Summary
If you're running NemoClaw sandboxes and need to keep tabs on what's happening inside, this gives you status checks, log inspection, and a TUI for debugging agent behavior. It assumes you already have the OpenShell CLI installed and a sandbox up. The combination of health checks and trace tools makes it straightforward to diagnose when something goes sideways in your inference setup. With over 800 installs and passing all three security audits, it's become the standard monitoring approach in the NemoClaw ecosystem. Not flashy, but it does exactly what you need when an agent misbehaves or a gateway goes quiet.
Install to Claude Code
npx -y skills add nvidia/skills --skill nemoclaw-user-monitor-sandbox --agent claude-codeInstalls into .claude/skills of the current project.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Files
SKILL.md
Select a file.
Featured
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
