Skip to main content
NemoClaw is NVIDIA’s open source security stack for OpenClaw. It wraps OpenClaw with the NVIDIA OpenShell runtime to provide kernel-level sandboxing, network policy controls, and audit trails for AI agents.

​
Quick start

Pull a model: 
ollama pull nemotron-3-nano:30b
Run the installer: 
curl -fsSL https://www.nvidia.com/nemoclaw.sh | \
  NEMOCLAW_NON_INTERACTIVE=1 \
  NEMOCLAW_PROVIDER=ollama \
  NEMOCLAW_MODEL=nemotron-3-nano:30b \
  bash
Connect to your sandbox: 
nemoclaw my-assistant connect
Open the TUI: 
openclaw tui
Ollama support in NemoClaw is still experimental.

​
Platform support

PlatformRuntimeStatus
Linux (Ubuntu 22.04+)DockerPrimary
macOS (Apple Silicon)Colima or Docker DesktopSupported
WindowsWSL2 with Docker DesktopSupported
CMD and PowerShell are not supported on Windows — WSL2 is required.
Ollama must be installed and running before the installer runs. When running inside WSL2 or a container, ensure Ollama is reachable from the sandbox (e.g. OLLAMA_HOST=0.0.0.0).

​
System requirements

  • CPU: 4 vCPU minimum
  • RAM: 8 GB minimum (16 GB recommended)
  • Disk: 20 GB free (40 GB recommended for local models)
  • Node.js 20+ and npm 10+
  • Container runtime (Docker preferred)
  • nemotron-3-super:cloud — Strong reasoning and coding
  • qwen3.5:cloud — 397B; reasoning and code generation
  • nemotron-3-nano:30b — Recommended local model; fits in 24 GB VRAM
  • qwen3.5:27b — Fast local reasoning (~18 GB VRAM)
  • glm-4.7-flash — Reasoning and code generation (~25 GB VRAM)
More models at ollama.com/search.