Control your Mac by voice with a Claude-backed assistant
Hold ⌃ control ⌥ option space, say what you need, let go. Task: Hold ⌃ control ⌥ option space, say what you need, let go. Atticus moves your windows, finds your files, reads your screen and gets it done. ☕ Leave a tip · Atticus is free; tips keep it going. 🧠 Learns as you use it · ⚡ Fast · 🔑 No API key · Free and open source Quick install Needs macOS 26 and an AI client: Claude Code on a Claude plan, Devin, Pi or a local model. Full install steps What it does Learns. Ask for something new once and it works out the steps. Ask again and it runs in a blink, with no AI. Instant commands. Opens apps, moves windows, plays music and searches the web with no AI at all. Sees your screen. Ask about anything on screen. Ask "where do I click?" and it points at the spot. Draws to explain. "Explain this and draw it" builds a labeled diagram on your screen. Dictate anywhere. Hold fn, talk, let go. Your words land in any text field, cleaned up. Hands-free. Turn on Settings → General → Wake word, then just say "Atticus" (or any wake word you pick). Keep talking after each answer; the box stays up while you work and only ✕ closes it. Background agents. Big jobs run behind your apps while you keep working. Meeting Copilot. Answers and notes during calls, saved on your Mac. Remembers you. Say "remember…" and every ask after that knows it. Your plan, no API key. Runs on Claude, Devin, Pi or a local model. Private and safe. Your voice stays on your Mac. Deletes, sends and purchases ask first. On Windows? @FindlayHi built Atticus for Windows, with integrations for Home Assistant, Jellyfin, Immich and more. Just ask Hands-free Turn on Wake word in Settings → General (off by default). The word is "Atticus" unless you type your own beside the switch. Say it, with or without "hey" first, wait for Listening…, then ask. Speech is recognized on your Mac only. After each answer it listens again quietly, with a small "Listening..." beside the timer; start talking and your words fill the bubble. Clicking other apps never closes a hands-free chat, so you can keep working while it does things for you. ✕ or Esc ends it, and a chat nobody talks to fades after about 90 seconds unless you moved or resized the box. The hotkey always takes over. While the wake word is on, macOS shows the orange mic dot. While Atticus works, the line next to ✕ minimizes the box to a small bar with its live steps. Hover and click the line to bring it back. Safe by default Safe mode runs the AI's commands in Claude Code's sandbox, so they can only write to a scratch folder. Before anything deletes, sends, buys or changes a file, Atticus asks you first. rm, sudo, disk tools and shutdown are always blocked. Every exact command is in the ask log. Apple's on-device speech turns your voice into text, and audio never leaves your Mac. Choose Hold to talk or Press to toggle in Settings → General → Shortcut behavior. Hold mode sends when you release. Toggle mode starts on the first press and sends on the second; pauses keep listening. Pressing the shortcut while Atticus answers stops it; during spoken playback it stops the voice. Esc cancels listening without sending. Toggle recordings reach a review screen after 60 seconds, rather than sending automatically. Closing the overlay or pausing Atticus stops its microphone, workers and voice. Click any answer to copy it, including earlier answers still shown in the box. Click your request to edit and ask again, or press ↑ in an empty typing box to recall the latest request. The overlay stays within your display when resized and respects Reduce Motion. While Atticus works in a covered window, another Space, or another display, a live mini screen shows that window; the steps below show the action. The finished view stays until the next ask, typing, or a click on it. Click it to open that exact window. The preview stays on your Mac, is never sent to the AI or saved, and stops streaming when the task ends. Without Screen Recording permission, the same card shows the app icon and window title. Apple's final transcript confirms each voice request before AI tools or learned shortcuts run. AI reasoning can start during a pause, but its tools wait for confirmation. If speech finalization takes too long, Atticus offers the partial text for review. Instant commands still skip the AI entirely. Supported built-in commands run mid-sentence, before you send. Learned shortcuts wait for confirmed words.; tools: Claude. Human role: The original post does not say how a person stayed involved.; limitations: Prerequisites include macOS 26, an active AI client subscription (Claude Pro/Max, Devin, Pi) or local model setup, and Accessibility permissions. Voice recognition is on-device for privacy, but AI reasoning costs depend on the chosen model plan. Safe mode restricts file writes to a scratch folder, and destructive commands (rm, sudo) are blocked. Human approval is mandatory for external actions..
Tools
Published on Agent Work Atlas:
Overview
Hold ⌃ control ⌥ option space, say what you need, let go.
