NVIDIA/NemoClaw

Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

About the project

NVIDIA/NemoClaw is an open-source reference stack for running supported AI agents inside NVIDIA OpenShell sandboxes with managed inference, network policies, integrations, snapshots, and lifecycle controls. It is used to run agents such as OpenClaw, Hermes, and LangChain Deep Agents with administrative and security controls. Catalogue add-ons guide coding agents through NemoClaw workflows.

32 files for Codex, Claude Code and OpenCode: nemoclaw-contributor-create-pr, nemoclaw-contributor-implement-issue, nemoclaw-contributor-onboard, nemoclaw-contributor-plan-issue and 28 more — 2,442 tokens loaded in every session.

22,871Stars on the repository
32Files it configures its agents with
2,442Tokens loaded in every session
3Agents configured

Instructions

Skills

These files are NVIDIA/NemoClaw's own configuration — they tell Codex, Claude Code and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.