Kaizen Agent is an open-source CLI tool that helps you ship better LLM apps by automating the boring parts of development:
🧪 Define test cases in a simple YAML file (input, expected output, pass/fail conditions)
🤖 Automatically run all test cases
🧠 If something fails, the agent analyzes and suggests prompt/code changes
🔁 It keeps retrying until the test passes
📦 Then it makes a pull request with the fix — ready to review
No more endless trial and error. Just write your tests and let the agent do the rest.