Skip to main content
NVIDIA
Explore
Models
Skills
Blueprints
GPUs
Docs
Help Center
Getting Started
  1. Create and verify your account to unlock full access to NVIDIA NIM APIs.
ResourcesDeveloper ForumsContact Support
FAQs
  • Terms of Use
    Privacy Policy
    Your Privacy Choices
    Contact

    Copyright © 2026 NVIDIA Corporation

    What is NVIDIA NemoClaw?

    NVIDIA NemoClaw is an open source reference stack that simplifies running OpenClaw always-on assistants with a single command. It installs the NVIDIA OpenShell runtime to add policy-based privacy and security guardrails, giving users more control over their agents' behavior and data handling.

    NemoClaw and OpenShell are currently available in early preview.

    NemoClaw uses open source models, like NVIDIA Nemotron, alongside the NVIDIA OpenShell runtime, a secure environment designed for executing claws more safely. By combining powerful open source models with built-in guardrails, NemoClaw helps simplify and strengthen the way organizations deploy AI agents.

    Why You Need NemoClaw

    Details about NemoClaw - click to view full size

    • One-command setup: Install the OpenShell runtime, open models, and tools to run always-on agents.
    • Built-in safeguards: Apply OpenShell configurable controls for privacy, security, and policy compliance.
    • AI-powered workflows: Use Nemotron and other open models to handle reasoning and task automation.
    • Flexible execution: Run long-running agents locally, on cloud, or on enterprise hardware with full control.

    NemoClaw Workflow

    NemoClaw Workflow - click to view full size

    On this page

    1. What is NVIDIA NemoClaw?
    2. Why You Need NemoClaw
    3. NemoClaw Workflow

    nvidia

    NemoClaw for OpenClaw

    NemoClaw

    Run always-on agents with greater control, privacy, and flexibility—installed with a single command.

    • NVIDIA AI
    • General
    • openclaw
    • sandbox
    • security
    View GitHubTry Now