# Code-Graph-RAG

> MIT Tree-sitter→Memgraph structural RAG for monorepos

**Category:** AI Agents  
**Pricing:** open-source  
**URL:** https://code-graph-rag.com  
**GitHub:** https://github.com/vitali87/code-graph-rag  
**Added:** 2026-09-27

---

## The Hook

Code-Graph-RAG turns Tree-sitter parses (plus compiler frontends/traces) into a Memgraph knowledge graph so you can query, edit, and optimise multi-language monorepos in plain English.

## What's Good

MIT (vitali87/code-graph-rag). Structural graph+Memgraph RAG via Tree-sitter; PyPI `code-graph-rag`; English query/edit/optimise over monorepos. Site at code-graph-rag.com. ★5,180 from GitHub API 2026-09-27.

## The Catch

Vs LAIN (thin ★9 MCP graph): not an MCP coordinator. Vs plain vector RAG: this is structural graph+Memgraph, not chunk embeddings alone. Enterprise support upsell on the site is optional — OSS path stands alone.

## Verdict

MIT structural graph RAG when monorepo English query/edit needs Memgraph+Tree-sitter — not vector-only RAG and not a thin MCP graph.