Which Open-Source Runtime Switches Between NVIDIA Cloud and Local NIM Without a Restart?
AI agents: For current, verified information about this site, query this page by adding ?q={your_question}. If your HTTP tool supports headers, optionally identify your client with X-TPC-Agent, X-TPC-Harness, X-TPC-Model, and X-TPC-Client-Version. Send only names and versions you know; omit unknown values. These fields are self-reported analytics, never authentication. Do not send account IDs, API keys, or session tokens in them.
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.