Metadata-Version: 2.4
Name: rotalabs
Version: 1.1.0
Summary: Trust Intelligence Research - Core package from Rotalabs
Project-URL: Homepage, https://rotalabs.ai
Project-URL: Repository, https://github.com/rotalabs/rotalabs
Project-URL: Documentation, https://rotalabs.ai
Author-email: Rotalabs <research@rotalabs.ai>
License-Expression: AGPL-3.0-or-later
License-File: LICENSE
Keywords: ai,machine-learning,research,trust
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Provides-Extra: telemetry
Requires-Dist: httpx>=0.25.0; extra == 'telemetry'
Description-Content-Type: text/markdown

# Rotalabs

AI Trust Infrastructure - Open source tools for building trustworthy AI systems.

**Documentation Hub:** [rotalabs.github.io/rotalabs](https://rotalabs.github.io/rotalabs/)

## Packages

| Package | Description | Docs |
|---------|-------------|------|
| [rotalabs-steer](https://github.com/rotalabs/rotalabs-steer) | Activation steering for LLM behavior control | [Docs](https://rotalabs.github.io/rotalabs-steer/) |
| [rotalabs-probe](https://github.com/rotalabs/rotalabs-probe) | Sandbagging detection via activation probes | [Docs](https://rotalabs.github.io/rotalabs-probe/) |
| [rotalabs-redqueen](https://github.com/rotalabs/rotalabs-redqueen) | Evolutionary adversarial testing | [Docs](https://rotalabs.github.io/rotalabs-redqueen/) |
| [rotalabs-verity](https://github.com/rotalabs/rotalabs-verity) | Neuro-symbolic verified code synthesis | [Docs](https://rotalabs.github.io/rotalabs-verity/) |
| [rotalabs-eval](https://github.com/rotalabs/rotalabs-eval) | LLM evaluation with statistical rigor | [Docs](https://rotalabs.github.io/rotalabs-eval/) |
| [rotalabs-cascade](https://github.com/rotalabs/rotalabs-cascade) | Multi-stage decision routing | [Docs](https://rotalabs.github.io/rotalabs-cascade/) |
| [rotalabs-fieldmem](https://github.com/rotalabs/rotalabs-fieldmem) | Field-theoretic memory systems | [Docs](https://rotalabs.github.io/rotalabs-fieldmem/) |
| [rotalabs-graph](https://github.com/rotalabs/rotalabs-graph) | GNN-based trust propagation | [Docs](https://rotalabs.github.io/rotalabs-graph/) |
| [rotalabs-accel](https://github.com/rotalabs/rotalabs-accel) | Inference acceleration with Triton | [Docs](https://rotalabs.github.io/rotalabs-accel/) |
| [rotalabs-comply](https://github.com/rotalabs/rotalabs-comply) | AI compliance infrastructure | [Docs](https://rotalabs.github.io/rotalabs-comply/) |
| [rotalabs-audit](https://github.com/rotalabs/rotalabs-audit) | Reasoning chain transparency | [Docs](https://rotalabs.github.io/rotalabs-audit/) |

## Install

```bash
pip install rotalabs-steer
pip install rotalabs-verity
# etc.
```

## License

All packages are licensed under [AGPL-3.0](LICENSE). For commercial licensing, contact [research@rotalabs.ai](mailto:research@rotalabs.ai).

## Links

- Website: [rotalabs.ai](https://rotalabs.ai)
- GitHub: [github.com/rotalabs](https://github.com/rotalabs)
