Native macOS · Apple notarized

True automation
for your Mac.

Tonttu gives AI agents structured control over your macOS apps and browser — using the UI itself, not just screenshots. Faster execution, fewer tokens, better results.

Download for macOS$39 · Lifetime license
Structured first
Screenshots only as fallback
3x fewer tokens
Per automated task
Any agent
Claude, GPT, Gemini, OpenClaw
tonttu

Demo coming soon

Scroll

Approach

Most agents screenshot everything.
Tonttu reads the UI.

Most computer-use agents screenshot your display for every single action — burning thousands of vision tokens each time. Tonttu takes a smarter approach: it reads the actual UI structure first and exposes named actions your agent can call directly. Screenshots are there when needed, but most tasks never require them.

Screenshot-based agents

  • Screenshot → send image → receive coordinates → click → repeat
  • Thousands of vision tokens per action
  • Slow — full image round-trip each step
  • Fragile — pixel coordinates break on resize

Tonttu

  • Reads UI structure → exposes named tool calls
  • Structured text — a fraction of the token cost
  • Fast — no images to encode, send, or decode
  • Resilient — semantic actions, not pixel coordinates

You don't need Claude Max for this

Mac automation shouldn't
require a subscription.

Claude Dispatch gives you computer control inside Cowork — but it's Claude-only, requires a Pro or Max plan, and relies on screenshots for every action. Tonttu works with any AI you already use, reads the UI structure first, and costs $39 once.

If you're already on a Max plan, Tonttu still saves you tokens on every task — structured tool calls instead of vision-heavy screenshot loops.

01

Works with any AI

Claude, GPT, Gemini, OpenClaw, local models — not locked to one provider.

02

No screenshot overhead

Structured text instead of vision tokens. Same task, fraction of the cost.

03

$39 once — no plan required

Bring whatever AI subscription you already have. Tonttu is the bridge.

Works with OpenClaw

Already running OpenClaw?
Plug in Tonttu.

OpenClaw agents gain structured access to every macOS app and browser on your machine — through named tool calls instead of relying on screenshots alone. Your existing skills and workflows stay the same. Tonttu just makes them faster and cheaper to run.

  • Drop-in — connects as a standard tool provider
  • Your agent calls named actions, not pixel coordinates
  • Cuts token usage per task by 3x or more
Without Tonttu

agent → screenshot display

agent → encode & send image to LLM

agent → receive coordinates

agent → click (x: 482, y: 316)

agent → screenshot again…

With Tonttu

agent → click_submit_button

agent → fill_email("value": "...")

Demo recording

Ship a product demo
without recording one.

Describe what you want to show. Your AI walks through your product, performs every action live, and narrates each step with text-to-speech. You get an MP4 — ready to share on your landing page, pitch deck, or docs site. No screen recording, no editing, no retakes.

Describe, don't perform

Tell your AI what to demonstrate. It navigates your app, clicks the right things, and shows the flow end to end.

Narrated with TTS

Every step is narrated with natural text-to-speech. Choose the persona and tone — sales pitch, tutorial, QA walkthrough.

Export as MP4

Get a polished video file. Drop it into your site, share it with investors, or post it — no editing software needed.

tonttu — demo recordingRecording

Sample recording coming soon

Capabilities

Everything in one native app.

Full macOS app control

Any native app — spreadsheets, email, dev tools, design software. Your AI interacts through the accessibility layer.

Browser automation

Any website, any page. No extensions to install. Works through content security policies that block other tools.

Narrated demo recording

AI-driven product walkthroughs with text-to-speech narration. Export MP4 directly.

Flow recording & replay

Record a sequence of actions. Replay it on demand. Reusable workflows without writing scripts.

Works with any AI

Claude, ChatGPT, Gemini, OpenClaw, local models — any agent that supports tool calls.

Private by design

No telemetry. Everything runs locally on your Mac. Apple notarized and signed.

Pricing

Pay once. Keep forever.

The $39 pays for itself in saved tokens within a week.

$39

One-time payment · Lifetime license

  • Full macOS and browser automation
  • Narrated demo recording with TTS
  • Flow recording and replay
  • Works with any AI agent or framework
  • Dramatically lower token costs per task
  • Free updates for life
Buy LicenseDownload free trial (14 days)

Requires macOS 14+ · Apple Silicon & Intel