Metadata-Version: 2.4
Name: autohelix
Version: 0.1.0
Summary: Agent-powered iterative optimization: put an AI agent in a verified improvement loop
Project-URL: Homepage, https://github.com/awslabs/AutoHelix
Project-URL: Repository, https://github.com/awslabs/AutoHelix
Project-URL: Issues, https://github.com/awslabs/AutoHelix/issues
Author: Matthew Trager, Elman Mansimov, Yi Zhang, Wei Xia, Stefano Soatto
License-Expression: Apache-2.0
License-File: LICENSE
License-File: NOTICE
Keywords: agent,ai,claude,code-generation,llm,optimization
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.11
Requires-Dist: click>=8.0
Requires-Dist: jinja2>=3.1
Requires-Dist: pyyaml>=6.0
Requires-Dist: rich>=13.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0; extra == 'dev'
Provides-Extra: examples
Requires-Dist: numpy>=1.20; extra == 'examples'
Requires-Dist: scikit-learn>=1.4; extra == 'examples'
Requires-Dist: scipy>=1.10; extra == 'examples'
Description-Content-Type: text/markdown

# AutoHelix

**Put an AI agent in a verified improvement loop.**

Set constraints and metrics; an AI agent proposes changes in a loop, and only
changes that pass your checks get merged. Works with Claude Code, Codex, and
OpenCode.

```bash
pip install autohelix
```

Documentation, examples, and demos: **https://github.com/awslabs/AutoHelix**
