Code Review Graph

Code Review Graph: Local-first code intelligence graph that indexes repositories into persistent graphs for AI coding tools.

Code Review Graph builds a persistent local graph of functions, calls, imports, and blast radius to serve targeted context to AI coding assistants. It parses 39 languages along with Jupyter and Databricks notebooks into a SQLite-backed graph using Tree-sitter. The system processes data locally on the user machine to ensure code privacy while connecting with tools like Claude Code, Cursor, Copilot, Codex, Windsurf, and Zed. Designed for engineering teams using AI assistants, it prevents tools from re-reading entire codebases on every prompt. Features include 30 MCP tools, 5 prompts, and incremental updates that re-index modified files in about 2.5 seconds.

Code Review Graph at a glance

Best for: Software engineer
Runs on: CLI, VS Code, API
Pricing: MIT licensed
Released: February 2026
Category: AI coding tool
Website: code-review-graph.com

Key features

Persistent local graph indexing
Tree-sitter parse pipeline
Blast radius and call chain calculation
Thirty MCP tools and five prompts
Incremental two-file re-indexing
Local-first code processing
Support for thirty-nine languages plus notebooks

Use it for

Reducing AI context window token usage during code reviews
Serving precise repository context to MCP-compatible AI assistants
Tracking blast radius and risk scores for code changes

Companions

Tools that articles about Code Review Graph recommend using with it, each with its job.

Claude Code — Installs as a skill so the agent queries the graph before grepping.
Codex — The installer wires the same graph into Codex.
Cursor — Auto-detected and configured alongside Claude Code.
OpenCode — Supported for mixed-agent setups.
Obsidian — Open the output as a vault to see how the code clusters.

Alternatives to Code Review Graph

CodeGraph — It eliminates file crawling, reducing AI agent tool calls by 88% and cutting costs.
CodeGraphContext — Turns codebases into interactive knowledge graphs for AI assistants.
Crit — It keeps human feedback localized and precise for AI agent code iterations.
Codebase Memory MCP — High-speed indexing and persistent knowledge graphs for AI coding agents.
Graphify — It replaces grepping with traceable graph paths, reducing token usage significantly.
Graphite — Accelerates review cycles with AI code reviews and stacked pull requests.
Axiomcodegraph — Resolves calls from types rather than syntax for higher accuracy.
arcKode — Runs fully locally via Ollama with symbol-level code indexing for compact VRAM setups.
Skillhub Local — Consolidates scattered AI agent context and skills into one local dashboard.
Rubi — It cuts AI token waste by keeping sessions short and mapping project knowledge.
SmallCode — Runs fully local with budget-managed context and a forgiving parser for small models.
CodeSight — Reduces AI token usage significantly and maps projects instantly.

All Code Review Graph alternatives