Prerequisites | NVIDIA NemoClaw

Before you start, verify that your machine has the software and hardware needed to run NemoClaw.

Hardware

Resource	Minimum	Recommended
CPU	4 vCPU	4+ vCPU
RAM	8 GB	16 GB
Disk	20 GB free	40 GB free

The sandbox image is approximately 2.4 GB compressed. During image push, the Docker daemon, k3s, and the OpenShell gateway run alongside the export pipeline. The pipeline buffers decompressed layers in memory. On machines with less than 8 GB of RAM, this combined usage can trigger the OOM killer. If you cannot add memory, configure at least 8 GB of swap to work around the issue at the cost of slower performance.

Software

Dependency	Version
Node.js	22.19 or later
npm	10 or later
Python	Python 3 at a trusted system location, with POSIX descriptor-relative filesystem support
Docker	Docker Engine, Docker Desktop, or Colima on a tested platform
Platform	Refer to Platforms below

On Linux, the installer checks Docker before it installs the NemoClaw CLI. The installer can install Docker, start the Docker service, and add your user to the docker group. When Docker is missing, the installer downloads Docker’s official convenience script, prompts for sudo, and starts the service when systemd is available. In a non-interactive run, the installer can reactivate the group through sg docker and continue onboarding. If that path is unavailable or does not restore Docker access, the installer exits with newgrp docker guidance before it starts onboarding.

NemoClaw uses an isolated python3 helper for descriptor-relative migration snapshot sanitization and deletion. NemoClaw does not resolve this credential-bearing helper through the host PATH. It accepts a verified executable at /usr/bin/python3, /usr/local/bin/python3, /opt/homebrew/bin/python3, /opt/local/bin/python3, or beside the Node.js executable. The sanitizer fails closed before it reads snapshot content if no candidate passes its ownership, permission, and executable checks. Supported Linux, macOS, and WSL environments provide the required POSIX filesystem operations. Native Windows is not a supported execution path; use WSL.

If you choose the native Linux Ollama install path, the onboard wizard also requires zstd for Ollama archive extraction. The installer also requires strings from binutils to verify the OpenShell binary before it continues with OpenShell install work.

Docker Group Access

NemoClaw needs Docker access. On personal Linux development machines, adding your user to the docker group is the standard way to run Docker without sudo. Members of the docker group can control the daemon with root-level impact. Grant this access only to trusted local accounts. On shared or managed systems, use your organization’s approved Docker access path. For background, review Docker’s daemon attack surface guidance.

On Debian and Ubuntu, NemoClaw installs zstd with apt-get if it is missing; on other Linux distributions, install zstd before onboarding. If the installer reports that strings is missing, install binutils and rerun the installer:

$ sudo apt-get install -y binutils

On macOS, NemoClaw uses the Docker-driver OpenShell gateway path with Docker Desktop or Colima. You do not need to install or sign a separate OpenShell VM driver helper for standard macOS onboarding. If you use Homebrew Colima, install the Docker CLI package with Colima because brew install colima does not provide the docker command:

$ brew install colima docker
$ colima start --cpu 4 --memory 8
$ docker info

OpenShell Lifecycle

For NemoClaw-managed environments, use nemo-deepagents onboard when you need to create or recreate the OpenShell gateway or sandbox. Avoid openshell self-update, npm update -g openshell, or openshell sandbox create directly unless you intend to manage OpenShell separately and then rerun nemo-deepagents onboard.

Docker Storage Driver

On Linux hosts running Docker 26 or later with the containerd image store enabled, nemo-deepagents onboard transparently builds a fuse-overlayfs-enabled cluster image. The containerd image store is the install-time default for fresh docker-ce installations on Ubuntu 24.04 and similar distros. The fuse-overlayfs-enabled image bypasses a kernel-level nested-overlay limitation in k3s. You do not need manual setup.

Platforms

The following table lists platforms with a documented installation path. A Tested with limitations row applies only to the configuration in its notes. The table comes from ci/platform-matrix.json, the single source of truth kept in sync by CI and QA.

OS	Container runtime	Status	Notes
DGX OS (Spark)	Docker	Tested	Use the standard installer and `nemo-deepagents onboard`. DGX Spark Express keeps automatic managed-vLLM serving-profile selection as option 1 and offers the fixed single-host catalog profile as option 2. The automatic two-DGX Spark managed-vLLM profile is Experimental, and physical two-node end-to-end validation is pending. For the profile requirements and controls, see Set Up vLLM on Two DGX Sparks. For the validated single-DGX Spark walkthrough with local inference, see the NVIDIA Spark playbook.
DGX OS (Station)	Docker	Tested with limitations	Tested with limitations across qualified profiles on one physical DGX Station GB300; see Additional Setup for DGX Station for accepted profiles, the pending no-OTA DGX OS `7.6.x` end-to-end qualification, runtime gates, and current dual-Station and dedicated CI limitations.
Linux	Docker	Tested	Primary tested path. Ubuntu 24.04 has host-level onboarding validation. A digest-pinned Ubuntu 26.04 userspace lane builds the CLI and runs preflight, installer, and platform contracts on eligible main pushes; Docker-host, AppArmor, Landlock, and live onboarding validation on 26.04 remain pending. Other distros (Ubuntu 22.04, Fedora, Rocky, Alma, NixOS, Arch) may work but are not validated.
macOS (Apple Silicon)	Colima, Docker Desktop	Tested with limitations	Start the container runtime (Colima or Docker Desktop) before installing; NemoClaw verifies the pinned official OpenShell formula and grants formula-scoped trust only around each Homebrew install, inspection, start, or stop operation, requires a legacy or changed formula to be repaired by rerunning the pinned installer, uses the standalone gateway only when Homebrew is absent or both the staged formula and installed keg are absent, requires Homebrew Colima users to install both Colima and the Docker CLI (`brew install colima docker`) before `docker info` can work, and recommends Xcode Command Line Tools (`xcode-select --install`) for Node native modules.
N1x FASTOS	Docker	Deferred	N1x Express remains Deferred until a physical NemoClaw Express E2E test passes. Host identity requires Linux `arm64`, a trusted `/etc/fastos-release` marker with `NAME="N1x FASTOS"`, and NVIDIA display PCI identity `10de:2e2a`. CUDA and Container Device Interface (CDI) readiness are still required.
Windows WSL2	Docker Desktop (WSL backend)	Tested with limitations	Requires WSL2 with Docker Desktop backend. See Additional Setup for Windows Machines before the Quickstart.

For the complete platform support matrix, including all deferred platforms and CI coverage, refer to Platform Support.

Additional Setup

Most supported platforms require no additional setup beyond the hardware and software requirements above. Use only the page that matches your host.

DGX Station Express Preparation

If you are using a qualifying DGX Station GB300, follow Prepare DGX Station to Install NemoClaw before the Quickstart.

Windows Preparation

If you are using Windows, follow Prepare a Windows Machine to Install NemoClaw before the Quickstart.

Next Steps

Quickstart installs NemoClaw and launches your first sandboxed agent.
Use NemoClaw Docs with Your Coding Agents lets your AI coding assistant fetch NemoClaw Markdown docs before setup.