> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/NVIDIA/NemoClaw/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Install NemoClaw, launch a sandbox, and run your first sandboxed OpenClaw agent.

Follow these steps to go from zero to a running sandboxed OpenClaw agent. The installer handles Node.js and NemoClaw setup, then walks you through the guided onboard wizard.

<Note>
  NemoClaw is **alpha software**. Interfaces, APIs, and behavior may change without notice as the project evolves. NemoClaw currently requires a fresh installation of OpenClaw.
</Note>

## Prerequisites

Verify that your environment meets the hardware and software requirements before you begin.

### Hardware

| Resource | Minimum    | Recommended |
| -------- | ---------- | ----------- |
| CPU      | 4 vCPU     | 4+ vCPU     |
| RAM      | 8 GB       | 16 GB       |
| Disk     | 20 GB free | 40 GB free  |

<Warning>
  The sandbox image is approximately 2.4 GB compressed. During image push, the Docker daemon, k3s, and the OpenShell gateway run alongside the export pipeline, which buffers decompressed layers in memory. On machines with less than 8 GB of RAM this combined usage can trigger the OOM killer. If you cannot add memory, configuring at least 8 GB of swap can work around the issue at the cost of slower performance.
</Warning>

### Software

| Dependency | Version requirement          |
| ---------- | ---------------------------- |
| Linux      | Ubuntu 22.04 LTS or later    |
| Node.js    | 20 or later (22 recommended) |
| npm        | 10 or later                  |
| Docker     | Installed and running        |
| OpenShell  | Installed                    |

Install [OpenShell](https://github.com/NVIDIA/OpenShell) before running the NemoClaw installer. The installer will install Node.js automatically if it is not present, but OpenShell must already be available.

## Install and onboard

<Steps>
  <Step title="Run the installer">
    Download and execute the NemoClaw installer script. The script installs Node.js via nvm if it is not already present, installs the `nemoclaw` CLI, and then launches the interactive onboard wizard.

    ```bash theme={null}
    curl -fsSL https://nvidia.com/nemoclaw.sh | bash
    ```

    The installer runs through the following stages:

    ```console theme={null}
    [INFO]  === NemoClaw Installer ===
    [INFO]  Node.js found: v22.x.x
    [INFO]  Runtime OK: Node.js v22.x.x, npm 10.x.x
    [INFO]  Installing NemoClaw from npm…
    [INFO]  Verified: nemoclaw is available at /usr/local/bin/nemoclaw
    [INFO]  Running nemoclaw onboard…
    ```

    <Note>
      If Node.js was installed via nvm, the installer will print instructions to reload your shell profile before `nemoclaw` is on your `PATH`. Follow those instructions or open a new terminal before continuing.
    </Note>
  </Step>

  <Step title="Complete the onboard wizard">
    After installation, the onboard wizard starts automatically. It configures the inference endpoint, API credential, and model for your sandbox.

    **Step 1 — Select your inference endpoint:**

    ```console theme={null}
    NemoClaw Onboarding
    -------------------
    ? Select your inference endpoint:
    > NVIDIA Build (build.nvidia.com)   recommended — zero infra, free credits
      NVIDIA Cloud Partner (NCP)        dedicated capacity, SLA-backed
    ```

    Select **NVIDIA Build** to get started immediately using free credits from [build.nvidia.com](https://build.nvidia.com).

    **Step 2 — Enter your NVIDIA API key:**

    ```console theme={null}
    Get an API key from: https://build.nvidia.com/settings/api-keys
    ? Enter your NVIDIA API key: **********************
    ```

    Get your API key from [build.nvidia.com/settings/api-keys](https://build.nvidia.com/settings/api-keys).

    **Step 3 — Select a model:**

    ```console theme={null}
    ? Select your primary model:
    > Nemotron 3 Super 120B (nvidia/nemotron-3-super-120b-a12b)
      Nemotron Ultra 253B (nvidia/llama-3.1-nemotron-ultra-253b-v1)
      Nemotron Super 49B v1.5 (nvidia/llama-3.3-nemotron-super-49b-v1.5)
      Nemotron 3 Nano 30B (nvidia/nemotron-3-nano-30b-a3b)
    ```

    **Step 4 — Review and confirm:**

    ```console theme={null}
    Configuration summary:
      Endpoint:    build (https://integrate.api.nvidia.com/v1)
      Model:       nvidia/nemotron-3-super-120b-a12b
      API Key:     nvapi-****...****
      Credential:  $NVIDIA_API_KEY
      Profile:     default
      Provider:    nvidia-nim

    ? Apply this configuration? Yes
    ```
  </Step>

  <Step title="Verify installation">
    When the wizard completes, the output confirms the running environment:

