knowledge-rag
Drop docs, search instantly from Claude Code — 12 MCP tools, 20 format parsers, hybrid search + reranking. Zero servers, zero API keys, 100% local.
Knowledge RAG is a fully local, zero-cloud document retrieval system that lets Claude Code search your PDFs, markdown, code, and notebooks natively. It indexes up to 1800+ files in under 3 minutes, using hybrid search (BM25 + semantic vectors + cross-encoder reranking) via 12 MCP tools. Everything runs locally via ONNX, no Docker, Ollama, or API keys required.
Features
Compatibility
Quick start
Use cases
Alternatives
Related searches
Comments
- RRebel NguyenMay 10, 2026
RAG from Claude Code without leaving the terminal is a killer productivity pattern
- RRiley WhiteMay 6, 2026
Drop docs and search instantly — the 12 MCP tools cover the full retrieval workflow
- OOaklyn JohnsonApr 22, 2026
20 format parsers means you can feed it almost any document type without preprocessing
- Quinn RiveraMar 4, 2026
Used for codebase documentation search, retrieval quality is noticeably better than naive embedding