jev-use
macOS voice and typed computer-use app where Jev picks the next on-screen action from the Accessibility tree, with no screenshots.
Overview
jev-use (savka777) is a macOS app for computer use by voice or typing. You say what you want, Jev picks the next on-screen action, and macOS performs it. The app reads the screen through the Accessibility tree rather than screenshots. It is built with Xcode and has no third-party dependencies; the TypeSafe key is stored in the Keychain, and setup asks for Accessibility, microphone and speech permissions.
Interaction options include holding a configurable shortcut (Control-Option-Space by default) to speak, typing into a widget, calling a shell script, a hands-free mode that submits after about 1.5 seconds of silence and pauses the microphone while executing, and an optional Hey Jev wake phrase that listens in the background. Escape cancels. The README notes Apple Speech may process audio online. It targets macOS 14.2+ and is MIT licensed.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which on-screen action and element should be performed next to fulfil the command?(inferred) | — |
How it works
- User speaks or types a command
- App reads the Accessibility tree
- Jev picks the next action
- macOS performs it; repeat until done
Strengths
- No screenshots needed
- Key stored in the Keychain
- Several hands-free interaction modes
Caveats
- Apple Speech may process audio online
- No evaluation of task success reported
- macOS only
Getting started
bash build.sh && open "$HOME/Applications/Desktop Voice.app" (macOS 14.2+ with Xcode).At a glance
- Type
- App
- Status
- prototype
- Language
- Swift
- Runtime
- macOS app
- Has code
- yes
- License
- MIT
Use cases and integrations
How curated lists describe it
Voice and typed computer use for macOS. You say what you want. Jev picks the next on-screen action. macOS performs it. No screenshots: the app reads the screen through the Accessibility tree.
logicrw/awesome-jev-projectsmacOS computer use by voice or typing that reads the screen through the Accessibility tree rather than screenshots. Key stored in the Keychain.
MrJev/awesome-jev
Frequently asked questions
Does it take screenshots?
No. It reads the screen through the macOS Accessibility tree.
How do I trigger it?
Hold the voice shortcut, type in the widget, use hands-free mode or say Hey Jev if enabled.
Where is the API key stored?
In the macOS Keychain.
Related projects
macOS menu-bar Swift app that turns on-device transcribed speech into Jev typed decisions and macOS actions, confirming hard-to-undo steps.
AppbetaSwiftVoice assistant daemon for Hyprland Linux desktops that acts through tool modules, with Jev gating which requests and actions proceed.
ProjectbetaPythonTalk to your Mac: local whisper.cpp transcribes, one Jev request picks the action and typed arguments, and code executes macOS automation.
ProjectprototypePythonFloating macOS bar for voice or text commands where Jev picks the next action from live accessibility controls in a loop.
ProjectprototypeSwiftPre-alpha Rust and Tauri voice control layer for macOS that reads the accessibility tree; Jev is a fallback rather than the router.
ProjectprototypeRustElectron app for controlling Windows 10/11 by Turkish or English speech, using OpenAI Realtime, Jev decisions, UI Automation and Playwright.
ProjectprototypeTypeScript