NVIDIA NemoClaw: Deploy Safer AI Agents in a Single Command

2 min read Original article ↗

Deploy more secure, always-on AI assistants with a single command.

Run Autonomous Agents More Safely

NVIDIA NemoClaw is an open source stack that adds privacy and security controls to OpenClaw. With one command, anyone can run always-on, self-evolving agents anywhere. Try NemoClaw now in early preview.

NemoClaw uses NVIDIA Agent Toolkit software to secure OpenClaw. It installs NVIDIA OpenShell to enforce policy-based privacy and security guardrails, giving users control over how agents behave and handle data. 

It also evaluates available compute resources to run high-performance open models like NVIDIA Nemotron™ locally for enhanced privacy and cost efficiency.

Run Autonomous, Self-Evolving Agents More Safely, Instantly

NVIDIA OpenShell is an open source runtime that enables autonomous agents to operate and adapt faster and more safely.

Create Trustworthy AI Agents With NVIDIA Agent Toolkit

Bring trust and safety to autonomous agents with NVIDIA Agent Toolkit. Use OpenShell for enhanced safety and privacy and AI-Q to build reasoning agents that transform enterprise data into explainable results.

Install and Get Started with the Early Preview

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

“Help me install nvidia.com/nemoclaw”

Features

Run Claws More Safely

OpenClaw has become the operating system for personal AI. NemoClaw adds security and privacy controls, so developers can build and run AI assistants with more confidence, while also contributing to the OpenClaw project.

Use Any Coding Agent

Tap open models like NVIDIA Nemotron locally on your dedicated system. A privacy router also connects agents to cloud-based frontier models, allowing agents to develop new skills within defined privacy and security guardrails. 

Deploy Anywhere

Join the Community

Join us on Discord to ask questions, share your projects, and connect with other developers and users.