GPU worker client for the Talos network. Pairs with your Talos account, serves open-model inference jobs over a WebSocket, and reports uptime for payouts.
Talos worker
Share your GPU with the Talos network and earn. This is the downloadable client (intended to live in its own public GitHub repo, talos-worker). It pairs with your Talos account using a code, then serves open-model inference jobs from the network via your local Ollama, reporting uptime and earning a share of real usage revenue.
The Talos web app never imports this repo. The two only talk over the network: a device code to pair, then jobs and heartbeats over a WebSocket.
Requirements
- Python 3.9+
- Ollama running locally with at least one model pulled,
ollama pull llama3.1:8b
- NVIDIA GPU recommended (detected automatically; CPU also works)
Install
pip install -e .
Pair
Get a code from your dashboard (Pair a device), then:
talos-worker pair # prompts for the code
or non-interactively:
talos-worker pair --code TALOS-XXXX-XXXX --server https://api.usetalos.xyz
Run
talos-worker run --allocation 0.5
- Opens a local dashboard at http://127.0.0.1:8674 with live status and a power
--allocation 0..1sets how much of the machine you offer. It maps to
- Uptime accrues while connected; earnings are credited per served job and
Commands
| Command | Description | | --- | --- | | talos-worker pair | Pair this machine with a code | | talos-worker run | Connect and serve inference jobs | | talos-worker status | Show config, GPU and available models and jobs |
Using talos-auto in your editor
This repo is for two different audiences:
- Sharing a GPU? That's
talos-worker, above: pair it, run it, earn. - Just want talos-auto in your editor? You do not need to run anything;
- Automatic: install sdk/ and run talos setup <tool> โ it writes the real config file for you and backs up the original. - Manual: each tool has its own folder with a guide, a config snippet, a verify.sh quickstart script and a bundled SDK example: cursor/, vscode/ (Continue / Cline), claude-code/, jetbrains/, zed/, aider/.
See docs/ for the shared overview, or examples/ for more example stacks (Go, Node.js, Vercel AI SDK, LiteLLM).
Contributing
See CONTRIBUTING.md.