tirth8205 / code-review-graph

TL;DR

Code-review-graph is a local-first tool that creates a persistent map of your codebase, enhancing AI coding tools' efficiency. It focuses on delivering relevant context during code reviews and large repository workflows.

✦ Why It Matters

Engineers can implement code-review-graph to streamline their code review process and enhance collaboration in large projects.

Key Takeaways

Install code-review-graph with a single command for easy setup.
Utilize Tree-sitter for efficient code parsing and mapping.
Achieve significant token savings during code reviews.
Enable incremental updates to keep your code graph current.

How It Works

code-review-graph builds a structural map of your codebase using Tree-sitter, which parses the code into an Abstract Syntax Tree (AST). This AST is stored as a graph of nodes and edges, representing functions, classes, and their relationships.

When changes occur, the tool identifies the 'blast radius' of affected files, allowing AI assistants to focus only on relevant changes instead of the entire codebase. This targeted approach drastically reduces the number of tokens processed during reviews.

tirth8205 / code-review-graph

tailwindlabs / tailwindcss

denoland / deno

angular / angular

NASA’s new dark energy space telescope can also detect killer asteroids

tailwindlabs / tailwindcss

denoland / deno

angular / angular

NASA’s new dark energy space telescope can also detect killer asteroids