NemoClawUse the NemoClaw status, logs, and TUI tools together to inspect sandbox health, trace agent behavior, and diagnose problems.
PATH.Run the status command to view the sandbox state, gateway health, and active inference configuration:
For local Ollama and local vLLM routes, nemoclaw <name> status also probes the host-side health endpoint directly.
This catches a stopped local backend before you retry inference.local from inside the sandbox.
Key fields in the output include the following:
healthy or unreachable together with the probed local URL.Run nemoclaw <name> status on the host to check sandbox state.
Use openshell sandbox list for the underlying sandbox details.
Stream the most recent log output from the blueprint runner and sandbox:
To follow the log output in real time:
Open the OpenShell terminal UI for a live view of sandbox network activity and egress requests:
For a remote sandbox, SSH to the instance and run openshell term there.
The TUI shows the following information:
Refer to Approve or Deny Agent Network Requests for details on handling blocked requests.
Run a test inference request to verify that the provider is responding:
If the request fails, check the following:
nemoclaw <name> status to confirm the active provider and endpoint.
For local Ollama and local vLLM, check the Inference line first.
If it shows unreachable, restart the local backend before retrying from inside the sandbox.nemoclaw <name> logs --follow to view error messages from the blueprint runner.