No uploading your data
All AI processing happens on-device — nothing is uploaded, so there is nothing to leak.
Offline AI Workstation · v1.0.1
Your AI workstation
No cloud required
Six AI modules running on your computer — chat, photos, documents, translation, speech, images — all fully on-device, with everything you make kept in one Library. Zero telemetry; your data never leaves the machine.
Your computerOn-device · where all the AI happens
AI ChatSmart PhotosDocument RecognitionTranslation StudioSpeech StudioImage GenerationLocal models · GPU inference
Outbound connections · only these
Model & update downloadsOne-way · never contains your content
Activate your serialOnce · about a minute
Licence status checkPeriodic · only confirms this computer's licence
Optional component downloadsOnly when you click · never contains your content
Your chats, documents, photos, recordingsNever uploaded
0 TELEMETRY · 100% ON-DEVICE · NO SUBSCRIPTION
6Integrated modulesChat / Photos / Documents / Translation / Speech / Image
0Telemetry & uploadsNo usage statistics collected
128KContext ceilingDepends on selected model
~200 MBInstallerModels download on demand
100%On-device inferenceAI works without internet
01 — New in 1.0
Six tools, now one workspace
1.0 connects what you make across the tools: easy to find, easy to carry on, and yours to take with you.
- ALibrary and handoffTranscripts, recognized text, translations, images and chats are kept in one Library; any item can be sent to another tool to carry on.
- BMeetings, from recording to minutesLive transcription (Beta) shows captions as you record, speaker separation works out who is speaking, and the insight report turns it all into a summary and action items.
- CConnect your own toolsDevices on your local network use this computer's models with an API key; AI agents can call text recognition and speech transcription directly.
02 — The Workstation
Six modules, one machine
Chat, photos, document recognition, translation, speech and image generation — one interface, one model manager, one Library, one privacy baseline.
03 — Live Feel
The AI lives in the machine in your hands
Streaming replies, thinking mode, multilingual translation — the panel here is a simulated demo; on a real machine, the GPU in your laptop does all of it, even offline.
04 — Principles
Three things we don't do
No usage statistics
Zero telemetry, no heartbeats, no trackers — in the app and on this website alike.
No monthly fees
Inference runs on your own GPU at near-zero marginal cost — no subscription, no account.
For Developers
Your GPU, for any tool
The Chat module ships OpenAI- and Anthropic-compatible APIs, lending your local compute to coding agents, editor plugins and automation scripts.
Developer? See the API →# Enter in any tool that supports a custom endpoint Base URL http://127.0.0.1:2918/v1 Model As shown on the app's API page API Key Same computer: any string
05 — Get Started
Already have your machine
Four steps from download to your first generation — most of the time is just waiting for models to download.
- STEP 01Download and installA roughly 200 MB installer; launch it and the app verifies your machine automatically.
- STEP 02Accept the termsA license agreement and privacy policy in plain language — the point is that your data stays on your computer.
- STEP 03Activate your serialEnter the serial sent to your email to bind it to this machine; it takes one connection and about a minute.
- STEP 04Download modelsPick models for the modules you want, with suggestions based on your hardware; after that it works fully offline.