Micro Agent
An AI agent that writes and fixes code for you. Just run micro-agent, give it a prompt, and it'll generate a test and then iterate on code until all test cases pass.
Why?
LLMs are great at giving you broken code, and it can take repeat iteration to get that code to work as expected. So why do this manually when AI can handle not just the generation but also the iteration and fixing?
Why a "micro" agent?
AI agents are cool, but general-purpose coding agents rarely work as hoped or promised. They tend to go haywire with compounding errors. The idea of a micro agent is to:
- Create a definitive test case that can give clear feedback if the code works as intended or not
- Iterate on code until all test cases pass
What this project is not
This project is not trying to be an end-to-end developer. It's a micro agent, small and focused, that does one thing well: write a test, then produce code that passes that test.
