nemoclaw-user-deploy-remote

Deploys NemoClaw to remote GPU hosts with sandboxing and credential rotation.

22.1k|3.0k|Updated Mar 15, 2026
One-click install
npx skills add https://github.com/NVIDIA/NemoClaw --skill nemoclaw-user-deploy-remote
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nemoclaw-user-deploy-remote
Source: https://github.com/NVIDIA/NemoClaw/tree/main/.agents/skills/nemoclaw-user-deploy-remote
Command: npx skills add https://github.com/NVIDIA/NemoClaw --skill nemoclaw-user-deploy-remote

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Running NemoClaw on remote GPU instances requires coordinating provisioning, installer versus legacy deploy flows, onboarding for OpenShell-managed messaging channels, and a set of image- and runtime-level hardening controls so agents remain sandboxed and credentials are handled safely. This Skill documents the end-to-end steps, warnings, and configuration knobs operators need to deploy a sandboxed OpenClaw agent remotely while preserving least-privilege and reproducible credential rotation.

Core Features & Use Cases

  • Provisioning guidance: Deprecated Brev compatibility path and the recommended pattern of provisioning a host, running the NemoClaw installer there, and completing the onboard flow.
  • Security hardening: Image and runtime controls including process limits, capability dropping, Landlock/read-only home policies, and notes about kernel requirements and fallback behavior.
  • Messaging and onboarding: How Telegram, Discord, and Slack tokens are registered with OpenShell providers, how channel config is baked at image-build time, and how to rotate credentials safely.
  • Use case: Deploy a GPU VM for a research assistant, configure CHAT_UI_URL and proxy settings for remote dashboard access, onboard the sandbox with a Telegram bot token, and verify inference and network policy from the host.

Quick Start

Provision a remote GPU host, install NemoClaw on that host, and run the onboarding wizard on the host to build and launch a hardened sandbox with your messaging channels configured.

Frequently Asked Questions about nemoclaw-user-deploy-remote

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I deploy NemoClaw to a remote GPU instance?

To deploy NemoClaw to a remote GPU, provision a host, run the NemoClaw installer directly on that host, and complete the onboarding wizard to build and launch a hardened sandbox.

What security hardening is applied when running OpenClaw agents remotely?

Remote OpenClaw agents are secured through image and runtime controls, including process ulimit enforcement, capability dropping, Landlock policies, and read-only workspace constraints to maintain least-privilege.

Can I configure Telegram and Slack messaging channels during remote sandbox onboarding?

Yes, you can configure Telegram, Discord, and Slack channels during onboarding by registering tokens with OpenShell providers, baking channel config at image-build time, and verifying network proxy settings.

Does the NemoClaw remote deployment flow still support Brev compatibility?

Brev compatibility is a deprecated deployment path; the recommended approach is provisioning a host, running the NemoClaw installer there, and completing the remote onboard flow for the sandbox.

How do I rotate credentials securely for a remote OpenClaw agent?

Credential rotation for remote agents is handled safely by baking channel configurations at image-build time and applying reproducible credential rotation steps documented in the onboarding flow.

Why is my remote dashboard access failing after sandbox configuration?

Remote dashboard access requires verifying your dashboard origin and correctly configuring CHAT_UI_URL and proxy settings on the GPU host during the NemoClaw installation and onboarding process.