code-review-graph
code-review-graph is a local code map that lets AI coding tools read only the files a change touches, for developers reviewing code.
What it is good for
- Reducing how much code an AI assistant reads during a review
- Finding callers and tests affected by a code change
- Keeping a codebase map updated as files change
- Running risk-scored pull request reviews in CI
At a glance
- Who it is for
- Setup
- Guided command-line setup
Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.
- Cost
- Free and open source
- Type
- MCP server or connector
- Tasks
- Works with
- Claude Code, Cursor, Windsurf, Zed, Codex, GitHub Actions
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 32,557
GitHub numbers as of Nov 2, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is code-review-graph free?
- Yes. It is free and open source (MIT license).
- Do I need to know how to code to use code-review-graph?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does code-review-graph work with?
- According to its own documentation, it works with Claude Code, Cursor, Windsurf, Zed, Codex, and GitHub Actions.
- What is code-review-graph good for?
- Reducing how much code an AI assistant reads during a review, finding callers and tests affected by a code change, keeping a codebase map updated as files change, and running risk-scored pull request reviews in CI.
Similar agents to code-review-graph
- REA
REA is an MCP server that lets AI agents reverse engineer apps and native binaries to explain how a feature works.
- CodeGraph
CodeGraph is a code knowledge graph that gives AI coding agents the relevant source code in fewer steps, running locally on your machine for developers.
- Context7
Context7 is an MCP server that gives AI coding agents up-to-date library documentation for developers.
- chrome-devtools-mcp
Chrome DevTools MCP is a connector that lets coding agents control and inspect a live Chrome browser for testing and debugging.
- codebase-memory-mcp
codebase-memory-mcp is an MCP server that builds a local map of a code repository so AI coding agents can find and trace code faster.
- Playwright MCP
Playwright MCP is an MCP server that lets AI apps control a web browser for you, for people who want their AI to click through websites and read pages.