tobocop2/lilbee
Local, offline experimental knowledge base. Index documents and code, search or ask questions — from the terminal or any AI agent. Built on Ollama + LanceDB + Kreuzberg + tree-sitter.
Supports hybrid RAG with semantic and BM25 search, exposing results via MCP server or JSON CLI for seamless agent integration. Features AST-aware code chunking via tree-sitter, multi-format ingestion (PDFs, Office docs, images with OCR), and per-project isolated indexes. Provides a REST API for embedding search into existing tools like Obsidian, plus interactive local chat without requiring external LLMs during retrieval.
4 stars and 2,176 monthly downloads. Available on PyPI.
Stars
4
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Monthly downloads
2,176
Commits (30d)
0
Dependencies
11
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/tobocop2/lilbee"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mhalder/qdrant-mcp-server
MCP server for semantic search using local Qdrant vector database and OpenAI embeddings
qdrant/mcp-server-qdrant
An official Qdrant Model Context Protocol (MCP) server implementation
cornelcroi/context-lens
Semantic search knowledge base for MCP-enabled AI assistants. Index local files or GitHub repos,...
tomschell/personal-kg-mcp
Personal Knowledge Graph MCP Server - Decision intelligence for multi-agent workflows
n-r-w/knowledgegraph-mcp
MCP server for enabling persistent knowledge storage for Claude through a knowledge graph with...