Setup

Set up MailTwin in 90 seconds

Three steps. Then you're writing email in your voice.

1. Install

Download MailTwin.dmg.
Open the disk image. Drag MailTwin into Applications.
Open MailTwin from the Applications folder. The menubar will get a new ✉️ icon.

macOS will probably ask "are you sure you want to open this?" the first time. That's the standard "downloaded from the internet" warning — MailTwin is signed and notarized by Apple, so you're good. Click Open.

2. Pick your AI

On a recent Apple Silicon Mac (M1 or newer, macOS 15.1+), MailTwin will pre-select Apple Intelligence for you. It runs entirely on-device, costs nothing, and needs zero setup. Just hit Continue.

Want a more powerful model? Pick Claude, ChatGPT, Gemini, or any of the other six providers, paste your API key, and you're set. Not sure which to pick? Read the provider guide — three sentences will tell you.

3. Grant two permissions

macOS asks twice, because Mail and the system keyboard live in separate sandboxes:

Automation → Mail. Lets MailTwin read the email you have selected and open replies on your behalf.
Accessibility. Lets MailTwin paste a generated reply into Mail's compose window. (Without it, the reply still lands on your clipboard — you'll just need ⌘V to drop it in.)

Click Grant in onboarding and macOS will pop the right pane for each. Toggle MailTwin on, return to onboarding, and you're done.

That's it

Open Mail, click any message, hit ⌘⇧A from anywhere, pick Reply (my style). MailTwin reads what you typed last week, drafts a reply in the same voice, and streams it into the compose window. Tweak it like any other draft, hit Send.

Stuck somewhere?

Onboarding has a built-in self-test that catches the most common speed bumps (Mail not running, permissions not granted, no message selected). If you're past onboarding and something's broken, open Settings → Setup → Generate diagnostics report and email the result to [email protected]. We usually reply within a day, often the same hour.