Choose your model endpoint

RemoteOps Loom runs on Windows and connects to an AI provider through a standard API endpoint, or uses a model running locally on your PC, or the built-in model (ready to use without your own endpoint).

Three ways to connect

Cloud API provider

Use a cloud AI provider through a standard API endpoint. Your prompts and file text go only to the model endpoint you pick.

Local PC model

Run a model directly on your Windows PC. With a local model, your prompts and file text are not sent to a cloud provider.

Built-in model

The built-in model is ready to use without your own endpoint.

Test your connection

Press the Test button to verify your endpoint configuration before running any commands. The interface displays the response time and the available context window for your selected model.

Select the right size

Send a hard step to a bigger model using run_on_model for complex refactors. Use a smaller model for small edits to save resources and reduce latency. This orchestration allows you to balance performance with cost when managing your Linux server administration tasks.

Quality varies between models, so always review the diff before accepting changes. Use Ask first mode to pause before every action that changes something. This ensures you see the exact file modification before the agent applies it to your working folder.