Connect a model

PDX Ops runs on your Windows desktop and connects to an AI model to provide intelligence. The agent executes your monitoring commands, and in Ask first mode you approve every change before it runs.

Choose your model

Cloud provider

Your prompt and the data the agent reads (command output, files) go to that provider, with secrets redacted first.

Local model

Run a model directly on your PC using WSL or a local endpoint. With a local model nothing leaves the PC.

Built-in model

It is ready to use without your own endpoint.

Test your connection

Press the Test button to verify your chosen endpoint. The tool shows the response time and the context window.

Select the right model

Use a bigger model for refactors or complex logic. Use a smaller model for small edits. You can send a hard step to a bigger model using the run_on_model orchestration feature for better results.

Quality varies between models, so review the diff carefully. Use Ask first to pause before every action that changes something. This ensures you approve every command before it affects your Linux server.