Skip to content

[GitHub Trending] tirth8205/code-review-graph

8 relevance
Score Breakdown
technical depth
9
novelty
8
actionability
8
community
5
strategic
6
personal
10

Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.

Local-first code intelligence graph for MCP directly improves AI coding tool efficiency.

AI/ML github.com
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-rep...
Summary

Code-review-graph is an open-source Python tool that uses Tree-sitter to build an AST-based structural map of a codebase, enabling AI coding assistants to perform reviews with precise, incremental context via the Model Context Protocol (MCP). It supports 15+ platforms including Cursor, Claude Code, and GitHub Copilot, and can compute a change's blast radius in seconds for a 500-file project, eliminating full-codebase re-reads. The tool auto-detects installed AI tools and configures MCP endpoints, hooks, and platform rules with a single command, while its uninstaller safely removes only its own artifacts.

Author

tirth8205