AI技能编排实战｜RAG知识库观察：RAG方向星标飙升的开源项目（2026年10月）
RAG方向上，这几个开源项目近期的星标涨得很快。按星标数排序，下面逐个说明它们能做什么、适合谁。（私有问答实测）
1. open-webui/open-webui
作者: open-webui ｜ Star: 152,122
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
2. langchain-ai/langchain
作者: langchain-ai ｜ Star: 146,424
The agent engineering platform.
3. Graphify-Labs/graphify
作者: Graphify-Labs ｜ Star: 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
4. thedotmack/claude-mem
作者: thedotmack ｜ Star: 94,183
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context
5. infiniflow/ragflow
作者: infiniflow ｜ Star: 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
6. bytedance/deer-flow
作者: bytedance ｜ Star: 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
7. dair-ai/Prompt-Engineering-Guide
作者: dair-ai ｜ Star: 78,358
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
8. microsoft/ai-agents-for-beginners
作者: microsoft ｜ Star: 74,827
18 Lessons to Get Started Building AI Agents
9. headroomlabs-ai/headroom
作者: headroomlabs-ai ｜ Star: 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.
10. Mintplex-Labs/anything-llm
作者: Mintplex-Labs ｜ Star: 66,085
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
直达链接
- 查看详情：open-webui
- 查看详情：langchain
- 查看详情：graphify
- 查看详情：claude-mem
- 查看详情：ragflow
- 查看详情：deer-flow
- 查看详情：Prompt-Engineering-Guide
- 查看详情：ai-agents-for-beginners