NVIDIA/NemoClaw
#122 of 783 by Stars among GitHub repos
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
About
NVIDIA NemoClaw is an open source reference stack for running always-on AI agents more safely inside NVIDIA OpenShell sandboxes. It provides guided onboarding, a hardened blueprint, routed inference, network policy, and lifecycle management through a single CLI.
For capabilities, architecture, security controls, and the full feature list, see the NemoClaw documentation.
Use the starter prompt when you want Cursor, Claude Code, Codex, Copilot, or another local coding agent to install NemoClaw with you.
The prompt tells your agent to use NemoClaw docs and skills, ask one question at a time, run commands only with your approval, and keep secrets out of chat.
Review Prerequisites before…
Excerpted from github.com/NVIDIA/NemoClaw
Latest metrics
| Stars | 21.8k | 2026-07-16 |
|---|---|---|
| Forks | 2.9k | 2026-07-16 |
| Commits | 3.2k | 2026-07-16 |
| Releases | 0 | 2026-07-16 |
| Watchers | 109 | 2026-07-16 |
| Open issues | 124 | 2026-07-16 |
| Open PRs | 60 | 2026-07-16 |