code-review-graph

Builds a local map of your codebase so AI coding tools read only the relevant parts. It aims to cut the context needed for code reviews and work in large repositories.

Share on XLicense: MIT

Overview

code-review-graph builds a local knowledge graph of your codebase using Tree-sitter, keeps it updated incrementally, and serves compact context over MCP. The aim is that an AI coding assistant reads only the files a change touches instead of re-reading large parts of the repo. A CLI command detects the AI tools you have installed and configures each one.

Key features

  • Parses code into a structural graph with Tree-sitter
  • Incremental updates as the code changes
  • Serves compact review context over MCP
  • One install command configures detected AI coding tools

Best for

Developers using AI coding tools on large repositories who want reviews to use less context. It installs with pip or pipx and runs entirely on your machine.

Upstream
tirth8205/code-review-graph
Fork on GitHub
Guo-astro/code-review-graph
Upstream stars
32k
Category
AI agents and LLM tools
Language
Python
License
MIT
Forked
2026-03-19
Sync status
In sync, has own commitsLast synced 2026-09-29