Metadata-Version: 2.4
Name: cocapn-colora
Version: 0.2.0
Summary: Multi-modal color theory engine — palette generation and visual identity for fleet agents
Author: Cocapn
License: MIT
Project-URL: Homepage, https://github.com/SuperInstance/cocapn-colora
Keywords: cocapn,fleet,agent
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# cocapn-colora

Value-conditioned LoRA adapters — adapters shaped by what the agent values.

Not just adapters — adapters shaped by values. Colora conditions LoRA fine-tuning on agent-defined value functions, producing specialized models that reflect fleet priorities.

## What It Does

- **Value Functions** — Define what matters (accuracy, safety, creativity)
- **Conditioned LoRA** — Fine-tune with value-aware gradient weighting
- **Adapter Composition** — Stack multiple value-conditioned adapters
- **Evaluation** — Score adapters against their target values

## Installation

```bash
pip install cocapn-colora
```

## Part of the Cocapn Fleet

Used by Forgemaster for LoRA training on the RTX 4050.

## License

MIT
