This project is an AI-powered code reviewer and static analysis server that identifies low-quality files and generates automated critiques. It functions as an automated quality scoring tool that evaluates source code structure and complexity through local parsing.
The system utilizes a standardized context protocol to stream analysis results to AI agents and editors. It integrates large language models to produce automated reviews and suggestions for improvement based on quantitative quality metrics.
The tool includes a weight-based scoring engine and an asynchronous analysis pipeline for processing files. It supports project-level configuration for file exclusions and metric weights, and exports analysis findings via static code analysis reporting.