Metadata-Version: 2.4
Name: openenv-agent
Version: 0.1.0
Summary: Agent client for OpenEnv environments - connects RL agents to OpenEnv servers for inference and training
Author: Croma
License: MIT
Keywords: openenv,reinforcement-learning,agent,rl,content-moderation
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: openai>=1.3.0
Requires-Dist: httpx>=0.25.0
Requires-Dist: pyyaml>=6.0
Requires-Dist: click>=8.0.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Requires-Dist: ruff>=0.1.0; extra == "dev"
Dynamic: license-file

# OpenEnv Agent

Python client library for connecting RL agents to OpenEnv servers.

## Installation

```bash
pip install openenv-agent
```

## Quick Start

```python
from openenv_agent import OpenEnvClient, ModerationAgent

# Connect to an OpenEnv server
client = OpenEnvClient(base_url="http://localhost:8000")

# Reset environment
obs = client.reset()

# Use the moderation agent
agent = ModerationAgent()
action = agent.predict(obs)

# Step the environment
next_obs, reward, done, info = client.step(action)
```

## CLI Usage

```bash
# Run agent against a server
openenv-agent run http://localhost:8000

# Interactive mode
openenv-agent interactive http://localhost:8000

# Evaluate on a dataset
openenv-agent eval http://localhost:8000 --dataset ./data.json
```

## Features

- Async/sync OpenEnv client with Gymnasium-style API
- Built-in ModerationAgent for content moderation environments
- Environment loader from openenv.yaml configs
- CLI tool for easy server interaction
