This project is a suite of automated tools and an LLM code review framework designed for design auditing, security scanning, and AI-driven code analysis. It functions as a developer workflow orchestrator that uses static analysis agents and agent-based workflows to automate pull request analysis and security audits.
The system employs a dual-loop agent architecture to coordinate primary analysis and secondary verification, reducing false positives. It distinguishes itself through the use of browser automation to perform live UI component testing and verify frontend changes against accessibility standards and brand guidelines.
The framework integrates into CI/CD pipelines to trigger automated security reviews and code audits before human intervention. It covers a broad range of capabilities including third-party dependency auditing, severity-based vulnerability classification, and the enforcement of organization-specific engineering standards and security policies.
