Nemoclaw User Get Started

OpenAIOfficialCreated by NVIDIADistributed by OpenAI

Skill
Workflow
Automation and integrations
Apache-2.0
Medium risk

From the author

Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.

— the description by NVIDIA

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The NemoClaw Quickstart skill provides a streamlined installation process for NemoClaw, including the necessary environment setup, sandbox creation, and agent configuration. It automates the installation of dependencies like Node.js and Docker, manages the onboarding wizard for inference provider selection, and configures network policies and messaging integrations. This skill is designed to get users from a clean host to a running, sandboxed OpenClaw agent environment efficiently.

What it does

Downloads and executes the NemoClaw installer script.
Automatically detects and installs required dependencies like Node.js and Docker.
Launches an interactive onboarding wizard to configure inference providers and sandbox settings.
Sets up network policy presets to control sandbox access to external services.
Configures optional messaging channels like Slack, Discord, or Telegram.
Provides commands to launch the OpenClaw UI or connect via terminal.

When to use it

When you are setting up NemoClaw on a new machine for the first time.
When you need to create a new sandboxed OpenClaw agent environment.
When you need to perform an express installation on supported platforms like WSL or DGX.
When you need to reconfigure or recreate the OpenShell gateway and sandbox environment.

Advantages

Automates complex environment setup and dependency management.
Provides a guided, interactive experience for configuring inference and security.
Supports non-interactive modes for CI/CD and automated deployment scenarios.
Ensures consistent sandbox configuration through validated policy presets.

Usage examples

“nemoclaw quickstart”: The agent initiates the NemoClaw installation script and launches the onboarding wizard to guide you through sandbox creation.
“install nemoclaw openclaw sandbox”: The agent triggers the installation process, checks for prerequisites, and prepares the environment for a new OpenClaw instance.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/openai/nemoclaw-user-get-started/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip nemoclaw-user-get-started.zip -d .agents/skills

Documentation by NVIDIA

NemoClaw Quickstart with OpenClaw

Follow these steps to get started with NemoClaw and your first sandboxed OpenClaw agent.

Note:

Make sure you have completed reviewing the Prerequisites before following this guide.

Install NemoClaw and Onboard OpenClaw Agent

Download and run the installer script. The script installs Node.js if it is not already present, then runs the guided onboard wizard to create a sandbox, configure inference, and apply security policies.

Note:

NemoClaw creates a fresh OpenClaw instance inside the sandbox during the onboarding process.

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

The piped installer prompts through your terminal. In headless scripts or CI, pass explicit acceptance to the bash side of the pipe:

$ curl -fsSL https://www.nvidia.com/nemoclaw.sh | NEMOCLAW_NON_INTERACTIVE=1 NEMOCLAW_ACCEPT_THIRD_PARTY_SOFTWARE=1 bash

If you use nvm or fnm to manage Node.js, the installer might not update your current shell's PATH. If nemoclaw is not found after install, run source ~/.bashrc (or source ~/.zshrc for zsh) or open a new terminal.

On Linux, the installer checks Docker before it installs NemoClaw. If Docker is missing, the installer downloads the official Docker convenience script, asks for sudo, installs Docker, and starts the Docker service when systemd is available. If Docker is installed but your current shell cannot use the Docker socket yet, the installer adds your user to the docker group when needed and exits with a recovery command.

On macOS, the installer uses the Docker-driver OpenShell gateway path with Docker Desktop or Colima.

$ newgrp docker
$ curl -fsSL https://www.nvidia.com/nemoclaw.sh | bash

On DGX Spark, DGX Station, and Windows WSL, an interactive installer offers express install after you accept the third-party software notice. Express install switches onboarding to non-interactive mode, allows sudo password prompts for required host changes, and selects the managed local inference path for that platform. Unless NEMOCLAW_POLICY_TIER is set, it applies sandbox policy in suggested mode with the balanced tier by default, using the base sandbox policy plus supported package, model, web-search, and local-inference presets. On WSL, express install selects the Windows-host Ollama setup path. Set NEMOCLAW_NO_EXPRESS=1 to skip the express prompt, or set NEMOCLAW_PROVIDER before launching the installer when you want to choose a provider yourself.

The installer auto-launches nemoclaw onboard when it can locate the freshly-installed binary. If it cannot locate the binary, or if blocking host preflight checks fail, it does not launch the wizard automatically. In that case, the installer prints the relevant diagnostics and a To finish setup, run: block with the explicit nemoclaw onboard command.

Note:

The onboard flow builds the sandbox image with NEMOCLAW_DISABLE_DEVICE_AUTH=1 so the dashboard is immediately usable during setup. This is a build-time setting baked into the sandbox image, not a runtime knob. If you export NEMOCLAW_DISABLE_DEVICE_AUTH after onboarding finishes, it has no effect on an existing sandbox.

