跳到正文
Hacker News (official RSS)·· 11 小時前AI 評分52

Atticus:macOS 免 API 金鑰即時語音助手,結合 Claude AI

Show HN: Atticus – Hold-to-talk voice assistant for macOS that runs on Claude -p

AI 導讀

Atticus 是一款在 macOS 上執行的即時語音助手,使用者只需按住快捷鍵說話,即可控制視窗、搜尋檔案、播放音樂,且不需額外 API 金鑰。

  1. 即時控制 開啟應用、移動視窗、搜尋檔案等操作平均 0.08 秒完成。
正文

Atticus. Your whole Mac, one sentence away.

Hold ⌃ control ⌥ option space, say what you need, let go.
Atticus moves your windows, finds your files, reads your screen and gets it done.

⚡ Fast  ·  🔑 No API key  ·  🧠 Remembers you  ·  Free and open source

  • Fast. Simple asks skip the AI: an app opens in 0.08 s. Ask for an action once and Atticus learns it, so next time it runs in a blink, with no AI and for free.
  • No API key. It runs on the Claude Pro or Max plan you already have, through Claude Code. Nothing to sign up for, no key to paste, no extra bill.
  • Remembers you. Say "remember…" and every ask after that knows it. It picks up who you are (your name, your apps) and fixes its own mistakes when you correct it.

macOS Swift Claude Cost


atticus-film.mp4

Just ask

You say Atticus
"Code on my big screen, Chrome and Terminal on the laptop." Arranges three windows across two displays.
"Open Spotify." · "Terminal on the left." Runs instantly, with no AI at all.
"Find my notes about the Tokyo trip." Searches your files by what's inside them, opens the match on your other screen.
"What's wrong with this code?" Looks at your screen and answers in a line.
"Summarize this article in three bullets." Reads the page for you.
"Reply: sounds good, see you at 7." Types it into the app you're in. It never sends.
"Play my late night coding playlist on Spotify." Plays it in a second, no clicks. Any song, artist or playlist.
"When I say focus mode, close Slack and open my to-do list." Remembers it. Next time, two words do it all.

Atticus arranging windows across two screens

Why Atticus

Fast

Opening apps and sites, moving windows, web searches and music skip the AI entirely (an app opens in 0.08 s). Actions you ask for once (opening apps, moving windows, playing music) become learned shortcuts: "Open Calculator and Chess" went from 5.5 s to 0.4 s, with no AI.

No API key

Runs on the Claude plan you already have, through claude -p. About 0.14¢ of plan usage per ask (~700 asks for $1 at API list rates). Atticus itself is free.

Remembers you

"Remember: open means bring it to the front." Saved rules go with every ask. It learns lasting facts about you (name, city, favorite apps), and when you correct it, it saves a rule so it gets it right next time. Edit all of it in Settings.

Private ears

Apple's on-device speech turns your voice into text. Audio never leaves your Mac.

Your whole Mac

Apps, windows, files, settings, the web and the screen, with Peekaboo for clicking inside any app.

Safe by default

Safe mode runs the AI's commands in Claude Code's sandbox: 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.

How the shortcut and the box work

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.

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, with Instant commands and Act while I’m talking on (Settings → Intelligence). Learned shortcuts wait for confirmed words.

Install

You need:

  • macOS 26 or later (Atticus uses Apple's new on-device speech)
  • A paid Claude plan (Pro or Max) and Claude Code. No Claude Code yet? The setup window installs it and signs you in.
  • Apple's command line tools: xcode-select --install
  • Optional: Peekaboo (see its install steps) so Atticus can click inside apps

Paste this in Terminal:

curl -fsSL https://raw.githubusercontent.com/SaarthurR/atticus-mac/main/install.sh | bash

It checks your Mac, downloads Atticus to ~/.atticus, builds ~/Applications/Atticus.app, and opens it. Atticus starts at login and updates itself from there (turn that off in Settings → About & Updates).

Working on the code instead? Clone the repo anywhere and run ./build.sh after each change.

The first launch opens a setup window. It checks your Claude plan, then asks for each macOS permission. After that, Atticus lives in the menu bar. Open it from Spotlight (⌘Space, "Atticus") for Settings: shortcut, sounds, model, speed, screen, memory and usage. If you sign out of Claude later, the setup window comes back by itself. To see it again: defaults delete com.atticus.app onboarded, then restart the app.

Test: python3 atticus.py --selftest on macOS, plus python3 -m unittest discover -s tests -v for offline regressions. After building, ~/Applications/Atticus.app/Contents/MacOS/Atticus --selftest checks native transcript matching without opening the app. Node, when installed, also checks embedded JavaScript syntax. For the UI interaction checks, run python3 -m http.server 8765 --bind 127.0.0.1 from the repo and open http://127.0.0.1:8765/tests/ui.html; it uses a mock native bridge and makes no Mac actions or AI calls.

Remove: launchctl bootout gui/$(id -u)/com.atticus.app, then delete ~/Applications/Atticus.app, ~/.atticus, ~/.config/atticus (your settings and history) and ~/Library/LaunchAgents/com.atticus.app.plist.

Watch for me

Say "tell me when Codex is done" or "watch this page until it says shipped". Atticus sets it up once, then checks every 5 seconds on your Mac with no AI, so waiting is free. When it fires you get a notification, and it runs a follow-up if you asked for one. A window must stay open on this desktop (covered is fine). Coding agents like Codex are watched through their own log, with no screen at all. Say "stop watching" to cancel.

Budget

Atticus has to stay fast and nearly free, so new features must fit under these limits:

  • Instant commands: no AI, $0.
  • AI asks: median under $0.002 and 6 s over the last 50 (Oct 10, 2026: $0.00095, 5.0 s). Check with python3 atticus.py --budget.
  • System prompt: under 10,000 characters with every option on. Every ask pays for it, and a test enforces it.
  • Anything that waits or runs in the background: $0 while it waits. AI only to set it up and to act at the end.

Usage count

Once a day, Atticus sends one random ID (made on your Mac, not tied to you) to PostHog, so I can see how many people use it. It never sends your name, your asks or your screen. Turn it off in Settings → Account & Access → Count me as a user.

Files

  • Atticus.swift: the app (hotkey, speech, overlay, onboarding window)
  • atticus.py: the brain (fast commands, system prompt, helpers for windows, web and screen)
  • ui/ui.html, ui/onboarding.html, ui/settings.html: the overlay, the welcome flow, and Settings
  • ui/AppIcon.icns: the app icon
  • ui/orbs.js: the thinking-orbs engine (MIT, Jakub Antalik)

License

MIT. See LICENSE. ui/orbs.js is from thinking-orbs, also MIT.

Contributing

Run regressions with a scratch ATTICUS_DIR and use tests/ui.html and tests/settings.html for mock-bridge UI checks. Keep personal agent settings, credentials and runtime state out of commits. Anonymous usage telemetry is disabled unless ATTICUS_POSTHOG_KEY is supplied through the environment; no key is embedded in the source.

來源:Hacker News (official RSS) · github.com