Metadata-Version: 2.4
Name: flowkit-sdk
Version: 0.1.1
Summary: Python SDK for the Flowkit AI voice kernel
Author: Flowkit Authors
License: Apache-2.0
Project-URL: Homepage, https://github.com/DeepFlowAI/flowkit
Classifier: Development Status :: 3 - Alpha
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Communications :: Telephony
Classifier: License :: OSI Approved :: Apache Software License
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: websockets>=12.0
Provides-Extra: test
Requires-Dist: pytest>=8.0; extra == "test"
Requires-Dist: pytest-asyncio>=0.23; extra == "test"

# flowkit-sdk

Python SDK for the [Flowkit](https://github.com/DeepFlowAI/flowkit) AI voice kernel.

> Status: pre-alpha (v0.1.0a1). M1 ships the protocol skeleton only — real
> call handling lands in M2 (WebRTC) and M3 (SIP).

## Install (editable, from this repo)

```bash
python3 -m venv .venv
.venv/bin/pip install -e .
```

## Minimal example

```python
import asyncio
from flowkit import Kernel

async def main():
    async with Kernel("ws://localhost:9600/ws") as kernel:
        # System.hello already completed inside __aenter__.

        @kernel.on("call.incoming")
        async def handle_incoming(event):
            print("incoming:", event)

        await asyncio.sleep(60)  # serve until cancelled

asyncio.run(main())
```

For the full API, see `flowkit/kernel.py` and `flowkit/call.py`.