Review the Configuration Before the Sandbox Build

After you enter the sandbox name, the wizard prints a review summary and asks for final confirmation before registering the provider, prompting for optional integrations, and building the sandbox image. For example, if you picked an OpenAI-compatible endpoint, the summary looks like the following:

  ──────────────────────────────────────────────────
  Review configuration
  ──────────────────────────────────────────────────
  Provider:      compatible-endpoint
  Model:         openai/openai/gpt-5.5
  API key:       COMPATIBLE_API_KEY (staged for OpenShell gateway registration)
  Web search:    disabled
  Messaging:     none
  Sandbox name:  my-gpt-claw
  Note:          Sandbox build typically takes 5–15 minutes on this host.
  ──────────────────────────────────────────────────
  Web search and messaging channels will be prompted next.
  Apply this configuration? [Y/n]:

The default is Y, so you can press Enter once to continue. Answer n to abort cleanly, fix the entries, and re-run nemoclaw onboard.

Non-interactive runs (NEMOCLAW_NON_INTERACTIVE=1) print the summary for log clarity but skip the prompt.

Configure Web Search and Messaging

After you confirm the summary, NemoClaw registers the selected provider with the OpenShell gateway and sets the inference.local route. The wizard then asks whether to enable Brave Web Search. If you enable it, enter a Brave Search API key when prompted.

The wizard also offers messaging channels such as Telegram, Discord, Slack, WeChat, and WhatsApp. Press a channel number to toggle it, then press Enter to continue. If you select a channel, NemoClaw validates the token format before it bakes the channel configuration into the sandbox. For example, Slack bot tokens must start with xoxb-. WeChat and WhatsApp are experimental. Review Messaging Channels (use the nemoclaw-user-manage-sandboxes skill) before enabling them.

Choose Network Policy Presets

After the sandbox image builds and OpenClaw starts inside the sandbox, NemoClaw asks which network policy tier to apply. The default Balanced tier includes common development presets such as npm, PyPI, Hugging Face, Homebrew, and Brave Search when the selected agent supports web search. Use the arrow keys or j and k to move, Space to select, and Enter to confirm.

The preset selector lets you include more destinations, such as GitHub, Jira, Slack, Telegram, or local inference. Press r to toggle a selected preset between read-only and read-write when the preset supports both modes.

When the install completes, a summary confirms the running environment. Before printing the summary, NemoClaw verifies that the sandbox gateway and dashboard port forward are reachable. Inference route and messaging bridge checks are reported as warnings when they need more time or additional configuration. The Model and provider line reflects the inference option you picked during onboarding. The example below shows the result if you picked an OpenAI-compatible endpoint during onboarding.

──────────────────────────────────────────────────
NemoClaw is ready

Sandbox:  my-gpt-claw
Model:    openai/openai/gpt-5.5 (Other OpenAI-compatible endpoint)

Start chatting

  Browser:
    http://127.0.0.1:18789/

  Terminal:
    nemoclaw my-gpt-claw connect
    then run: openclaw tui

Authenticated dashboard URL, if needed:
  nemoclaw my-gpt-claw dashboard-url --quiet

Manage later

  Status:      nemoclaw my-gpt-claw status
  Logs:        nemoclaw my-gpt-claw logs --follow
  Model:       nemoclaw inference set --model <model> --provider <provider> --sandbox my-gpt-claw
  Policies:    nemoclaw my-gpt-claw policy-add
  Credentials: nemoclaw credentials reset <KEY> && nemoclaw onboard
──────────────────────────────────────────────────

[INFO]  === Installation complete ===

If you picked a different option, the Model line shows that provider's model and label instead. For example, you might see gpt-5.4 (OpenAI), claude-sonnet-4-6 (Anthropic), gemini-2.5-flash (Google Gemini), llama3.1:8b (Local Ollama), nvidia-routed (Model Router), or <your-model> (Other OpenAI-compatible endpoint).

Load references/quickstart-details.md for detailed steps on Respond to the Onboard Wizard.

Run Your First Agent Prompt

You can chat with the agent from the terminal or the browser.

Open the OpenClaw UI in a Browser to Chat with the Agent

The onboard wizard starts a background port forward to the sandbox dashboard, then prints the dashboard URL in the install summary. The default host port is 18789. If that port is already taken, NemoClaw uses the next free dashboard port, such as 18790, and prints that port in the final URL. If the chosen port becomes occupied after the sandbox build starts, onboarding rolls back the newly-created sandbox and asks you to retry instead of printing an unreachable dashboard URL. The install transcript does not print the gateway token. If the browser requires authentication, use the dashboard-url --quiet command to print a complete URL explicitly.

nemoclaw my-gpt-claw dashboard-url --quiet

Open the dashboard URL in your browser. If the browser asks for authentication, run nemoclaw my-gpt-claw dashboard-url --quiet and open the returned URL. Treat the authenticated URL like a password.

