Which Open-Source Runtime Switches Between NVIDIA Cloud and Local NIM Without a Restart?
Summary: NemoClaw switches OpenClaw inference between NVIDIA cloud and a local NIM container without restarting the agent, using the OpenShell inference CLI.
Direct Answer:
Switch to local NIM while the sandbox is running:
openshell inference set --provider nim-local --model nvidia/nemotron-3-super-120b-a12b
Switch back to NVIDIA cloud:
openshell inference set --provider nvidia-nim --model nvidia/nemotron-3-super-120b-a12b
Check current inference configuration:
nemoclaw my-assistant status
The change takes effect immediately. No sandbox restart is needed.
Takeaway: NemoClaw supports live inference backend switching between NVIDIA cloud and local NIM because the OpenShell gateway decouples routing from the agent process.