LU Labs
All-in-one local AI studio·Chat · Code · Image · Video
LU Labs Desktop App
MACOS · WINDOWS · LINUX · FREE
One app · four studios
Four studios. One window.
Zero cloud.
Chat, code, image and video generation. LU Labs detects your stack and runs every studio locally.
Write a launch tweet
On it. Here are three angles that hook on privacy…
ChatText
Private chat with any local model you load, no cloud in the loop. Thinking mode, RAG and voice.
export run() {
+ await model.load()
+ return stream(ctx)
}
● 2 edits · tests passing
CodeCodex
A coding agent with real tools, editing and running your files on device.
ImageComfyUI
Generate full resolution images on your own GPU. FLUX.1 and any checkpoint.
LIVE
VideoLive
Turn prompts into video on your own hardware. No render queue, no limits.
Private by design
Nothing is ever sent automatically.
ON-DEVICE
Runs 100% on your machine
Every token, pixel and frame is generated by your own hardware. The cloud is never in the loop.
NO TELEMETRY
Zero data collection
No accounts required to run local. No analytics, no phone-home, no API keys to leak.
AUTO-CLEANUP
Processes die with the app
The ComfyUI process is auto-killed on close. Your chats survive restarts, on disk, with you.
Works with the runtimes you already have
OllamaLM StudiovLLMllama.cppComfyUItext-gen-webui
Simple pricing
Free forever self-hosted. Or let us run the GPUs.
Run your first local model in minutes.
Download the LU Labs desktop app, point it at your hardware, and start generating. Private, free, and yours.