Chat with the Agent from the Terminal

Connect to the sandbox and use the OpenClaw CLI.

nemoclaw my-assistant connect
# inside the sandbox:
openclaw tui

References

Load references/quickstart-hermes.md when users ask for Hermes setup, NemoHermes onboarding, or running Hermes inside OpenShell. Installs NemoClaw, selects the Hermes agent, and launches a sandboxed Hermes API endpoint.
Load references/prerequisites.md when verifying prerequisites before installation. Lists the hardware, software, and container runtime requirements for running NemoClaw.
Load references/windows-preparation.md when preparing a Windows machine for NemoClaw, enabling WSL 2, configuring Docker Desktop for Windows, or troubleshooting a Windows-specific install error. Covers Windows-only preparation steps required before the Quickstart.
Load references/quickstart-details.md when you need detailed steps for Respond to the Onboard Wizard.

nemoclaw-user-overview — NemoClaw Overview (use the nemoclaw-user-overview skill) to learn what NemoClaw is and its capabilities

Files

ATTRIBUTION.mdAdded by AutoGineer947 B
BENCHMARK.md2.8 KiB
LICENSEAdded by AutoGineer10.0 KiB
SKILL.md10.7 KiB
agents/openai.yaml538 B
evals/evals.json6.7 KiB
references/prerequisites.md4.4 KiB
references/quickstart-details.md9.8 KiB
references/quickstart-hermes.md6.6 KiB
references/windows-preparation.md6.2 KiB
skill-card.md2.4 KiB
skill.oms.sig5.5 KiB

