Skip to content

[GitHub Trending] tirth8205/code-review-graph

8.3 relevance
Score Breakdown
technical depth
9
novelty
8
actionability
9
community
6
strategic
7
personal
9

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

Local-first code intelligence graph for MCP/CLI, directly addresses developer experience and AI tooling with benchmarked context reductions.

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 a structural AST graph of a codebase, enabling AI coding assistants to read only the minimal set of files affected by a change via blast-radius analysis. It integrates with platforms like Cursor, Claude Code, and GitHub Copilot through MCP, supports incremental updates in under 2 seconds for a 2,900-file project, and can exclude 27,700+ files from review context in large monorepos. Installation is a single pip command with auto-detection of existing AI tools and platform-specific configuration.

Author

tirth8205