Nemoclaw Setup

Automates the full deployment of NVIDIA NemoClaw, a sandboxed AI agent platform running OpenClaw with Landlock, seccomp, and network namespace isolation inside Docker via k3s. Handles the entire stack: Node.js and Docker prerequisites, cgroup v2 fixes for k3s, OpenShell gateway setup, sandbox creation with Nemotron model configuration, and web UI port forwarding with systemd keepalive. Includes workarounds for the known "device identity required" bug in OpenClaw versions before v2026.3.12 and steps for exposing the UI via Cloudflare Tunnel with proper origin headers and Access protection. Use this when setting up a production sandboxed agent environment on NVIDIA hardware or when you need the web interface accessible remotely with all the annoying Docker permission and networking bits already solved.

skills.sh installs: 902
GitHub stars: 1.1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add jezweb/claude-skills --skill nemoclaw-setup --agent claude-code

Installs into .claude/skills of the current project.

Files

NemoClaw Setup

Install NVIDIA NemoClaw — a sandboxed AI agent platform built on OpenClaw with Landlock + seccomp + network namespace isolation. Runs inside Docker via k3s (OpenShell).

What You Get

Sandboxed AI agent with web UI and terminal CLI
Powered by NVIDIA Nemotron models (cloud or local)
Network-policy-controlled access to external services
Optional remote access via Cloudflare Tunnel

Prerequisites

Requirement	Check	Install
Linux (Ubuntu 22.04+)	`uname -a`	—
Docker	`docker ps`	`sudo apt install docker.io`
Node.js 20+ (22 recommended)	`node --version`	`nvm install 22`
NVIDIA GPU (optional but recommended)	`nvidia-smi`	—
NVIDIA API key	—	https://build.nvidia.com/settings/api-keys

Workflow

Step 1: Pre-flight Checks

# Check Docker
docker ps 2>/dev/null || echo "Docker not running or no access"

# Check Node.js
node --version

# Check if already installed
which nemoclaw && nemoclaw --version
which openshell && openshell --version

If nemoclaw is already installed, skip to Step 4.