A 4-inch touch display that runs dashboards you build yourself. Every screen is a web page — HTML, CSS, a little Python — so the information you actually care about gets its own piece of glass, and you can tap it.
It listens, too. Ask it something out loud, or record a meeting and get a live transcript and a summary — in dozens of languages. Prefer buttons? The tiles double as a second keyboard for the shortcuts you run all day.
Most desk gadgets ship a fixed set of screens and leave you there. DeskProxy ships an SDK instead: every screen on the device is a tile — a mini-app written in plain HTML and CSS. Build the exact readout your work needs — your build status, your queue depth, your shop's orders, your bench sensors — and put it on glass you can reach.
Your desk already hears every call you take. DeskProxy is the only thing on it that can write them down — and then answer questions about what was said.
One press starts it, one press ends it. The full discussion is captured and kept as a note you can search later — not a 90-minute audio file you will never open again.
Words appear on the display as they're spoken, so you can see the recording is working without alt-tabbing to check. Mark a moment mid-meeting and it's flagged in the transcript.
Transcription isn't English-only. Speak the language your team actually meets in and get a transcript back in it.
When it stops, you get the decisions and action items — a summary you'd actually forward — with the full transcript underneath when you need the exact words.
"What's the weather in Berlin?" "Add dentist Friday at 3." "What's on my calendar tomorrow?" The answer comes back on the display as a card, not as a voice reading a paragraph at you.
Launch apps, switch spaces, run macros, control playback. Say it instead of finding the shortcut — and the same actions are one tap away on the glass.
Next meeting, package ETA, portfolio, now playing — ambient on your desk, not buried in tab #47.
Mute the mic, skip the track, fire the macro, start the timer. One tap on real glass beats four clicks.
The render, the deploy, the backup, the soak test. Park it on the display and stop babysitting a terminal window.
The dashboard you'd never bother opening in a browser is worth building when it's always visible and one tap deep.
These ship with the device — and every one of them was built with the same SDK you get. Nothing here is privileged.
DeskProxy's desktop app isn't a settings page — it's the brain. Configure every tile, remap every key, pick your AI, watch it all update on the device live.
Most AI gadgets route your life through their cloud and charge rent for it. DeskProxy is built the other way around.
Plug in your own Anthropic, OpenAI or Gemini key — or point it at Ollama and keep every token on your machine. You pay providers directly, at cost. No markup, no monthly AI fee.
API keys are stored in the macOS Keychain, encrypted by your OS — never in config files, never synced to us. We couldn't read them if we wanted to.
Speech-to-text runs on-device with Whisper — audio goes to your Mac, gets transcribed locally, and stops there. Prefer a cloud model for long dictation? That is a switch you flip, never the default.
Nothing to sign up for. Your calendar, stocks and habits sync straight from the sources with your own credentials — DeskProxy never sees them in transit.
Browse the store from the desktop app, tap install, it's on your device in seconds — no firmware flashing, no cables, no restarts. Community tiles land here too, so the catalogue grows faster than we could build it.
Leave your email and we'll tell you the moment it's available — pricing, availability, and first access for the people on this list. One message when it matters, nothing else. Ever.
You're on the list. Talk soon. ✓