> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/NVIDIA/NemoClaw/llms.txt
> Use this file to discover all available pages before exploring further.

# Monitor sandbox activity

> Inspect sandbox health, trace agent behavior, and diagnose problems using status, logs, and the OpenShell TUI.

# Monitor sandbox activity

NemoClaw provides several tools for inspecting sandbox health, tracing agent behavior, and diagnosing problems: the `openclaw nemoclaw status` command, the `openclaw nemoclaw logs` command, and the OpenShell terminal UI (`openshell term`).

## Prerequisites

* A running NemoClaw sandbox.
* The OpenShell CLI on your `PATH`.

## Check sandbox health

Run the status command to view the sandbox state, blueprint run information, and active inference configuration:

```bash theme={null}
openclaw nemoclaw status
```

For machine-readable output, add the `--json` flag:

```bash theme={null}
openclaw nemoclaw status --json
```

Key fields in the output:

| Field              | Description                                                       |
| ------------------ | ----------------------------------------------------------------- |
| Sandbox state      | Whether the sandbox is `running`, `stopped`, or in an error state |
| Blueprint run ID   | Identifier for the most recent blueprint execution                |
| Inference provider | Active provider name, model ID, and endpoint URL                  |

<Note>
  If you run `openclaw nemoclaw status` from **inside** the sandbox, the command detects the sandbox context and reports it. Host-level sandbox and inference details are not available from within the sandbox. Run `openshell sandbox status` on the host for full host-side details.
</Note>

## View logs

Stream the most recent log output from the blueprint runner and sandbox:

```bash theme={null}
openclaw nemoclaw logs
```

<Tabs>
  <Tab title="Follow in real time">
    Tail the log output as new lines arrive:

    ```bash theme={null}
    openclaw nemoclaw logs -f
    ```
  </Tab>

  <Tab title="Limit output lines">
    Display a specific number of recent log lines:

    ```bash theme={null}
    openclaw nemoclaw logs -n 100
    ```
  </Tab>

  <Tab title="By run ID">
    View logs for a specific blueprint run instead of the most recent one:

    ```bash theme={null}
    openclaw nemoclaw logs --run-id <id>
    ```

    Retrieve the run ID from `openclaw nemoclaw status`.
  </Tab>
</Tabs>

## Monitor network activity in the TUI

Open the OpenShell terminal UI for a live view of network activity and egress approval prompts:

```bash theme={null}
openshell term
```

The TUI shows:

* Active network connections from inside the sandbox
* Blocked egress requests awaiting operator approval
* Inference routing status

For a remote sandbox, SSH to the instance and run `openshell term` there:

```bash theme={null}
ssh my-gpu-box 'cd /home/ubuntu/nemoclaw && set -a && . .env && set +a && openshell term'
```

See [Approve network requests](/network-policy/approve-network-requests) for details on acting on blocked requests.

## Test inference

Run a test inference request to verify that the provider is responding:

```bash theme={null}
nemoclaw my-assistant connect
openclaw agent --agent main --local -m "Test inference" --session-id debug
```

If the request fails:

1. Run `openclaw nemoclaw status` to confirm the active provider and endpoint.
2. Run `openclaw nemoclaw logs -f` to view error messages from the blueprint runner.
3. Verify that the inference endpoint is reachable from the host.

## Diagnose common issues

<AccordionGroup>
  <Accordion title="Sandbox shows as stopped">
    Re-run onboard to recreate the sandbox:

    ```bash theme={null}
    nemoclaw onboard
    ```
  </Accordion>

  <Accordion title="Inference requests time out">
    Verify the provider endpoint is reachable from the host. Check the active endpoint:

    ```bash theme={null}
    openclaw nemoclaw status
    ```

    If the endpoint is unreachable, re-run onboard to select a different provider or confirm your `NVIDIA_API_KEY` is valid.
  </Accordion>

  <Accordion title="Agent cannot reach an external host">
    Open the TUI and approve the blocked egress request:

    ```bash theme={null}
    openshell term
    ```

    To allow the endpoint permanently, add it to `nemoclaw-blueprint/policies/openclaw-sandbox.yaml` and re-run `nemoclaw onboard`. See [Customize the network policy](/network-policy/customize-network-policy).
  </Accordion>

  <Accordion title="Blueprint run failed">
    Retrieve the run ID from `openclaw nemoclaw status`, then view the error output for that run:

    ```bash theme={null}
    openclaw nemoclaw logs --run-id <id>
    ```
  </Accordion>

  <Accordion title="cgroup v2 error during onboard">
    On Ubuntu 24.04, DGX Spark, or WSL2, Docker requires `"default-cgroupns-mode": "host"` in `/etc/docker/daemon.json`. Apply the fix and retry:

    ```bash theme={null}
    nemoclaw setup-spark
    nemoclaw onboard
    ```
  </Accordion>

  <Accordion title="Status shows 'not running' inside the sandbox">
    This is expected behavior. The status command cannot query host-level state from within the sandbox. Run `openshell sandbox status` on the host instead.
  </Accordion>
</AccordionGroup>

## Related topics

<CardGroup cols={2}>
  <Card title="Approve network requests" icon="shield-check" href="/network-policy/approve-network-requests">
    Use the OpenShell TUI to allow or block agent egress requests.
  </Card>

  <Card title="Switch inference providers" icon="microchip" href="/inference/switch-inference-providers">
    Change the active model or provider without restarting the sandbox.
  </Card>

  <Card title="Customize the network policy" icon="shield" href="/network-policy/customize-network-policy">
    Permanently allow endpoints that the agent needs to reach.
  </Card>
</CardGroup>