knowledge-rag
Local RAG server for Claude Code, Cursor and other MCP clients: hybrid BM25 + vector search with cross-encoder reranking on by default, 13 MCP tools, 33 file types including code, re-indexing on file changes. One Python process with embedded ChromaDB and FastEmbed ONNX: no Docker, database server or API key; offline after the first model download.
Open the source (opens github.com) https://github.com/lyonzin/knowledge-rag
What it is
AI repositories from lyonzin.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
Get the code
git clone https://github.com/lyonzin/knowledge-rag.git
Standard git access to a public repository
Setup steps: not provided by the source. Follow the instructions on the source.
Related
-
loci
AI repositoriesShared memory for AI coding tools: hybrid search, cited Q&A, harness memory discovery and a built-in Web console. Local index, MCP + HTTP.
git clone https://github.com/IvenKooLab/loci.git -
memex
AI repositoriesSearch Claude Code, Codex, Pi, OpenCode, Github Copilot & Cursor transcripts. Resume sessions. Track tokens.
git clone https://github.com/nicosuave/memex.git -
mempalace
AI repositoriesThe best-benchmarked open-source AI memory system. And it's free.
git clone https://github.com/MemPalace/mempalace.git -
graphify
AI repositoriesTurn 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.
git clone https://github.com/Graphify-Labs/graphify.git -
pmb
AI repositoriesLocal-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.
git clone https://github.com/oleksiijko/pmb.git -
bm25s
AI repositoriesFast BM25 search in Python, powered by Numpy and Numba
git clone https://github.com/xhluca/bm25s.git