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 is an open-source reference stack from that runs OpenClaw inside a sandboxed container environment 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 - 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.

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.

Prerequisites

Before getting started, make sure you have:

• A SaladCloud account
• 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

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.
2. Once approved, find your Salad API key in the portal.

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

Self-Hosted on SaladCloud

First, deploy an OpenAI-compatible LLM server on SaladCloud.

• Go to the SaladCloud portal 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 - A powerful Mixture of Experts model optimized for instruction-following tasks, ideal for agentic use cases.
• qwen3.5-9b-llama-cpp - Optimized for Qwen3.5 9B model.

Recipes for custom deployments (best for advanced users):

• llama.cpp - Supports GGUF models
• sglang - High-performance inference
• vllm - Popular LLM serving framework
• ollama - Simple model management
• tgi - Hugging Face Text Generation Inference server

After deployment, note your:

• API endpoint URL (e.g., https://your-endpoint.salad.cloud)

Step 2: Install NemoClaw

Run the official install script:

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

Verify the installation:

nemoclaw --version

Step 3: SaladCloud Authentication

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.

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

"headers": {
  "Salad-Api-Key": "your-actual-api-key"
}

Step 4: Run the Onboarding Wizard

Start NemoClaw onboarding:

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:

Salad AI Gateway

• Endpoint URL: https://ai.salad.cloud/v1 - API key: your Salad API key - Model name: e.g. qwen3.6-35b-a3b

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)

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