Memantoclaw Monitor Sandbox

Memantoclaw Monitor Sandbox

Inspect sandbox health, trace agent behavior, and diagnose problems.

Prerequisites

• A running MemantoClaw sandbox.
• The OpenShell CLI on your PATH.

Use the MemantoClaw status, logs, and TUI tools together to inspect sandbox health, trace agent behavior, and diagnose problems.

Step 1: Check Sandbox Health

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

$ memantoclaw <name> status

Key fields in the output include the following:

• Sandbox state, which indicates whether the sandbox is running, stopped, or in an error state.
• Blueprint run ID, which is the identifier for the most recent blueprint execution.
• Inference provider, which shows the active provider, model, and endpoint.

Run memantoclaw <name> status on the host to check sandbox state. Use openshell sandbox list for the underlying sandbox details.

Step 2: View Blueprint and Sandbox Logs

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

$ memantoclaw <name> logs

To follow the log output in real time:

$ memantoclaw <name> logs -f

Step 3: Monitor Network Activity in the TUI

Open the OpenShell terminal UI for a live view of sandbox network activity and egress requests:

$ openshell term

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

The TUI shows the following information:

• Active network connections from the sandbox.
• Blocked egress requests awaiting operator approval.
• Inference routing status.

Refer to Approve or Deny Agent Network Requests (see the memantoclaw-manage-policy skill) for details on handling blocked requests.

Step 4: Test Inference

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

$ memantoclaw my-assistant connect
$ openclaw agent --agent main --local -m "Test inference" --session-id debug

If the request fails, check the following:

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

Related Skills

• memantoclaw-reference — Troubleshooting for common issues and resolution steps
• memantoclaw-manage-policy — Approve or Deny Agent Network Requests for the operator approval flow
• memantoclaw-configure-inference — Switch Inference Providers to change the active provider