Metadata-Version: 2.5
Name: roboharm
Version: 0.0.3
Summary: RoboHarm ships in robouse (agent as a policy for embodied agents): pip install robouse. https://robouse.ai
Project-URL: Homepage, https://robouse.ai
Project-URL: robouse, https://pypi.org/project/robouse/
Project-URL: Repository, https://github.com/benchflow-ai/robouse
Project-URL: RoboHarm study, https://robouse.ai/work/robouse-harm-1/
Author-email: Xiangyi Li <xiangyi@benchflow.ai>
License-Expression: Apache-2.0
Keywords: alignment,benchflow,embodied-agents,robotics,safety
Classifier: Development Status :: 7 - Inactive
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.11
Requires-Dist: robouse>=0.1.0
Description-Content-Type: text/markdown

# roboharm

RoboHarm, alignment for embodied agents, is part of **robo-use** ([robouse.ai](https://robouse.ai)). The code and the RoboHarm task suite ship in the [`robouse`](https://pypi.org/project/robouse/) package:

```sh
pip install 'robouse[sim]'
robouse tasks | grep roboharm
```

This package only points there: installing `roboharm` installs `robouse`. First study: [Reproducing Robocurve's RoboHarm](https://robouse.ai/work/robouse-harm-1/).
