tt-proxy 0.1.0

Connect your local Ollama LLMs to Tasking — real-time WebSocket relay

tt-proxy

Connect your local Ollama LLMs to Tasking — real-time streaming, no port forwarding needed.

Install

pip install tt-proxy

Usage

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

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 running locally