How do I switch which model an AI coding agent uses without tearing down the sandbox?
Last updated: 4/27/2026
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 needed.
Note that filesystem and process policies are the only layers that require full sandbox re-creation.
Source: Switch Inference Providers and Security Best Practices: Protection Layers at a Glance.