Show HN: Strava for AI coding – analytics on your Copilot/Claude/Codex usage (github.com)

A new open-source tool called "AI Engineer Coach" has been launched to provide comprehensive analytics on the usage of AI coding assistants such as Copilot, Claude, and Codex. This tool analyzes local session logs without sending data externally, offering engineers actionable insights to improve their coding practices. Key features include tracking progress through practice scores and activity charts, detecting anti-patterns with 45 editable rules, and measuring output by coding language and model. Additionally, it highlights repeated prompts to help users develop reusable skills and offers context health checks to ensure optimal usage of these AI tools. The significance of this tool lies in its potential to enhance the programming experience and productivity for developers using AI assistants. By offering a localized analytics platform, it empowers users to adopt more effective coding strategies while maintaining their data privacy. The ability to visualize trends, identify weaknesses, and promote efficient practices can lead to better software development outcomes, making it a valuable resource in the AI/ML community. As the demand for AI-driven programming solutions increases, tools like AI Engineer Coach can facilitate smarter development cycles and foster skill growth among engineers.