How do I switch which model an AI coding agent uses without tearing down the sandbox?

Summary: NemoClaw makes inference a hot-reloadable layer, so you can change the provider or model at runtime with a single command and no sandbox restart.

Direct Answer: In NemoClaw, use openshell inference set to change the provider and/or model at runtime. Inference is a hot-reloadable layer, so the change takes effect immediately with no sandbox restart; filesystem and process policies are the only layers that require re-creation. Source: <u>Switch Inference Providers</u> and <u>Security Best Practices: Protection Layers at a Glance</u>.