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

# Use NemoClaw with SaladCloud

> Learn how to use NVIDIA NemoClaw - a secure, sandboxed OpenClaw runtime with a self-hosted model on SaladCloud.

*Last Updated: May 18, 2026*

## Introduction

[NVIDIA NemoClaw](https://github.com/NVIDIA/NemoClaw) is an open-source reference stack from that runs OpenClaw inside a
sandboxed container environment [NVIDIA OpenShell](https://github.com/NVIDIA/OpenShell). It adds OS-level filesystem and
network isolation to OpenClaw agents, making it safer to run autonomous AI assistants on your machine. NemoClaw supports
custom OpenAI-compatible inference endpoints, so you can point it at a model on SaladCloud instead of a cloud provider.

NemoClaw works with SaladCloud in two ways:

* **[Salad AI Gateway](/ai-gateway/explanation/overview)** - no infrastructure to deploy or manage. Sign up for access,
  point NemoClaw at a single shared endpoint, and use your Salad API key with standard authentication. Currently in
  closed beta with monthly flat-rate access.
* **Self-hosted model** - deploy your own LLM recipe on SaladCloud Container Engine, billed per hour. Note: NemoClaw
  cannot pass custom headers, so authentication must be disabled on self-hosted deployments.

<Warning>
  NemoClaw is currently in **alpha** (as of March 2026). APIs, configuration schemas, and runtime behavior are subject
  to breaking changes between releases. It is not recommended for production use.
</Warning>

## Prerequisites

Before getting started, make sure you have:

* A [SaladCloud account](https://portal.salad.com)
* Docker installed (Linux/Windows WSL2) or Apple Container (macOS)
* A Linux, macOS, or Windows (WSL2) machine

## Step-by-Step Setup

### Step 1: Choose Your Backend

<Tabs>
  <Tab title="Salad AI Gateway">
    Salad AI Gateway is the recommended option for NemoClaw - it uses standard Bearer token authentication, which
    NemoClaw supports natively.

    1. Sign up for early access at [salad.com/ai-gateway](https://salad.com/ai-gateway).
    2. Once approved, find your **Salad API key** in the [portal](https://portal.salad.com/api-key).

    Available models:

    | Model             | Description                                                              |
    | :---------------- | :----------------------------------------------------------------------- |
    | `qwen3.6-35b-a3b` | Qwen 3.6 35B-A3B - best for agentic tasks, coding, and complex reasoning |
    | `qwen3.6-27b`     | Qwen 3.6 27B - strong balance of capability and speed                    |
    | `qwen3.5-9b`      | Qwen 3.5 9B - fastest response times, suited for lighter tasks           |
  </Tab>

  <Tab title="Self-Hosted on SaladCloud">
    First, deploy an OpenAI-compatible LLM server on SaladCloud.

    * Go to the [SaladCloud portal](https://portal.salad.com) and create an account if you do not already have one.
    * Create an organization or choose an existing one, then click "Deploy a container group".
    * Select an LLM recipe. The Qwen3.6-35B-A3B (llama.cpp) recipe is well-suited for conversational assistant use
      cases. On the recipe page, provide a name and deploy - the rest is preconfigured with recommended settings.
    * Once deployed, your endpoint will be live and serving an OpenAI-compatible API.

    Available recipes:

    Ready-to-deploy recipes (best for less technical users):

    * [qwen3.6-35B-A3B](/container-engine/reference/recipes/qwen3.6-35b-a3b-llama-cpp) - A powerful Mixture of Experts
      model optimized for instruction-following tasks, ideal for agentic use cases.
    * [qwen3.5-9b-llama-cpp](/container-engine/reference/recipes/qwen3.5-9b-llama-cpp) - Optimized for Qwen3.5 9B model.

    Recipes for custom deployments (best for advanced users):

    * [llama.cpp](/container-engine/reference/recipes/llama-cpp) - Supports GGUF models
    * [sglang](/container-engine/reference/recipes/sglang) - High-performance inference
    * [vllm](/container-engine/reference/recipes/vllm) - Popular LLM serving framework
    * [ollama](/container-engine/reference/recipes/ollama) - Simple model management
    * [tgi](/container-engine/reference/recipes/tgi) - Hugging Face Text Generation Inference server

    After deployment, note your:

    * **API endpoint URL** (e.g., `https://your-endpoint.salad.cloud`)
  </Tab>
</Tabs>

### Step 2: Install NemoClaw

Run the official install script:

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

Verify the installation:

```bash theme={null}
nemoclaw --version
```

### Step 3: SaladCloud Authentication

<Tabs>
  <Tab title="Salad AI Gateway">
    AI Gateway uses standard Bearer token authentication. Enter your Salad API key when the onboarding wizard prompts
    for an API key - no additional configuration needed.
  </Tab>

  <Tab title="Self-Hosted on SaladCloud">
    For easy setup, when deploying your SaladCloud container group, leave the **Authentication** toggle off. Your
    endpoint will be accessible without a key.

    If you prefer to keep authentication enabled, you can still use NemoClaw by providing a dummy API key during
    onboarding and hardcoding your actual key in the config file after setup (see Step 4). You need to connect to the
    sandbox and update config file : /sandbox/.openclaw/openclaw\.json. Add the following `headers` section under
    models.providers

    ```json theme={null}
    "headers": {
      "Salad-Api-Key": "your-actual-api-key"
    }
    ```
  </Tab>
</Tabs>

### Step 4: Run the Onboarding Wizard

Start NemoClaw onboarding:

```bash theme={null}
nemoclaw onboard
```

When prompted to select an inference endpoint:

1. Choose **Other OpenAI-compatible endpoint** from the provider list
2. Enter your endpoint URL when prompted:

<Tabs>
  <Tab title="Salad AI Gateway">
    * **Endpoint URL**: `https://ai.salad.cloud/v1` - **API key**: your Salad API key - **Model name**: e.g.
      `qwen3.6-35b-a3b`
  </Tab>

  <Tab title="Self-Hosted on SaladCloud">
    * **Endpoint URL**: `https://your-endpoint.salad.cloud/v1` - **API key**: any non-empty string (e.g., `dummy`) since
      authentication is disabled - **Model name**: the name of the model you deployed (e.g., `qwen3.6-35b-a3b`)
  </Tab>
</Tabs>

5. NemoClaw will build a container and validate connectivity to the endpoint before completing setup
6. Follow the remaining prompts to finish configuration

### Step 5: Test the Connection

Once onboarding completes you can connect to your sandboxed assistant by running
`nemoclaw <your_assistant_name> connect` and then connecting to it via the local TUI (`openclaw tui`), by accessing
local dashboard (`ws://127.0.0.1:18789`) or by setting up a messaging channel (e.g., Telegram bot).

> "Hello! Summarize what SaladCloud is in two sentences."

If NemoClaw responds, your setup is complete.

### Model Recommendations

* **Qwen 3.6-35B-A3B**: Best for complex assistant tasks and agentic workflows
* **Qwen 3.5-9B**: Suitable for simple Q\&A and quick responses