Features
A desktop voice assistant that stays out of the way, keeps your speech on your machine and never lets the model run a command unchecked.
- Overlay that never steals focus
- A corner panel built on
wlr-layer-shellwith GTK4 and WebKitGTK. It floats above your windows and leaves the keyboard where it was. - Hotkey or wake word
- Push to talk with a keybinding, or turn on the always-on wake word. Conversation mode reopens the microphone when Atticus ends on a question.
- Local speech, both ways
- Recognition tuned for Brazilian Portuguese with
faster-whisper, English supported. ThePipervoice stays loaded so answers start speaking at once. - Instant commands
- Timers, alarms, reminders, volume, brightness, media, lists, Wi-Fi, Bluetooth and lock screen run locally in Portuguese and English, with no AI round trip.
- Sandboxed by default
- Model commands run inside
bubblewrap: files read-only, keys and browser profiles hidden, no network. Real changes need an Allow card.rm,sudoandgit pushnever run. - Sees and drives the desktop
- Screen reading with
grimandtesseract, web search, local file search, native click and typing, plus smart home through a Home Assistant server.
Usage
Bind one key and talk. Atticus runs as a systemd user service, so you manage it like any other.
Talk to it hotkey · wake word
Press Ctrl+Alt+Space, speak, press again to send. The answer streams into the panel and is read aloud. Close with Esc or let it fade.
$ atticus-ctl toggle
$ hyprctl reloadRun it as a service systemd user
Settings live in ~/.config/atticus/settings.json. Restart the service after editing them and follow the logs live.
$ systemctl --user status atticus
$ systemctl --user restart atticus
$ journalctl --user -u atticus -fVoice pipeline
Every request takes the same path from your voice to a spoken answer.
- Trigger A hotkey or the wake word opens the microphone.
- Transcribe faster-whisper turns speech into text, locally.
- Route Everyday commands run at once. The rest goes to the model.
- Gate Model commands pass the sandbox or wait for your Allow.
- Answer The reply streams into the overlay panel.
- Speak Piper reads it aloud in a neural voice.
Numbers
| Metric | Value |
|---|---|
| Speech languages | PT-BR / EN |
| Command safety tiers | 4 |
| Default Whisper model | small |
| Telemetry | none |
Install
Clone and build. build.sh sets up the virtual environment, downloads the Portuguese voice and starts the user service.
$ git clone https://github.com/marcostolosa/atticus-linux.git && cd atticus-linux && ./build.sh- Requires Omarchy or another Hyprland / Wayland session, and Python 3.11+.
build.shchecks the system packages and prints the exactpacmanline for anything missing.- The brain defaults to the
claudeCLI. An OpenAI or Claude-style endpoint (Ollama, LM Studio) works too. - Log out and back in once after the first install so
ydotoolcan click and type.
Links
A voice for your Linux desktop that you can read, audit and change. Star it on GitHub, file an issue, or send a pull request.