Just say “Hey Fetchi.”

Honestly: the microphone is open. With the wake word on, which is the default, every frame of audio is checked against your Fetchi's name — on your Mac, by two modules that import no network client of any kind, so none of that audio is uploaded. No audio leaves the machine until you've said the name. One exception, named here rather than buried: on the paid plans the realtime voice lane streams live audio to OpenAI while you are speaking to it, and on those plans it starts switched on. One control turns it off. If you'd rather Fetchi not listen at all, switch the wake word off and hold ctrl+option to talk instead; then it hears nothing until you press the key.

In a folder on your Mac called Fetchi Brain. Plain markdown: one page per person, project, place, preference and routine, one bullet per fact, each fact citing the day it was learned. That folder is not uploaded anywhere. The code that writes it imports no network client, and the app hands no website a way in. Open it in Finder, read it in any text editor, put it under git, delete a page you'd rather it didn't have — Fetchi re-reads the folder and never restores what you removed, and it asks before forgetting anything itself. It is not on your Desktop on purpose: the Desktop syncs to iCloud on a lot of Macs, and that would upload the whole thing; there's a shortcut there instead. What does travel is the working set — to answer a turn, a short digest of what it already knows about you rides along with your words, the same trip they make. It just isn't kept at the other end.

It works your Mac: reads the screen, takes the mouse, clicks and types. It drives a browser, writes a Gmail into an open compose window, reads Apple Mail, makes Notes and Reminders, controls Music, opens any app, pulls a YouTube video's transcript, searches the web, and checks in on you unprompted. Gmail and Google Calendar can be linked to properly if you connect the accounts. What it does not do yet: book restaurants, buy anything, place phone calls, or send texts and iMessages. None of that is built, and we'd rather say so here than let you find out after paying.

Tell it what you're trying to get done today. It holds on to those, and comes back on its own with one small next step — no prompt from you. Then it goes quiet: a clock decides when it may speak again, not the model.

Two safeguards, and they work differently. On a multi-step job, each step is checked against something observable before it's allowed to count as verified — a step that merely ran says "ran", not "done". And on any single action, Fetchi is blocked from claiming it did something unless a receipt proves the tool actually ran. That rule exists because earlier versions did tell people work was finished when it wasn't; catching it in the logs afterwards wasn't good enough. You also choose how much rope it gets: ask on everything, ask on the important stuff, or full trust.

Your wake word and speech-to-text run on your Mac. To answer you, the text of what you said goes to our server, which passes it to Anthropic's Claude and passes the answer back — and when the question is about what's on your screen, the screenshot goes with it. That server's database has no column a prompt, a transcript or a screenshot could go into: it holds your account row, the metering rows, and a push subscription if you paired a phone. It counts usage so that you don't need your own API key. We also don't log request bodies — but that half is a policy rather than a schema, and it is worth knowing which of the two you are relying on. A premium voice sends the sentence Fetchi is about to say on to a text-to-speech provider; Apple's built-in voices are synthesised on the Mac itself. Indexing — sending brain text out to be embedded — is a switch, and it ships off. The turns that drive the pointer are built to run on OpenAI's GPT-6 Astra through that same server — arriving, not shipped: the model isn't open to us yet, so today they fall back to Claude. It's all written out plainly, including the awkward parts, in the privacy policy.

When the answer is in the pixels, yes. Fetchi captures your screen and sends it along with your words to the model that answers, and we are not going to dress that up. What we can tell you is that it is not kept. On your Mac the capture is deleted in the same function that made it. On our server there is no column an image could go into. And Fetchi declines to capture at all when a password manager, a banking page or a sign-in screen is what's in front of it. On a turn with nothing visual about it no capture is taken in the first place — what goes is your words and a few hundred bytes of context. If you want that off the network altogether, the Settings switch that moves answering to a model running on your own Mac does exactly that. The window at the top of this page is drawn in HTML from the shipped window, in grey.

Lawyers, doctors, accountants — anyone holding a file they are not allowed to paste into a chat window. What Fetchi learns about the matter is markdown in your folder, not a memory in an account somewhere else. Read the list of everything that does leave your Mac before you decide it clears your bar.

Free is a trial, not a plan. No card, and inside it the app paces you at 15 agent tasks a month — but the limit that actually ends it is on our server and it happens once, not monthly: $2.50 of usage, or 14 days from the day you sign up, whichever runs out first. When it goes, the hosted side stops — the agent work and the conversation both, because Free has one allowance covering the two — and nothing comes back on the 1st. You carry on by taking a plan, or by buying top-up credit, which also lifts the deadline. The paid plans are Pro, $20 a month, with 150 agent tasks, and Max, $100 a month, with 1,000 agent tasks. An agent task is a job where Fetchi picks up a tool or takes the mouse — asking it something, or just talking to it, is not one. On Pro and Max, conversation carries on after the agent tasks are gone: talk runs to its own, further ceiling, so what stops is the hands, not the voice. Teams is that same Pro plan bought by the seat — $20 per seat, per month, on one bill, every seat a full Pro account metered against the person using it rather than drawn from a pool, and the owner sees each person's spend in dollars but never what they asked Fetchi (how a team works, including what it does not have yet). The pricing page has the whole of it, and cancelling is one button inside the app that opens Stripe's own billing page — here's exactly where it is.

Yes. Your Fetchi is yours: name it, shape how it speaks, and watch it learn how you like things done.