Questions, answered.

A privacy-first desktop app for local AI. It runs local chat, a coding agent, and image & video generation entirely on your own machine — plus optional hosted plans if you would rather not manage a GPU.

In local mode there is no external content filter sitting between you and the model. The model you load defines its own behaviour; nothing is silently blocked or logged by a cloud service.

Anything your local backend supports — LU Labs auto-detects 12 runtimes including Ollama, LM Studio, vLLM and llama.cpp, and drives ComfyUI for images and video.

In local mode, no — not prompts, files, images or telemetry. Nothing is ever sent automatically. Hosted plans obviously process on our GPUs, but only the request you explicitly send.

No phone-home, no analytics SDK, no crash pings on local mode. The code is open source, so you can verify this yourself.

The ComfyUI process is auto-killed when you close the app, so nothing keeps running or listening after you quit. Your chats are stored on your own disk and survive restarts.

Yes. Self-hosting is free forever and open source. You only pay if you choose a hosted plan so we run the GPUs for you.

Both. Yearly billing gives you two months free versus paying monthly. You can switch or cancel at any time from your account.

Hosted plans include a 14-day money-back guarantee. Cancel anytime and you keep access until the end of the period.

Convenience and hardware. Hosted plans need no GPU, no setup and no maintenance — the same studios, running on our machines, in your browser.

Same open models and studios. Higher tiers unlock larger models, longer context, higher quotas and priority GPU queues.

Anytime. There is no lock-in — export your work and self-host, or start hosted and drop to local whenever you like.