Common questions

Jobs wait in the relay queue. When your PC wakes and reconnects, it picks them up. If it stays offline long enough, the job times out and the agent or bot gets an error. Nothing runs while the machine is offline.

Yes. Pause from the system tray so new jobs wait. You can also leave it running; heavy games will compete for the GPU, so pausing is the cleaner option.

Anything that calls MCP or the HTTP API. Coding agents: Cursor, Claude Code, GitHub Copilot agent mode. Assistants: Grok Bot, ChatGPT custom connectors. Custom and automation bots: Slack and Discord bots, scripts, and n8n-style workflows calling the HTTP API from a backend. Setup steps are in the docs.

Windows 10 and 11 are supported today. Mac and Linux clients are planned.

Prompts and model outputs for the jobs you accept travel through the relay so your agent or bot can read the result. The client does not upload your files, screenshots, or browsing history. See the Privacy page.

No. Jobs can only run inference on models already installed in Ollama. See the Security page.

No. The client makes an outbound connection only.

The Windows installer is in private preview. Sign up at relay.idlerate.dev and verify your email, and we'll send you the download link.

Your account needs an active trial or plan. Finish signup and email verification to start your trial.

On the PC, run ollama pull <model>. The new model shows up in list_models after the PC refreshes its list.

Sign up at relay.idlerate.dev. That's also where you start your trial and sign in.

Sharing is rolling out to accounts over the first weeks. Once it reaches your account, sharing is set per machine. Turn it on for a machine and other users' agents and bots can run inference jobs on that GPU while it's idle. Sharing is off until you turn it on. Senders' jobs will stay on their own machines and reach yours only when they pick it for a job or turn on Auto overflow to shared machines (off by default), first come, first served. You can turn sharing off from your dashboard anytime, or use gaming pause in the Idlerate tray app when you start a game. Shared jobs can only run inference on models you've installed, the same limits as your own jobs. Jobs that run on another member's machine are processed in plain text on that PC, so its owner could see the prompt and output. Don't send anything private to shared machines. We're just getting started and growing the community, so tell us what would make sharing more useful for you.

We're just getting started. We're growing the community and building the roadmap around what users ask for.