Metadata-Version: 2.4
Name: outpost9
Version: 0.0.1
Summary: Python SDK for Outpost9 AI agent deployment platform
Author-email: Outpost9 <hello@outpost9.ai>
License: MIT
Keywords: agents,ai,deployment,outpost9
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
Requires-Dist: starlette>=0.36.0
Requires-Dist: uvicorn>=0.27.0
Provides-Extra: dev
Requires-Dist: pytest-asyncio>=0.23.0; extra == 'dev'
Requires-Dist: pytest>=8.0.0; extra == 'dev'
Description-Content-Type: text/markdown

# Outpost9 Python SDK

Deploy AI agents with one decorator.

## Installation

```bash
pip install outpost9
```

## Quick Start

```python
from outpost9 import route

@route("/research")
async def research(topic: str):
    print(f"Researching: {topic}")  # Streams via SSE
    result = await run_research(topic)
    return {"report": result}
```

## How It Works

1. The `@route` decorator registers your function as an HTTP endpoint
2. `print()` statements are captured and streamed via Server-Sent Events
3. The final return value is sent as the result

## Running Locally

```bash
outpost9-serve
```

This starts a local server with all registered routes.
