NemoClaw is OpenClaw running inside NVIDIA's OpenShell security sandbox. Every network call, file access, and AI request goes through a policy engine you control — your API keys never touch the inside of the container. You don't need NVIDIA GPU hardware to use it; most users run it on a $10/month VPS connected to Claude or OpenAI.
Guides
NemoClaw uses the same skill architecture as OpenClaw — all official skills are compatible. We don't maintain a separate skills database for NemoClaw:
→ Skills Guide: Write Your Own
→ Skills Database: 53 Verified Official
Skill install commands are identical: openclaw skill install <name> works unchanged inside the NemoClaw sandbox.
NemoClaw vs OpenClaw — What's Different
| Feature | NemoClaw | OpenClaw |
|---|---|---|
| Execution environment | OpenShell security sandbox (containerised) | Direct on host OS |
| Network policy | Deny-by-default; you allowlist domains explicitly | Permissive by default |
| API key security | Keys stored outside sandbox via OpenShell provider system | In config files on host |
| GPU inference | Optional NVIDIA Nemotron models if GPU available | Ollama or cloud providers |
| Setup complexity | More steps (Docker, OpenShell, sandbox, Caddy) | Single CLI install |
| Skill compatibility | Full — all 53 official OpenClaw skills work | Full |
If you don't need the sandbox security model, OpenClaw is simpler to start with. If you're handling credentials, production infrastructure, or sensitive data, NemoClaw's defaults are worth the extra setup.
Related on This Site
- OpenClaw hub — the base framework NemoClaw runs on top of
- IronClaw — a different security-hardened approach: stricter defaults without Docker/OpenShell
- Weekly News Digest — NemoClaw updates and OpenShell security advisories