code-review-graph

code-review-graph builds a structural map of your codebase using Tree-sitter to provide AI assistants with precise, context-aware information. By tracking changes incrementally and calculating the blast radius of modifications, it significantly reduces token consumption during code reviews. The tool integrates seamlessly with various AI coding platforms via the Model Context Protocol to ensure only relevant code is analyzed.

code-review-graph is a structural analysis tool designed to optimize AI coding assistants by reducing token consumption through intelligent context pruning. By utilizing Tree-sitter to build a persistent graph of code entities and their relationships, it enables AI models to focus only on the 'blast radius' of specific changes rather than scanning entire repositories. This approach addresses the inefficiency of current AI coding tools that often re-read large codebases, providing a significant performance boost and cost reduction in complex development environments.