AmberLee2427/nancy-brain
Nancy's RAG backend and HTTP API/MCP server connectors.
Ingests GitHub repositories and PDFs into a vector search index (using txtai/FAISS embeddings) with dynamic per-document weighting, exposing results via FastAPI HTTP endpoints and Model Context Protocol tools for AI agents. Supports optional document summaries via local models or Anthropic API, chunking configuration via `chunky-files`, and a Streamlit admin UI for managing repositories, articles, and knowledge base builds without CLI overhead.
Available on PyPI.
Stars
2
Forks
2
Language
Python
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Dependencies
31
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/AmberLee2427/nancy-brain"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shinpr/mcp-local-rag
Local-first RAG server for developers using MCP. Semantic + keyword search for code and...
nkapila6/mcp-local-rag
"primitive" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨
tac0de/knowledge-to-action-mcp
MCP server for Obsidian GraphRAG, agent-ready context, preview-only planning, and safe repo handoffs
Daniel-Barta/mcp-rag-server
Lightweight RAG server for the Model Context Protocol: ingest source code, docs, build a vector...
yumeiriowl/repo-graphrag-mcp
An MCP server that uses LightRAG and Tree-sitter to build a repository knowledge graph from code...