AI Agent Skill Library in Action | RAG Knowledge Articles: Fast-Rising Open Source Projects in RAG (Oct 2026)

In RAG, these open-source projects are gaining stars fast. Sorted by star count, each entry below says what it does and who it's for. (vector search review)

1. open-webui/open-webui

Owner: open-webui ｜ Stars: 152,122

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

2. langchain-ai/langchain

Owner: langchain-ai ｜ Stars: 146,424

The agent engineering platform.

3. Graphify-Labs/graphify

Owner: Graphify-Labs ｜ 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, no vector store.

4. thedotmack/claude-mem

Owner: thedotmack ｜ Stars: 94,183

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, Codex, Gemini, Hermes, Copilot, OpenCode + More

5. infiniflow/ragflow

Owner: infiniflow ｜ 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

Owner: bytedance ｜ 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 minutes to hours.

7. dair-ai/Prompt-Engineering-Guide

Owner: dair-ai ｜ Stars: 78,358

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

8. microsoft/ai-agents-for-beginners

Owner: microsoft ｜ Stars: 74,827

18 Lessons to Get Started Building AI Agents

9. headroomlabs-ai/headroom

Owner: headroomlabs-ai ｜ 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

Owner: Mintplex-Labs ｜ Stars: 66,085

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

Direct links

Curated by StackPilot —— the ai agent skill library. Browse all categories for the full directory.