NVIDIA NemoClaw
Deploy more secure, always-on AI assistants with a single command.
Overview
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.
Install and Get Started Quickly
-
Terminal
-
Agent
$ curl -fsSL https://nvidia.com/nemoclaw.sh | bash
$ nemoclaw onboard
“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
Always-on agents need dedicated compute to run tools, write code, and complete tasks. NemoClaw provides local, 24/7 compute for autonomous agents on systems like NVIDIA GeForce RTX™ PCs/laptops, NVIDIA RTX™ PRO workstations, and NVIDIA DGX Station™ or DGX Spark™.
Join the Community
Join us on Discord to ask questions, share your projects, and connect with other developers and users.