NVIDIA /NemoClaw
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
★ 23,029⑂ 3,218👁 109⑃ 9,259● 4,972▤ 1
+4
日增长
+100
周增长
+306
月增长
23,029
stars
3,218
forks
109
watchers
9,259
prs
4,972
issues
1
releases
README
NVIDIA NemoClaw: Reference Stack for Sandboxed AI Agents in OpenShell NVIDIA NemoClaw is an open source reference stack for running supported AI agents more safely inside NVIDIA OpenShell sandboxes. It provides guided onboarding, managed inference, network policy, managed integrations, OpenShell-backed state persistence, and lifecycle operations through the NemoClaw CLI and its agent-specific aliases. Supported agents: - OpenClaw (default) - Hermes - LangChain Deep Agents Code For capabilities, architecture, security controls, and the full feature list, see the NemoClaw documentation. Get Started Start with Your Coding Agent Use the starter prompt when you want Cursor, Claude Code, Codex, Copilot, or another local coding agent to install NemoClaw with you. Copy the NemoClaw starter prompt. 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. Install Using the Installer in Your Terminal Review Prerequisites before installing. On a supported DGX or Windows Subsystem for Linux (WSL) host, press Enter at the Run express install with these settings? [Y/n]: prompt to use the recommended preset settings for that platform. Express install mode installs OpenClaw by default. If you accept, refer to NemoClaw Quickstart with OpenClaw. Enter n if you want to choose Hermes or LangChain Deep Agents Code, a sandbox name, an inference provider, and a model interactively. When connecting to a Hermes sandbox from a light terminal, NemoClaw may install a managed nemoclaw-light Hermes skin for readable assistant text; it removes that managed skin state again when the terminal no longer needs it and preserves any user-selected Hermes skin. | Agent | Guide | |-------|-------| | OpenClaw (default) | Quickstart with OpenClaw | | Hermes | Quickstart with Hermes | | LangChain Deep Agents Code | Quickstart with LangChain Deep Agents Code | Documentation Refer to the following pages on the official documentation website for more information on NemoClaw. | Page | Description | |------|-------------| | Overview | What NemoClaw does and how it fits together. | | Architecture Overview | High-level overview of the host CLI, agent integration layer, blueprint, sandbox lifecycle, and protection layers. | | Ecosystem | How OpenClaw, OpenShell, and NemoClaw form a stack and when to use NemoClaw versus OpenShell alone. | | Architecture Details | Detailed description of agent integration structure, blueprint lifecycle, sandbox environment, and host-side state. | | Prerequisites | Hardware, software, and supported platforms, with any platform-specific pre-setup. | | Choose an Inference Provider | Supported providers, validation, and routed inference configuration. | | Network Policies | Baseline rules, operator approval flow, and egress control. | | Customize Network Policy | Static and dynamic policy changes, presets. | | Security Best Practices | Controls refe
Top issues
#7209VDR 5 checklist: non-DGX findings and current-release verification36 comments · 2026-07-20#8178[Epic] Support native Windows through OpenShell MXC26 comments · 2026-08-03#13935[V1 E2E] Enable DGX Station (GB300, Ubuntu 24, ARM64) in CI17 comments · 2026-10-28#8144[Epic] Support llama.cpp as a managed local inference server17 comments · 2026-08-03#7361Canonical provider credential resolution via separate --provider/-m flags sends mask_secret() output as literal API key (401 Invalid API key)15 comments · 2026-07-22#9813Phase 1 slice 11: Complete the OpenShell CLI consumer sweep13 comments · 2026-08-20#7003`status` inference health can only attest a fresh exec's environment, never the serving process's — surface process-level (self-reported) health13 comments · 2026-07-16#7144perf(e2e): reduce rebuild-hermes runtime with pinned fixtures and reusable build cache11 comments · 2026-07-18
Discussions
#14460NemoClaw v0.0.144 is out 🎉0 comments · 2026-11-13#14408Opt-in keyless web search for Hermes sandboxes (no credential to inject)0 comments · 2026-11-11#14386NemoClaw v0.0.143 is out!0 comments · 2026-11-11#14282NemoClaw v0.0.142 is out!0 comments · 2026-11-06#14165NemoClaw v0.0.141 is out!0 comments · 2026-11-04#14053Automatic AI agent developer0 comments · 2026-11-01#14005NemoClaw v0.0.140 is out!0 comments · 2026-10-30#13974Content-aware egress filtering: should NemoClaw have a hook for PII redaction on allowed traffic?0 comments · 2026-10-29
Latest release
Native Podman E2E toolchains — 2026-10-01 ci-native-podman-e2e-2026-10-01 Pre-release 2026-10-01Pinned CI toolchains for NemoClaw's native Podman E2E jobs. These assets preserve existing reviewed binaries so E2E startup no longer depends on expiring GitHub Actions artifacts. Recovered without modification from trusted main E2E run 36537895087, generate-matrix job 109331743180, at commit 2272c5c15dd873c79436120ac0bfd21f70ae962e. That job staged the original toolchains through action 8d7409d66a0e664829f9ddab177aa8460974291f before candidate checkout, verifying source run 33211526093 and its artifact identities. The original source artifacts have since expired. | Architecture | Retained a