code-review-graph
Local code graph for AI-assisted reviews with 63x context reduction
Visit code-review-graph.com ↗What is code-review-graph?
code-review-graph builds a persistent structural map of your codebase using Tree-sitter, then serves targeted context to Claude Code, Cursor, Copilot and other MCP-compatible AI assistants. Instead of re-reading entire repositories on each prompt, the tool identifies only the functions, imports and call chains affected by a change, dramatically reducing token usage and review cost while keeping code local.
Designed for engineering teams using AI assistants daily, it supports 39 languages plus Jupyter and Databricks notebooks. The tool installs with a single command, integrates with 16 AI coding platforms, and maintains an incremental SQLite-backed graph that updates in milliseconds without requiring full repository re-indexing.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered code-review-graph automatically. Evidence: GitHub tirth8205/code-review-graph; repo has AGENTS.md, CLAUDE.md, GEMINI.md. View source.
Similar vibe-coded apps
Open source AI gateway routing across 350+ providers through one endpoint
Open-source AI job search agent that runs locally in your CLI
Agent kernel that routes AI models, caches context, and audits tool calls
Beginner-friendly interface for ComfyUI image, video, and music generation
Shared persistent memory for AI coding tools across sessions and applications
In-browser behavior tree execution engine for AI agents at ~60Hz
Local context layer that reduces AI coding agent token usage by 50-90%