Two weeks ago, I launched Kaizen Agent – an open-source tool to help you test, debug, and automatically fix LLM agents and apps.

It runs evaluations based on YAML-defined inputs/outputs, detects failures, suggests fixes, re-runs tests, and even opens a pull request — all from a single CLI command.

What’s new since launch: Greatly improved README with better examples and onboarding

Now compatible with Mastra, a popular TypeScript agent framework

Full documentation site launched → https://kaizen-agent.github.io/kaizen-agent/

Available on PyPI → pip install kaizen-agent

It’s still early, but if you’re building production-ready LLM apps and tired of tedious trial and error, I’d love your feedback. Try it out locally — and if you find it useful, a GitHub would mean a lot!

Thanks for checking it out