K
knowledge-rag
lyonzin/knowledge-rag
Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.
★243stars
Python
MIT
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?Plugins, MCP & Skills project leveraging antigravity and claude, built with Python, open-source
Who made it?Maintained by lyonzin team, 243⭐ on GitHub, #1268 out of 2373 in Plugins, MCP & Skills
Why does it exist?As the Plugins, MCP & Skills landscape evolved, the lyonzin team identified the need for better antigravity solutions. knowledge-rag was created to simplify claude workflows.
What can it do?Key use cases: claude-code, claude-code-cli, codex
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/lyonzin/knowledge-rag | 官网 https://pypi.org/project/knowledge-rag/
🔗 github.com/lyonzin/knowledge-rag | 官网 https://pypi.org/project/knowledge-rag/
Topics
antigravityclaudeclaude-codeclaude-code-clicodexcursor-aidocument-searchhybrid-searchinteligencia-artificialknowledge-baselocal-aimcpmcp-serverragrag-chatbotrag-pipelinererankingretrieval-augmented-generationsemantic-searchvector-database