Open Laboratory Docs

Run Laboratory OS through managed Uplink, a self-hosted Uplink edge, or Tailscale.

Understand how Open Laboratory's container, persistence, tunnels, subdomains, and security model fit together.

Install Docker, NVIDIA drivers, and the NVIDIA Container Toolkit on a Linux machine.

Docker run reference for managed Uplink, self-hosted Uplink, and Tailscale access.

Build a text-to-video pipeline using Wan 2.2 inside a ComfyUI workflow — from model install to first render.

Deploy a production-grade OpenAI-compatible endpoint serving Qwen3 at full GPU throughput — no token costs, no rate limits.

Run OpenCode inside a sandboxed Laboratory desktop — full filesystem access, terminal, and live supervision from your browser.

Generate your first AI image using ComfyUI on Open Laboratory.

Run a local language model and chat with it using Open WebUI.

Frequently asked questions about Open Laboratory.

How Open Laboratory handles state across container restarts, and how to bind mount a volume for durable storage.

How Laboratory OS protects your desktop, apps, and data in practice.

Choose between a GPU virtual machine and a managed container platform for Laboratory OS.

Run Laboratory OS on a Linux GPU VM from any cloud provider.

Run Laboratory OS on a GPU platform that accepts custom Docker images.