NemoClaw
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference observed · 2026-10-17
Health v2 · maintenance only
69/100
- Activity 100
- Release rhythm 60
- Longevity 15
Flags: prerelease_only
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 219
- days_rel: 19
- days_push: 4
- n_releases_24m: 1
Adoption not part of the score
22754 stars · 3145 forks observed · 2026-10-17
What it is AI-extracted, prompt v1, taxonomy v1, 2026-10-12, confidence 0.97
NVIDIA NemoClaw is a reference stack that runs AI agents like OpenClaw, Hermes, and LangChain Deep Agents inside secure OpenShell sandboxes. It provides a CLI for onboarding, managed inference, network policies, and state persistence.
Use cases
- run AI coding agents securely on a DGX or WSL host
- manage sandboxed inference for multiple agents with network policies
- deploy and monitor AI agents in a controlled OpenShell environment
- integrate custom plugins and state backups for AI agents
- configure and enforce network request approvals for AI agents
When to choose
- you need sandboxed execution of AI agents with strict security controls
- you want a managed CLI to handle inference routing and lifecycle of agents
- your deployment targets include NVIDIA hardware or WSL environments
- you require built‑in network policy and state persistence for agents
When to avoid
- you are looking for a pure library without a CLI or sandboxing layer
- your agents are not compatible with OpenShell or require non‑NVIDIA runtimes
- you need a lightweight solution without the overhead of managed inference
Facets
cli-tool · maturity active
cli agent-framework state-management security windows typescript openshell nvidia managed-inference sandboxed-agents sandboxing network-policy ai-agents devops linux wsl nodejs docker
10 sources
- readme: https://github.com/NVIDIA/NemoClaw · fetched 2026-10-17 · eaeccc89d7da
- homepage: https://docs.nvidia.com/nemoclaw/latest/ · fetched 2026-09-28 · a2ee006c816f
- site_page: https://docs.nvidia.com/nemoclaw/user-guide/openclaw/resources/engineer-agentic-documentation · fetched 2026-09-28 · a564bb5f842c
- site_page: https://docs.nvidia.com/nemoclaw/user-guide/openclaw/about/overview · fetched 2026-09-28 · 9d627320cb92
- site_page: https://docs.nvidia.com/nemoclaw/user-guide/openclaw/about/how-it-works · fetched 2026-09-28 · 49d6e6024087
- site_page: https://docs.nvidia.com/nemoclaw/user-guide/openclaw/about/ecosystem · fetched 2026-09-28 · 7cca05e55153
- site_page: https://docs.nvidia.com/nemoclaw/user-guide/openclaw/get-started/quickstart · fetched 2026-09-28 · 438ff3219f33
- site_page: https://docs.nvidia.com/nemoclaw/user-guide/openclaw/inference/about-inference-routing · fetched 2026-09-28 · fdcd3d6e5433
- site_page: https://docs.nvidia.com/nemoclaw/user-guide/openclaw/manage-sandboxes/install-openclaw-plugins · fetched 2026-09-28 · 1861398e52d4
- site_page: https://docs.nvidia.com/nemoclaw/user-guide/openclaw/resources/agent-skills · fetched 2026-09-28 · d81e39e1c930
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| NVIDIA/NemoClaw | main | 69 |
| NVIDIA/nemoclaw-community | examples | 57 |
For agents
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem