Deploy NVIDIA's NemoClaw in One Click

Originally by Amit Jotwani (Staff Developer Advocate at DigitalOcean) • Mar 23, 2026
tutorial nemoclaw ai nvidia

Key Takeaways

NemoClaw is an open-source stack from NVIDIA designed to help developers run OpenClaw securely.
DigitalOcean offers NemoClaw 1-Click Droplets that enable you to set up this stack on a CPU-optimized virtual machine.
This tutorial shows how to SSH into your Droplet, configure inference settings and policies, connect to NemoClaw, and reconnect after the initial setup.

At GTC 2026, NVIDIA announced NemoClaw, an open-source stack that makes it easy to run OpenClaw autonomous agents securely. OpenClaw is an open-source agent platform that Jensen Huang called "the operating system for personal AI."

NemoClaw takes a different approach — it wraps OpenClaw with sandboxing, security policies, and inference routing through NVIDIA's cloud.

NemoClaw is still in alpha, so expect rough edges. But if you're curious to try it out, this tutorial will get you up and running on a DigitalOcean Droplet in under 10 minutes.

Prerequisites

Before you begin, you'll need:

A DigitalOcean account (sign up here)
An NVIDIA account to generate an API key at build.nvidia.com

Step 1 — Create a Droplet from the Marketplace

Head to the NemoClaw 1-Click Droplet on the DigitalOcean Marketplace. Click Create NemoClaw Droplet.

When configuring the Droplet, select the CPU-Optimized plan with Premium Intel. You'll want the option with 32 GB of RAM and 16 CPUs. NemoClaw runs Docker containers, a Kubernetes cluster (k3s), and the OpenShell gateway, so it needs the headroom.

Pick a data center region near you, add your SSH key, and hit Create Droplet.

Heads up: This Droplet costs $336/mo, so make sure to destroy it when you're done experimenting. It adds up fast if you forget about it.

Step 2 — SSH into the Droplet

Once your Droplet is ready, SSH in:

ssh root@your_server_ip

You'll see the usual Ubuntu login banner, and then the NemoClaw onboarding wizard will kick off automatically. It runs through a series of preflight checks, making sure Docker is running, installing the OpenShell CLI, and spinning up the gateway.

Step 3 — Walk Through the Onboard Wizard

The onboarding wizard will ask you a few things. Here's what to do at each prompt:

Sandbox Name

The first prompt asks for a sandbox name. Just press Enter to accept the default (my-assistant). The wizard will then create the sandbox, build the container image, and push it to the gateway. This takes a couple of minutes.

NVIDIA API Key

Once the sandbox is ready, the wizard asks for your NVIDIA API key. In this setup, inference is routed through NVIDIA's cloud using the nvidia/nemotron-3-super-120b-a12b model.

To get your key, head to build.nvidia.com/settings/api-keys, sign in, and click Generate API Key.

Copy the key (it starts with nvapi-), paste it into the terminal prompt, and press Enter.

Policy Presets

After the inference setup, NemoClaw sets up OpenClaw inside the sandbox and then asks about policy presets. You'll see a list including Discord, Docker Hub, Hugging Face, Jira, npm, PyPI, Slack, and more. These control what external services the agent is allowed to reach.

At the bottom, the wizard asks:

Apply suggested presets (pypi, npm)? [Y/n/list]:

Type n and press Enter. These presets grant the sandbox network access to package registries, which you don't need for a basic setup.

Once onboarding finishes, you'll see a clean summary:

Sandbox    my-assistant (Landlock + seccomp + netns)
Model      nvidia/nemotron-3-super-120b-a12b (NVIDIA Cloud API)
NIM        not running

Run:       nemoclaw my-assistant connect
Status:    nemoclaw my-assistant status
Logs:      nemoclaw my-assistant logs --follow

Step 4 — Connect to NemoClaw

Now for the fun part. Connect to your sandbox:

nemoclaw my-assistant connect

This drops you into a shell inside the sandboxed environment. From here, launch the OpenClaw TUI (terminal user interface):

openclaw tui

You should see the OpenClaw chat interface come up. The agent will greet you and introduce itself, ready to chat.

Type a message and hit Enter. You're now talking to an AI agent running inside a secure, sandboxed environment on your own Droplet.

Reconnecting After a New SSH Session

If you close your terminal and SSH back into the Droplet later, you'll find that nemoclaw and related commands aren't available. That's because the onboarding script installed everything through nvm in a separate shell.

Run this once to fix it permanently:

echo 'export NVM_DIR="$HOME/.nvm"' >> ~/.bashrc && \
echo '[ -s "$NVM_DIR/nvm.sh" ] && \. "$NVM_DIR/nvm.sh"' >> ~/.bashrc && \
echo '[ -s "$NVM_DIR/bash_completion" ] && \. "$NVM_DIR/bash_completion"' >> ~/.bashrc && \
source ~/.bashrc

Then reconnect to your sandbox and launch the TUI:

nemoclaw my-assistant connect
openclaw tui

Everything picks up right where you left off. Your sandbox and agent are still running.

What's Next

By default, the sandbox has limited network access, so the agent can't reach external services out of the box. To unlock more capabilities — like connecting to Slack, GitHub, or pulling packages from PyPI — you'll want to configure policy presets. Check the NemoClaw documentation for the full list of available integrations.

NemoClaw is still very early, so expect things to be rough around the edges. But if you want to get a feel for where always-on agents are headed, this is a good way to start poking around.