    ```console theme={null}
    ──────────────────────────────────────────────────
    Sandbox      my-assistant (Landlock + seccomp + netns)
    Model        nvidia/nemotron-3-super-120b-a12b (NVIDIA Cloud API)
    ──────────────────────────────────────────────────
    Run:         nemoclaw my-assistant connect
    Status:      nemoclaw my-assistant status
    Logs:        nemoclaw my-assistant logs --follow
    ──────────────────────────────────────────────────

    [INFO]  === Installation complete ===
    ```

    The sandbox is now running with Landlock, seccomp, and network namespace isolation active.
  </Step>
</Steps>

## Connect to the sandbox

<Steps>
  <Step title="Open a shell in the sandbox">
    Run the following command from your host to open an interactive shell session inside the sandbox:

    ```bash theme={null}
    nemoclaw my-assistant connect
    ```

    You will see the connection banner and be dropped into the sandbox shell:

    ```console theme={null}
    Connecting to OpenClaw sandbox: my-assistant
    You will be inside the sandbox. Run 'openclaw' commands normally.
    Type 'exit' to return to your host shell.

    sandbox@my-assistant:~$
    ```
  </Step>

  <Step title="Send a test message using the OpenClaw TUI">
    The OpenClaw TUI opens an interactive chat interface. From inside the sandbox, run:

    ```bash theme={null}
    openclaw tui
    ```

    Type a message and press Enter to send it to the agent. The TUI also displays network egress requests in a side panel — any attempt to reach an unlisted host will appear here for your approval.
  </Step>

  <Step title="Send a test message using the OpenClaw CLI">
    Use the OpenClaw CLI to send a single message and print the agent's response without entering the TUI:

    ```bash theme={null}
    openclaw agent --agent main --local -m "hello" --session-id test
    ```

    | Flag           | Description                                              | Default |
    | -------------- | -------------------------------------------------------- | ------- |
    | `--agent`      | The agent configuration to use.                          | —       |
    | `--local`      | Run against the local sandbox rather than a remote host. | false   |
    | `-m`           | The message to send to the agent.                        | —       |
    | `--session-id` | Session identifier for conversation continuity.          | —       |

    If the agent replies, your sandbox is working correctly. Type `exit` to return to your host shell.
  </Step>
</Steps>

## Non-interactive onboarding

You can skip the interactive prompts by passing all required flags to `nemoclaw onboard` directly. This is useful for automated provisioning or CI environments.

```bash theme={null}
nemoclaw onboard \
  --endpoint build \
  --api-key "$NVIDIA_API_KEY" \
  --model nvidia/nemotron-3-super-120b-a12b
```

| Flag             | Description                                                                                          |
| ---------------- | ---------------------------------------------------------------------------------------------------- |
| `--api-key`      | API key for endpoints that require one. Skips the interactive key prompt.                            |
| `--endpoint`     | Endpoint type: `build`, `ncp`, `nim-local`, `vllm`, `ollama`, `custom`. Default: interactive prompt. |
| `--ncp-partner`  | NCP partner name. Required when `--endpoint ncp`.                                                    |
| `--endpoint-url` | Endpoint URL. Required for `ncp`, `nim-local`, `ollama`, and `custom`.                               |
| `--model`        | Model ID to use. Skips the interactive model selection prompt.                                       |

<Note>
  The `nim-local`, `vllm`, `ollama`, and `custom` endpoint types are experimental. Use `--endpoint build` or `--endpoint ncp` for production setups.
</Note>

## Next steps

<CardGroup cols={2}>
  <Card title="How It Works" icon="circle-info" href="/about/how-it-works">
    Understand the plugin, blueprint, and sandbox lifecycle before customizing your setup.
  </Card>

  <Card title="Switch inference providers" icon="arrows-rotate" href="/inference/switch-inference-providers">
    Switch to a different Nemotron model or configure an NCP endpoint.
  </Card>

  <Card title="Approve network requests" icon="shield-check" href="/network-policy/approve-network-requests">
    Review and approve agent egress requests surfaced in the OpenShell TUI.
  </Card>

  <Card title="Customize network policy" icon="sliders" href="/network-policy/customize-network-policy">
    Pre-approve trusted domains to avoid manual approval at runtime.
  </Card>

  <Card title="Deploy to a remote GPU" icon="server" href="/deployment/deploy-to-remote-gpu">
    Deploy your sandbox to a remote GPU instance for always-on operation.
  </Card>

  <Card title="Monitor sandbox activity" icon="chart-line" href="/monitoring/monitor-sandbox-activity">
    Track agent behavior, network egress, and inference calls through the OpenShell TUI.
  </Card>
</CardGroup>