AI Models

NemoClaw WINDOWS Setup Guide (It Actually WORKS)

Published
Mar 19, 2026
Duration
19:24
Module
AI Models
Click to load the YouTube player

Video summary

Companion notes

# NemoClaw runs on Windows only through WSL2, and the GPU passthrough step is where it usually dies

## Why a native install is off the table NemoClaw does not run on Windows natively. It depends on Linux kernel features — landlock, network namespaces — that the NT kernel does not ship. The video's intro states "even experienced developers can't get it to work natively," which is why the guide is built around WSL2 as a Linux sidecar.

## The base layer: WSL2 + Ubuntu + systemD You install WSL2 and Ubuntu in a single PowerShell-as-admin command, reboot, then edit /etc/wsl.conf to add [boot] systemd=true. The creator calls this "the step that almost every guide skips and it'll break everything later." Docker Desktop (Windows AMD64 build from docker.com) is then pointed at Ubuntu 22.04 under Resources → WSL integration, verified with the hello-world image.

## The make-or-break step: Nvidia driver 595.79 Before touching Linux, the Windows Nvidia driver must be updated. The rig ships on driver 581.95; the required upgrade is 595.79, released March 10, 2025. Installing the Windows driver auto-writes the GPU stub inside WSL2. The creator is emphatic: "Do not install any Nvidia driver inside the Ubuntu WSL2 side." Doing so overwrites the stub. A repo bug also 404s the dGPU path, requiring a manual swap to Nvidia's generic deb repo.

## Verifying GPU passthrough before going further Run nvidia-smi and nvcc --version. If nvidia-smi returns nothing or errors, the creator says "nothing after this will work" and tells you to stop — not loop. The fallback is the agent-install path from the earlier NemoClaw video, not retrying.

## Installing Node.js, the CLI, and the sandbox Node.js 20+ and npm 10+ are installed via the Nvidia repo. Then go nemo claw pulls the CLI from GitHub. The installer runs 22 steps; the sandbox in the demo is named box plant. You paste an Nvidia API key from build.envvidia.com (account + 2FA required) and pick a model provider — the demo uses free Neotron 3 Super 12B, though its 131K context window is "not very confident." A 5-minute container toolkit install precedes this.

## After install nemo claw box plan status should show phase ready, then nemo claw box plan connect drops you into the OpenClaw TUI. A hi prompt returning a response confirms the stack is live. Policy presets default to pip and npm only; Discord/Telegram/Slack are deliberately deferred to a future video.

Watch on YouTube

Prefer the native player? Open it on YouTube: https://www.youtube.com/watch?v=WBZU-LIduto