NemoClaw
- About
- NVIDIA's open-source stack for running AI agents in secure sandboxes.
- Catalogue
- No. 105
- Category
- AI
- GitHub stars
- ★ 0

Overview
NVIDIA NemoClaw is an open-source reference stack for running AI agents more safely inside NVIDIA OpenShell sandboxes. It supports OpenClaw by default, as well as Hermes and LangChain Deep Agents Code.
What it does well
NemoClaw provides guided setup, managed inference, network policies, managed integrations, persistent state and lifecycle commands through one CLI. It adds privacy and security guardrails around long-running agents and can run open models locally. It is an alpha project, so maintainers respond on a best-effort basis.
Why it’s in the collection
NemoClaw addresses the biggest worry with always-on AI agents: what they can reach. It wraps popular open-source agents in policy-controlled sandboxes, and it is Apache-licensed.
On GitHub
- Stars
- 0
- Forks
- 0
- Commits
- 0
- Repository
- NVIDIA/NemoClaw
Languages
- TypeScript 94.4%
- Shell 2.8%
- Python 1.8%
- Other 1%



