benmarte/autoimprove

README preview

<div align="center">

# 🔁 autoimprove

### Autonomous codebase improvement loop for Claude Code

[![Claude Code](https://img.shields.io/badge/Claude%20Code-Plugin-blueviolet?logo=anthropic)](https://code.claude.com)
[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
[![Languages](https://img.shields.io/badge/languages-10%2B-blue)](#supported-languages)

*Inspired by [karpathy/autoresearch](https://github.com/karpathy/autoresearch) — but for any codebase, not just ML training loops.*

</div>

---

## What is this?

Karpathy's `autoresearch` lets an AI agent run ML experiments overnight: modify `train.py` → measure `val_bpb` → keep if better, discard if worse → repeat. You wake up to a log of experiments and a better model.

View full repository on GitHub →