14 |
| headroomlabs-ai/headroom | 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… | 75,347 | 5,847 | Apache-2.0 | Oct 13 | Oct 14 |
| onyx-dot-app/onyx | Open Source AI Platform - AI Chat with advanced features that works with every LLM | 32,453 | 4,560 | Oct 14 | Oct 14 | |
| getzep/graphiti | Build Real-Time Knowledge Graphs for AI Agents | 31,745 | 3,267 | Apache-2.0 | Oct 14 | Oct 14 |
| ScrapeGraphAI/Scrapegraph-ai | Python scraper based on AI | 31,623 | 3,221 | MIT | Oct 6 | Oct 8 |
| 1Panel-dev/MaxKB | MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。 | 22,972 | 3,195 | GPL-3.0 | Oct 14 | Oct 14 |
| arc53/DocsGPT | 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. | 18,319 | 2,208 | MIT | Oct 14 | Oct 14 |
| langbot-app/LangBot | Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ… | 18,160 | 1,652 | Apache-2.0 | Oct 14 | Oct 14 |
| StarTrail-org/LEANN | [MLsys2026 Best Paper]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device. | 13,027 | 1,184 | MIT | Oct 14 | Oct 14 |
| adbar/trafilatura | Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML | 6,845 | 433 | Apache-2.0 | Sep 21 | Sep 21 |
| SenteLabsAI/OpenExecutive | AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js). | 5,600 | 596 | Apache-2.0 | Oct 14 | Oct 14 |
| volcengine/MineContext | MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse） | 5,535 | 415 | Apache-2.0 | May 7 | Oct 14 |
| vitali87/code-graph-rag | The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs | 5,256 | 699 | MIT | Oct 14 | Oct 14 |
| alvinreal/awesome-opensource-ai | Curated list of the best truly open-source AI projects, models, tools, and infrastructure. Daily updated. | 4,861 | 684 | CC0-1.0 | Oct 10 | Oct 11 |
| gptme/gptme | Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top! | 4,448 | 450 | MIT | Oct 14 | Oct 14 |
| pipeshub-ai/pipeshub-ai | The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 40+ connectors) into a permission-aware… | 3,833 | 600 | Apache-2.0 | Oct 14 | Oct 14 |
| aiming-lab/SimpleMem | [ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal | 3,831 | 404 | MIT | Jul 24 | Oct 14 |
| doobidoo/mcp-memory-service | Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation. | 2,014 | 347 | Apache-2.0 | Oct 14 | Oct 14 |
| nduckmink/arkon | Arkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via… | 1,493 | 297 | Jun 3 | Oct 14 | |
| cbcoutinho/nextcloud-mcp-server | Nextcloud MCP Server | 384 | 92 | AGPL-3.0 | Oct 14 | Oct 14 |
| guaardvark/guaardvark | Self-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server for Claude Code and Cursor, and local… | 263 | 55 | MIT | Oct 13 | Oct 14 |
| meilisearch/meilisearch-mcp | A Model Context Protocol (MCP) server for interacting with Meilisearch through LLM interfaces. | 194 | 33 | MIT | Sep 8 | Oct 14 |
| ali-kamali/Axon.MCP.Server | Transform your codebase into an intelligent knowledge base for AI-powered development with Cursor IDE, Google AntiGravity, and MCP-enabled assistants | 166 | 24 | Jun 30 | Oct 14 | |
| nkapila6/mcp-local-rag | "primitive" RAG-like web search model context protocol (MCP) server that runs locally. no APIs | 134 | 21 | MIT | Aug 31 | Oct 14 |
| kkjiangk/agent-py | Personal AIOps engineering project with durable workflows, scoped hybrid retrieval, reliable event delivery, and verified API/browser contracts. | 101 | 9 | Oct 4 | Oct 15 | |
| RayenMlayeh/jevcrawl | MCP server and CLI that crawls websites for AI agents: finds the answer page 2x more often than Crawl4AI, 10x cheaper per answer than letting Claude crawl. | 80 | 7 | Apache-2.0 | Oct 15 | Oct 21 |
| jgouviergmail/LIA-Assistant | Smart multi-agent conversational assistant with LangGraph orchestration, Human-in-the-Loop, enterprise-grade observability, and full i18n support (6 languages) | 73 | 11 | Oct 13 | Oct 14 | |
| XAIHT/Tlamatini | Tlamatini is a self-hosted AI developer assistant for local or cloud LLMs: hybrid RAG (FAISS+BM25) over your codebase, a 100+ tool Multi-Turn engine, an 86-agent visual workflow… | 15 | 1 | MIT | Oct 14 | Oct 14 |
| kushalBanda/AI-Engineer | Runnable AI engineering modules: agents, MCP, memory, RAG, voice, fine-tuning, MLOps, and security. One folder per module. | 9 | 2 | MIT | Oct 9 | Oct 14 |
| suyu-creator/github-code-rag-mcp | MCP server for real-time GitHub code search and reuse. FTS5 full-text index + Bing fallback + bonus requirements analysis Agent. Zero git clone, zero vector DB, only 1 dependency. | 2 | 0 | MIT | Aug 25 | Oct 14 |
Other languages
- TypeScript 11
- Rust 9
- JavaScript 3
- Go 3
Related topics
- LLM 49
- MCP 34
- AI 28
- AI agents 23
- Agents 22
- Python 19
- MCP server 18
- Model Context Protocol 12
- OpenAI 11
- Semantic search 11
- Claude Code 10
- Artificial intelligence 10
Read from GitHub by SpecStream between September 21, 2026 and October 21, 2026; each row shows the day its repository was read. Stars and pushes change every day, and the GitHub page is the current one. Forks and archived repositories are left out.