your cursor has a home — visit the top of the page
Live demo on this page — no install

Talk. It works. You watch.

Co-Agent is a voice-first AI that lives on your computer — Mac or Windows — and brings its own. Hold a key, say the thing, and watch it happen on your screen or on its private cloud desktop.

Signed & notarized · macOS 13+ · Windows finishing beta

Agent Computer
⤢ Expand⇩ Paste⇧ Copy
Co-Agent cloud desktop
Powering on your computer…
right here
“open google up there”

Don’t take our word for it.
Try it, right here.

These are not videos. The voice below is the real engine that ships in the app, and the computer is a real cloud desktop minted for you when you press the button.

demo

🖥 One real computer. Your voice drives it. live

Press start and a REAL disposable cloud desktop is created for you — then hold the talk button and boss it around. It points, it opens sites, you watch it happen on the machine below.

🖥️

A real Linux desktop, born when you click, wiped three minutes later. Nothing here is a video.

One Co-Agent. Two computers.

Yours — where it points, guides, and drafts. And its own — where it does the messy work without touching your stuff.

🎙

Push-to-talk voice

Hold a chord, ask anything about what's on your screen. It answers out loud in seconds and points at the exact pixel it means — “it's right here.”

🖥

Its own computer

A private cloud desktop that boots on demand and sleeps when idle. Your agent browses, downloads, installs, and works there — you watch live in a floating window.

🧭

Shows you — or does it

“Show me how” walks you click-by-click with on-screen arrows. “Take me there” clicks for you, step by step, stopping the instant you touch the mouse.

🎬

Workflow recorder

Do the task once while it records. Every click becomes a step; out comes an SOP document and an agent-readable file — your process, captured and repeatable.

🤝

Your real agent underneath

Heavy work is handed to YOUR agent — Hermes, Claude Code, Codex, whatever you run. Co-Agent is the voice and hands; your agent is the brain that knows your business.

✏️

Circle it. Say “this one.”

Draw on your screen while you talk — the marked-up screenshot goes straight to your agent with your words. “Fix this part” finally means something to a machine.

🛡️

Blind Private Relay

Voice reaches Google through our relay, so Google never sees your IP or location — and the relay can't read the encrypted stream. No single company holds both who-you-are and what-you-said. On by default.

Watch it actually work.

Six moments from a normal day with Co-Agent. They play themselves — or click around.

Built shy by design.

An assistant on your computer should be deaf and blind until you say otherwise. So it is.

🔇
Hears only while you hold the keys.Push-to-talk is physical: release the chord and the microphone lane is closed. No wake words, no always-listening.
👁
Sees one screenshot per question.Your screen is captured when you ask about it — not continuously. Silence sends nothing.
🔒
Voice is processed by Google's Gemini — never readable by us. Held-button audio and that turn's screenshot are encrypted end-to-end to Google's paid Gemini API (not used for training, per Google's terms). Our server only mints a single-use token that expires in minutes; it never sees your content.
🛡️
Blind Private Relay — nobody holds both halves. On by default, your voice reaches Google through our relay, so Google sees our server's address, not yours or your location. The relay only forwards encrypted bytes it can't read. We know who you are but never what you said; Google processes what you said but never learns who or where you are. (One toggle turns it off for a hair less latency.)
🏠
Your agent stays yours.Task handoffs run on YOUR agent on YOUR machine. Business context, files, memory — none of it routes through us.
🗑
The cloud computer is disposable.It's wiped minutes after you stop using it. Nothing persists unless you save it somewhere yourself.
Clicking your computer needs your approval.Real input on your machine pops an Allow/Deny card, every time, with a plain-English reason. Every action is receipted.

What we collect: your email address. That's the list. No trackers, no analytics, no ad pixels — on this site or in the app — and we never sell or share data, period. Emails are used for your account and occasional offers from us, with a working unsubscribe. Read the whole thing in plain English: the one-page privacy policy.

This demo page: holding the talk button streams your voice to our server and on to Google's Gemini Live API to generate the reply; release the button and the stream stops. Drawing on the page can also turn the microphone on (with your browser's permission and a clear on-screen indicator) so you can talk while you circle things — press Esc and it's off. We don't store demo audio. Demo computers are deleted automatically after three minutes.

Simple prices. Serious coworker.

Voice included on every subscription. No metering anxiety — typical daily use costs us pennies, so we don't nickel-and-dime you.

Co-Agent

$15/mo
  • Voice with pointing & guidance
  • Workflow recorder → SOPs
  • On-device dictation, free forever
  • Bring your own agent (Hermes, Claude, Codex)
  • Hosted Agent Computer
Get started
MOST POPULAR

Co-Agent + Computer

$30/mo
  • Everything in Co-Agent
  • Private hosted Agent Computer
  • Boots in seconds, sleeps when idle
  • Your agent drives it — you watch live
  • Copy/paste bridge both directions
Get started

Lifetime

$100 once
  • Own the app forever
  • Voice on your own Gemini key (free tier works)
  • One year of updates included
  • $50/yr for updates after
  • Hosted computer (add-on available)
Get started

Questions.

What do I need to run it?

Mac and Windows. One signed download, no terminal, no setup scripts. macOS 13+ today; the Windows build is finishing beta — join the list and you'll get it first.

What AI powers the voice?

Google's Gemini Live models power speech understanding and the voice itself. Subscriptions include voice through our pooled keys with per-session single-use tokens; lifetime licenses run on your own free Gemini key. Heavy tasks run on your own agent — Hermes, Claude Code, or Codex.

Can it click things on my computer?

Only with your approval. Any real input on your machine raises an Allow/Deny card stating exactly what it wants to do, and every executed action is recorded in a local receipt you can audit.

What exactly is the Agent Computer?

A private Linux cloud desktop that exists when you need it. Your agent can browse, download files, install apps, and run long jobs there instead of on your machine. It boots in seconds from a warm pool, sleeps when you're not using it, and its files are disposable by design.

Is my data used for training?

We don't train anything on your data, and voice turns are processed through Google's paid Gemini API. We keep operational metering (token counts), not your content.