code-review-graph

Local-first code intelligence graph for AI coding tools: Tree-sitter AST graph + blast-radius analysis served over MCP, so agents read ~82x fewer tokens per review question.

20,541 2,139 Python MITupdated yesterday

coding

View on GitHubDispute this mapping →

Curator's take

The rare benchmark-honest repo: it tells you the 528x number is the best case and its recall metric is circular. Install once, it configures 14 platforms (Codex, Claude Code, Cursor...). Reach for it on monorepos where review context is the token sink; skip on small repos where a grep costs less than the graph's own metadata.

Mapped by ShipWithAI editors · links verified

README.md

code-review-graph

Stop burning tokens. Start reviewing smarter.

English | 简体中文 | 日本語 | 한국어 | हिन्दी

Usage · Commands · FAQ · Troubleshooting · GitHub Action · Reproducing the benchmarks · Roadmap

AI coding tools can end up re-reading large parts of your codebase on review tasks. code-review-graph fixes that. It builds a structural map of your code with Tree-sitter, tracks changes incrementally, and gives your AI assistant precise context via MCP so it reads only what matters.

The Token Problem: 38x to 528x token reduction across 6 real repositories

Quick Start

pip install code-review-graph                     # or: pipx install code-review-graph
code-review-graph install          # auto-detects and configures all supported platforms
code-review-graph build            # parse your codebase

One command sets up everything. install detects which AI coding tools you have, writes the correct MCP configuration for each one, installs platform-native hooks/skills where supported, and injects graph-aware instructions into your platform rules. It auto-detects whether you installed via uvx or pip/pipx and generates the right config. Restart your editor/tool after installing.

One Install, Every Platform: auto-detects Codex, Claude Code, CodeBuddy Code, Cursor, Windsurf, Zed, Continue, OpenCode, Antigravity, Gemini CLI, Qwen, Qoder, Kiro, and GitHub Copilot

To target a specific platform:

code-review-graph install --platform codex       # configure only Codex
code-review-graph install --platform cursor      # configure only Cursor
code-review-graph install --platform claude-code  # configure only Claude Code
code-review-graph install --platform gemini-cli   # configure only G

Continue your stack

What teams reach for next — and why each earns a place beside code-review-graph. Ranked by curator confidence.

Alternative to See all + compare →

codegraph-mcp

No-train, on-prem code knowledge graph served to AI agents over MCP — symbols, call edges, cross-language links and blast-radius queries, with a hash-chained audit log of every read.

Why it fitsBoth pre-index a semantic code graph and serve it to agents over MCP; code-review-graph adds blast-radius/risk scoring and a CI review action, codegraph-mcp stays a leaner symbol/caller index.

codeflow

Paste a GitHub URL or drop a local folder → interactive architecture map in the browser: dependency graph, blast radius, health grade, security scan. Single index.html, zero install.

Why it fitsBoth build a dependency graph with blast-radius analysis; codeflow renders it visually for humans with zero setup, code-review-graph serves a tree-sitter-accurate graph to AI agents over MCP.

Understand-Anything

Plugin for Claude Code and 16 other hosts that turns any codebase into an interactive knowledge graph — multi-agent analysis, layered dashboard, guided tours, diff-impact view, domain mapping.

Why it fitsCode knowledge graphs for opposite consumers: understand-anything renders an explorable dashboard to teach humans the architecture; code-review-graph feeds minimal context to agents.