evals/evals.json

[
  {
    "id": "docs-get-started-prerequisites-001",
    "question": "I'm checking prerequisites before installation. Help me verify my host has the required hardware, software, and platform support so I can avoid a failed first setup.",
    "expected_skill": "nemoclaw-user-get-started",
    "ground_truth": "A NemoClaw-specific answer that helps the user verify my host has the required hardware, software, and platform support and gives enough concrete guidance, decision criteria, verification steps, or risk framing to avoid a failed first setup."
  },
  {
    "id": "docs-get-started-prerequisites-002",
    "question": "I'm using a machine with limited CPU, memory, disk, or Docker capacity. Help me understand the practical minimums and known bottlenecks so I can prepare the machine before onboarding starts.",
    "expected_skill": "nemoclaw-user-get-started",
    "ground_truth": "A NemoClaw-specific answer that helps the user understand the practical minimums and known bottlenecks and gives enough concrete guidance, decision criteria, verification steps, or risk framing to prepare the machine before onboarding starts."
  },
  {
    "id": "docs-get-started-prerequisites-003",
    "question": "I'm choosing between local, Windows WSL, and remote GPU setup. Help me compare supported platform paths so I can start with the environment most likely to work.",
    "expected_skill": "nemoclaw-user-get-started",
    "ground_truth": "A NemoClaw-specific answer that helps the user compare supported platform paths and gives enough concrete guidance, decision criteria, verification steps, or risk framing to start with the environment most likely to work."
  },
  {
    "id": "docs-get-started-windows-preparation-001",
    "question": "I'm preparing a Windows machine for NemoClaw. Help me enable WSL 2, Ubuntu, and Docker Desktop correctly so I can enter the standard quickstart from a working Linux environment.",
    "expected_skill": "nemoclaw-user-get-started",
    "ground_truth": "A NemoClaw-specific answer that helps the user enable WSL 2, Ubuntu, and Docker Desktop correctly and gives enough concrete guidance, decision criteria, verification steps, or risk framing to enter the standard quickstart from a working Linux environment."
  },
  {
    "id": "docs-get-started-windows-preparation-002",
    "question": "I'm unsure whether Windows-specific setup is complete. Help me check the WSL and Docker integration steps that commonly block installs so I can fix host issues before running the NemoClaw installer.",
    "expected_skill": "nemoclaw-user-get-started",
    "ground_truth": "A NemoClaw-specific answer that helps the user check the WSL and Docker integration steps that commonly block installs and gives enough concrete guidance, decision criteria, verification steps, or risk framing to fix host issues before running the NemoClaw installer."
  },
  {
    "id": "docs-get-started-windows-preparation-003",
    "question": "I'm ready to leave the Windows preparation guide. Help me confirm the Ubuntu shell can run the required commands so I can follow the quickstart without mixing Windows and Linux instructions.",
    "expected_skill": "nemoclaw-user-get-started",
    "ground_truth": "A NemoClaw-specific answer that helps the user confirm the Ubuntu shell can run the required commands and gives enough concrete guidance, decision criteria, verification steps, or risk framing to follow the quickstart without mixing Windows and Linux instructions."
  },
  {
    "id": "docs-get-started-quickstart-001",
    "question": "I'm running the OpenClaw quickstart. Help me install NemoClaw and create my first sandboxed agent so I can send a prompt to a working OpenClaw assistant.",
    "expected_skill": "nemoclaw-user-get-started",
    "ground_truth": "A NemoClaw-specific answer that helps the user install NemoClaw and create my first sandboxed agent and gives enough concrete guidance, decision criteria, verification steps, or risk framing to send a prompt to a working OpenClaw assistant."
  },
  {
    "id": "docs-get-started-quickstart-002",
    "question": "I'm encountering installer prompts or host preflight checks. Help me understand what the installer is asking for and why so I can continue setup without granting unnecessary access.",
    "expected_skill": "nemoclaw-user-get-started",
    "ground_truth": "A NemoClaw-specific answer that helps the user understand what the installer is asking for and why and gives enough concrete guidance, decision criteria, verification steps, or risk framing to continue setup without granting unnecessary access."
  },
  {
    "id": "docs-get-started-quickstart-003",
    "question": "I'm finishing onboarding. Help me verify the sandbox, inference route, and OpenClaw agent are connected so I can know the setup succeeded end to end.",
    "expected_skill": "nemoclaw-user-get-started",
    "ground_truth": "A NemoClaw-specific answer that helps the user verify the sandbox, inference route, and OpenClaw agent are connected and gives enough concrete guidance, decision criteria, verification steps, or risk framing to know the setup succeeded end to end."
  },
  {
    "id": "docs-get-started-quickstart-hermes-001",
    "question": "I'm choosing Hermes instead of OpenClaw. Help me launch a sandboxed Hermes API endpoint so I can serve the agent workflow my downstream clients expect.",
    "expected_skill": "nemoclaw-user-get-started",
    "ground_truth": "A NemoClaw-specific answer that helps the user launch a sandboxed Hermes API endpoint and gives enough concrete guidance, decision criteria, verification steps, or risk framing to serve the agent workflow my downstream clients expect."
  },
  {
    "id": "docs-get-started-quickstart-hermes-002",
    "question": "I'm moving through onboarding for Hermes. Help me confirm NemoClaw selected Hermes-specific setup and configuration so I can avoid accidentally creating the default OpenClaw environment.",
    "expected_skill": "nemoclaw-user-get-started",
    "ground_truth": "A NemoClaw-specific answer that helps the user confirm NemoClaw selected Hermes-specific setup and configuration and gives enough concrete guidance, decision criteria, verification steps, or risk framing to avoid accidentally creating the default OpenClaw environment."
  },
  {
    "id": "docs-get-started-quickstart-hermes-003",
    "question": "I'm checking the sandboxed Hermes endpoint. Help me run a small request that proves the endpoint is live so I can hand it to clients or tests with confidence.",
    "expected_skill": "nemoclaw-user-get-started",
    "ground_truth": "A NemoClaw-specific answer that helps the user run a small request that proves the endpoint is live and gives enough concrete guidance, decision criteria, verification steps, or risk framing to hand it to clients or tests with confidence."
  }
]

Requirements and compatibility

Written for: OpenAI Codex

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs network access, Needs an API key

Security

What our scanner noticed· Medium risk

Large base64-encoded blobs
Instructions that use the network
Downloads piped into a shell

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by

NVIDIA

Publisher

OpenAI (Official)

Distributed by

OpenAI

Source

openai/plugins · plugins/nvidia/skills/nemoclaw-user-get-started · commit d420d13

Licence

Apache License 2.0 (redistribution allowed)

LICENSE (written by AutoGineer)
ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-09

AutoGineer is not affiliated with or endorsed by NVIDIA or OpenAI.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download nemoclaw-user-get-started.zip

From the author

AutoGineer summary

What it does

When to use it

Advantages

Usage examples

Install

Documentation by NVIDIA

NemoClaw Quickstart with OpenClaw

Install NemoClaw and Onboard OpenClaw Agent

Review the Configuration Before the Sandbox Build

Configure Web Search and Messaging

Choose Network Policy Presets

Run Your First Agent Prompt

Open the OpenClaw UI in a Browser to Chat with the Agent

Chat with the Agent from the Terminal

References

Related Skills

Files

evals/evals.json

Requirements and compatibility

Security

Attribution and licence

Related skills

Wizard

Emails

Conversion Tracking

Directory Submissions

Sms

Marketing Loops

Download ZIP