Skills nemoclaw

install

source · Clone the upstream repo

git clone https://github.com/TerminalSkills/skills

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/TerminalSkills/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/nemoclaw" ~/.claude/skills/terminalskills-skills-nemoclaw && rm -rf "$T"

OpenClaw · Install into ~/.openclaw/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/TerminalSkills/skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/nemoclaw" ~/.openclaw/skills/terminalskills-skills-nemoclaw && rm -rf "$T"

manifest: skills/nemoclaw/SKILL.md

safety · automated scan (medium risk)

This is a pattern-based risk scan, not a security review. Our crawler flagged:

curl piped into shell
makes HTTP requests (curl)

Always read a skill's source content before installing. Patterns alone don't mean the skill is malicious — but they warrant attention.

source content

NemoClaw

Overview

NemoClaw is an open-source stack by NVIDIA that installs and runs OpenClaw inside a sandboxed environment (OpenShell) with policy-enforced security controls. OpenShell provides Landlock, seccomp, and network namespace isolation. Sandboxes enforce strict egress control — all inference requests route through the OpenShell gateway, not directly to the internet. Network and inference policies are hot-reloadable; filesystem and process policies are locked at creation.

Instructions

1. Install NemoClaw

Prerequisites: Linux Ubuntu 22.04+, Node.js 20+, Docker running, NVIDIA OpenShell installed, NVIDIA API key from build.nvidia.com.

curl -fsSL https://nvidia.com/nemoclaw.sh | bash

The installer runs the guided onboard wizard, creates a sandbox, configures inference (NVIDIA cloud), and applies security policies. After install you see:

──────────────────────────────────────────────────
Sandbox my-assistant (Landlock + seccomp + netns)
Model nvidia/nemotron-3-super-120b-a12b (NVIDIA Cloud API)
──────────────────────────────────────────────────

2. Manage sandboxes from the host

nemoclaw onboard                      # Interactive setup wizard
nemoclaw my-assistant connect         # Shell into sandbox
nemoclaw my-assistant status          # Sandbox health check
nemoclaw my-assistant logs --follow   # Stream logs
nemoclaw start                        # Start auxiliary services
nemoclaw stop                         # Stop services
nemoclaw deploy my-assistant          # Deploy via Brev to remote GPU instance

3. Work inside the sandbox

openclaw tui                          # Interactive chat TUI
openclaw agent --agent main --local -m "hello" --session-id test
openclaw nemoclaw launch              # Bootstrap OpenClaw in sandbox
openclaw nemoclaw status              # Show sandbox health
openclaw nemoclaw logs [-f]           # Stream logs

4. Security policies

Network: All outbound blocked by default, allowlist-based egress, hot-reloadable. When agent requests unlisted host → blocked + surfaced in TUI for operator approval.
Filesystem: Only
```
/sandbox
```
and
```
/tmp
```
writable, locked at creation.
Process: Privilege escalation blocked, seccomp syscall filtering, locked at creation.
Inference: All model API calls intercepted by OpenShell gateway, routed to NVIDIA cloud. Default model:
```
nvidia/nemotron-3-super-120b-a12b
```
.

5. Troubleshoot

nemoclaw my-assistant status                        # NemoClaw health
openshell sandbox list                              # OpenShell sandbox state
nemoclaw my-assistant logs --follow | grep inference # Check inference connectivity

Common issues: Docker not running → start daemon. API key invalid → re-run

nemoclaw onboard

. Sandbox conflicts → check

openshell sandbox list

. Network blocked → check egress allowlist.

Examples

Example 1: Set up a new sandboxed coding agent

User request: "I want to run an OpenClaw agent in a secure sandbox with NemoClaw on my Ubuntu server"

Actions taken:

Verify prerequisites: confirm Ubuntu 22.04+, Node.js 20+, Docker running
Install OpenShell from https://github.com/NVIDIA/OpenShell

Run the NemoClaw installer:

curl -fsSL https://nvidia.com/nemoclaw.sh | bash

Follow onboard wizard — enter sandbox name
```
code-agent
```
, select Nemotron model, provide NVIDIA API key

Connect to sandbox:

nemoclaw code-agent connect

Inside sandbox, start the agent TUI:
```
openclaw tui
```

Expected output: Agent running inside isolated sandbox with Landlock filesystem protection, seccomp syscall filtering, network namespace isolation, and all inference routed through OpenShell gateway.

Example 2: Deploy a sandboxed agent to a remote GPU instance

User request: "Deploy my NemoClaw sandbox to a remote GPU so I can run larger models"

Actions taken:

Confirm local sandbox

research-agent

is working:

nemoclaw research-agent status

Output:

research-agent: running (Landlock + seccomp + netns)

Deploy to remote GPU via Brev:

nemoclaw deploy research-agent

Monitor remote deployment:

nemoclaw research-agent logs --follow

Expected output: Remote GPU instance provisioned, NemoClaw installed, sandbox

research-agent

running on remote with same security policies applied. All inference routed through NVIDIA cloud API.

Guidelines

NemoClaw requires a fresh OpenClaw installation — do not install on existing OpenClaw setups.
Alpha software — APIs may change without notice; not production-ready yet.
Linux only — Ubuntu 22.04+ required, no macOS or Windows support.
The
```
curl | bash
```
installer is from nvidia.com (official NVIDIA source). For manual installation, clone the repo and follow the README at https://github.com/NVIDIA/NemoClaw.
When the agent tries to reach a host not in the egress allowlist, the request is blocked and surfaced in the OpenShell TUI for operator approval. If approved, the host is added to the allowlist.
Blueprint lifecycle: Resolve artifact → Verify digest → Plan resources → Apply through OpenShell CLI.
Architecture: Host runs nemoclaw CLI (TypeScript) + Blueprint (Python) + OpenShell Runtime → Sandbox contains the OpenClaw agent with strict isolation.