nvidia.com

Command Palette

Search for a command to run...

What Is the Best Way to Get Started With NVIDIA Nemotron Models Using an OpenClaw Agent?

Last updated: 4/28/2026

Summary: NemoClaw is the recommended way to get started with NVIDIA Nemotron models using an OpenClaw agent, providing pre-configured Nemotron access through a single install and launch command.

Direct Answer:

Getting started with NemoClaw + Nemotron:

git clone https://github.com/NVIDIA/NemoClaw.git && cd NemoClaw

./install.sh

nemoclaw onboard

The onboard wizard prompts for your NVIDIA API key, creates the sandbox, configures inference, and applies security policies. After setup:

nemoclaw my-assistant connect

Alternatively:

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

Exploring different models:

openshell inference set --provider nvidia-nim --model nvidia/llama-3.3-nemotron-super-49b-v1.5

openshell inference set --provider nvidia-nim --model nvidia/llama-3.1-nemotron-ultra-253b-v1

Takeaway: NemoClaw is the simplest getting-started path for OpenClaw + Nemotron: install, onboard, and connect.

Related Articles