Workflow
Hold ⌃ control ⌥ option space, say what you need, let go. Atticus moves your windows, finds your files, reads your screen and gets it done. ☕ Leave a tip · Atticus is free; tips keep it going. 🧠 Learns as you use it · ⚡ Fast · 🔑 No API key · Free and open source Quick install Needs macOS 26 and an AI client: Claude Code on a Claude plan, Devin, Pi or a local model. Full install steps What it does Learns. Ask for something new once and it works out the steps. Ask again and it runs in a blink, with no AI. Instant commands. Opens apps, moves windows, plays music and searches the web with no AI at all. Sees your screen. Ask about anything on screen. Ask "where do I click?" and it points at the spot. Draws to explain. "Explain this and draw it" builds a labeled diagram on your screen. Dictate anywhere. Hold fn, talk, let go. Your words land in any text field, cleaned up. Hands-free. Turn on Settings → General → Wake word, then just say "Atticus" (or any wake word you pick). Keep talking after each answer; the box stays up while you work and only ✕ closes it. Background agents. Big jobs run behind your apps while you keep working. Meeting Copilot. Answers and notes during calls, saved on your Mac. Remembers you. Say "remember…" and every ask after that knows it. Your plan, no API key. Runs on Claude, Devin, Pi or a local model. Private and safe. Your voice stays on your Mac. Deletes, sends and purchases ask first. On Windows? @FindlayHi built Atticus for Windows, with integrations for Home Assistant, Jellyfin, Immich and more. Just ask Hands-free Turn on Wake word in Settings → General (off by default). The word is "Atticus" unless you type your own beside the switch. Say it, with or without "hey" first, wait for Listening…, then ask. Speech is recognized on your Mac only. After each answer it listens again quietly, with a small "Listening..." beside the timer; start talking and your words fill the bubble. Clicking other apps never closes a hands-free chat, so you can keep working while it does things for you. ✕ or Esc ends it, and a chat nobody talks to fades after about 90 seconds unless you moved or resized the box. The hotkey always takes over. While the wake word is on, macOS shows the orange mic dot. While Atticus works, the line next to ✕ minimizes the box to a small bar with its live steps. Hover and click the line to bring it back. Safe by default Safe mode runs the AI's commands in Claude Code's sandbox, so they can only write to a scratch folder. Before anything deletes, sends, buys or changes a file, Atticus asks you first. rm, sudo, disk tools and shutdown are always blocked. Every exact command is in the ask log. Apple's on-device speech turns your voice into text, and audio never leaves your Mac. Choose Hold to talk or Press to toggle in Settings → General → Shortcut behavior. Hold mode sends when you release. Toggle mode starts on the first press and sends on the second; pauses keep listening. Pressing the shortcut while Atticus answers stops it; during spoken playback it stops the voice. Esc cancels listening without sending. Toggle recordings reach a review screen after 60 seconds, rather than sending automatically. Closing the overlay or pausing Atticus stops its microphone, workers and voice. Click any answer to copy it, including earlier answers still shown in the box. Click your request to edit and ask again, or press ↑ in an empty typing box to recall the latest request. The overlay stays within your display when resized and respects Reduce Motion. While Atticus works in a covered window, another Space, or another display, a live mini screen shows that window; the steps below show the action. The finished view stays until the next ask, typing, or a click on it. Click it to open that exact window. The preview stays on your Mac, is never sent to the AI or saved, and stops streaming when the task ends. Without Screen Recording permission, the same card shows the app icon and window title. Apple's final transcript confirms each voice request before AI tools or learned shortcuts run. AI reasoning can start during a pause, but its tools wait for confirmation. If speech finalization takes too long, Atticus offers the partial text for review. Instant commands still skip the AI entirely. Supported built-in commands run mid-sentence, before you send. Learned shortcuts wait for confirmed words.
Reported result
Actual outcomes are not reported in the source; no specific business metrics or success rates are provided. The tool claims to learn repeated commands for instant execution without AI and provides meeting notes saved locally. A measurable acceptance check would be verifying that a voice command to 'move window to left' executes instantly after being taught, and that a 'send email' request triggers a confirmation prompt before action.
Human role
The original post does not say how a person stayed involved.
Limitations
Prerequisites include macOS 26, an active AI client subscription (Claude Pro/Max, Devin, Pi) or local model setup, and Accessibility permissions. Voice recognition is on-device for privacy, but AI reasoning costs depend on the chosen model plan. Safe mode restricts file writes to a scratch folder, and destructive commands (rm, sudo) are blocked. Human approval is mandatory for external actions.
Try it
I want to test Atticus voice control on my Mac. First, verify I have macOS 26 and [replaceable: Claude Code/Devin/Pi] installed. Install Atticus via the provided script. Configure the wake word to 'Hey Mac' in Settings. Perform a dry run: say 'Hey Mac, open Safari and search for [replaceable: topic]'. Confirm the browser opens and search executes. Next, test safety: say 'Hey Mac, delete [replaceable: test file]'. Verify that Atticus asks for confirmation before deleting. Do not proceed to real file deletion or email sending without explicit human approval. Report if the voice recognition latency is under 2 seconds and if the confirmation prompt appears correctly.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.