Metadata-Version: 2.4
Name: open-agent-sdk-v2
Version: 1.0.0
Summary: OpenClaw-inspired AI Agent Framework with NVIDIA Nemotron, Voice, Canvas, Browser Sandbox, and Multi-Channel Support
Author-email: Himan D <himanshu@open.ai>
License: MIT
Keywords: agent,ai,langchain,nemotron,nvidia,openclaw,openshell,orchestration
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.10
Requires-Dist: httpx>=0.27.0
Requires-Dist: langchain-anthropic>=0.2.0
Requires-Dist: langchain-community>=0.3.0
Requires-Dist: langchain-core>=0.3.0
Requires-Dist: langchain-nvidia-ai-endpoints>=0.3.0
Requires-Dist: langchain-openai>=0.2.0
Requires-Dist: langchain>=0.3.0
Requires-Dist: langgraph>=0.2.0
Requires-Dist: pydantic-settings>=2.0.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: python-dotenv>=1.0.0
Requires-Dist: pyyaml>=6.0.0
Requires-Dist: rich>=13.0.0
Requires-Dist: structlog>=24.0.0
Requires-Dist: typer>=0.12.0
Provides-Extra: all
Requires-Dist: playwright>=1.40.0; extra == 'all'
Provides-Extra: browser
Requires-Dist: playwright>=1.40.0; extra == 'browser'
Provides-Extra: voice
Requires-Dist: espeak; extra == 'voice'
Requires-Dist: speechrecognition; extra == 'voice'
Description-Content-Type: text/markdown

# OpenAgent SDK

OpenClaw-inspired AI Agent Framework with NVIDIA Nemotron, Voice, Canvas, Browser Sandbox, and Multi-Channel Support.

## Features

- **NVIDIA Nemotron** - Advanced reasoning with LangChain integration
- **Voice** - Text-to-Speech and Speech-to-Text
- **Canvas** - Interactive code workspace with execution
- **Browser Sandbox** - Playwright-based web automation
- **Multi-Channel** - WhatsApp, Signal, IRC, Matrix, Nostr, and more
- **Memory** - Persistent MEMORY.md-style storage
- **Skills** - Markdown-based skill system
- **TUI** - Terminal user interface included

## Installation

```bash
pip install open-agent-sdk
```

## Quick Start

```python
from open_agent import create_deep_agent

agent = create_deep_agent(name="assistant")
await agent.initialize()
response = await agent.process_message("Hello!")
print(response)
```

## Environment Variables

```bash
export NVIDIA_API_KEY=your_nvidia_api_key
```

## Optional Dependencies

```bash
# Voice support
pip install open-agent-sdk[voice]

# Browser automation
pip install open-agent-sdk[browser]

# All extras
pip install open-agent-sdk[all]
```

## License

MIT License - Himan D <himanshu@open.ai>
