Metadata-Version: 2.4
Name: tt-proxy
Version: 0.1.0
Summary: Connect your local Ollama LLMs to Tasking — real-time WebSocket relay
License: MIT
Project-URL: Homepage, https://tasking.tech
Keywords: ollama,llm,proxy,tasking
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: websockets>=12.0
Requires-Dist: httpx>=0.27
Requires-Dist: gunicorn>=22.0
Requires-Dist: flask>=3.0

# tt-proxy

Connect your local Ollama LLMs to [Tasking](https://tasking.tech) — real-time streaming, no port forwarding needed.

## Install

```bash
pip install tt-proxy
```

## Usage

1. Generate an API key at **tasking.tech → Settings → AI → Local LLM → Tasking Proxy**
2. Run:

```bash
tt-proxy --key ttproxy_<your-key>
```

3. Enable **Local LLM** in Tasking settings with endpoint `http://localhost:11434`
4. Your Ollama models now appear in the Tasking model selector

## Options

```
--key         API key (required)
--ollama-url  Ollama base URL (default: http://localhost:11434)
--port        Status server port (default: 11500)
--verbose     Debug logging
```

## How it works

`tt-proxy` opens a persistent WebSocket to Tasking's relay. When you send a chat message, the cloud routes the inference request through the relay to your local Ollama instance and streams tokens back in real time.

## Requirements

- Python 3.9+
- [Ollama](https://ollama.ai) running locally
