# NVIDIA NemoClaw

## Docs

- [How It Works](https://mintlify.wiki/NVIDIA/NemoClaw/about/how-it-works.md): Plugin, blueprint, sandbox creation, and inference routing concepts for NemoClaw.
- [Release notes](https://mintlify.wiki/NVIDIA/NemoClaw/about/release-notes.md): Changelog and feature history for NemoClaw releases.
- [Deploy to a remote GPU](https://mintlify.wiki/NVIDIA/NemoClaw/deployment/deploy-to-remote-gpu.md): Provision a remote GPU VM with NemoClaw using Brev. Covers prerequisites, the deploy command, connecting to the sandbox, and monitoring.
- [Set up the Telegram bridge](https://mintlify.wiki/NVIDIA/NemoClaw/deployment/set-up-telegram-bridge.md): Forward messages between a Telegram bot and the OpenClaw agent running inside the sandbox.
- [Quickstart](https://mintlify.wiki/NVIDIA/NemoClaw/get-started/quickstart.md): Install NemoClaw, launch a sandbox, and run your first sandboxed OpenClaw agent.
- [Switch inference providers](https://mintlify.wiki/NVIDIA/NemoClaw/inference/switch-inference-providers.md): Change the active inference model while the sandbox is running. No restart is required.
- [NVIDIA NemoClaw](https://mintlify.wiki/NVIDIA/NemoClaw/introduction.md): Run OpenClaw AI agents safely inside NVIDIA OpenShell — with sandboxed execution, cloud inference, and declarative network policy.
- [Monitor sandbox activity](https://mintlify.wiki/NVIDIA/NemoClaw/monitoring/monitor-sandbox-activity.md): Inspect sandbox health, trace agent behavior, and diagnose problems using status, logs, and the OpenShell TUI.
- [Approve network requests](https://mintlify.wiki/NVIDIA/NemoClaw/network-policy/approve-network-requests.md): Review and approve blocked agent network requests in the OpenShell TUI.
- [Customize the network policy](https://mintlify.wiki/NVIDIA/NemoClaw/network-policy/customize-network-policy.md): Add, remove, or modify allowed endpoints in the sandbox policy. Covers static changes, dynamic updates, and policy presets.
- [Architecture](https://mintlify.wiki/NVIDIA/NemoClaw/reference/architecture.md): Plugin structure, blueprint lifecycle, sandbox environment, and inference routing.
- [Commands](https://mintlify.wiki/NVIDIA/NemoClaw/reference/commands.md): Full CLI reference for all NemoClaw plugin and standalone commands.
- [Inference profiles](https://mintlify.wiki/NVIDIA/NemoClaw/reference/inference-profiles.md): Configuration reference for NemoClaw inference providers — NVIDIA cloud, NCP partners, and experimental local options.
- [Network policies](https://mintlify.wiki/NVIDIA/NemoClaw/reference/network-policies.md): Baseline network policy, filesystem rules, policy layers, and the operator approval flow for NemoClaw sandboxes.