Gesture, voice, and AI control for macOS.
↓ Scroll to exploreJust your Mac's webcam. No special hardware.
Right hand pinch — move your hand to drag the cursor anywhere on screen.
Quick left pinch for click. Hold for 1 second for right-click.
Draw a circle while pinching — captures that region to your clipboard instantly.
Open hand flick in any direction — up, down, left, right arrow keys.
Hold a fist to activate speech-to-text. Say "press enter" or just dictate.
Hold both fists — ask Claude anything. Gets spoken back to you.
Left pinch, right fist. Move to scroll. Accelerates the longer you hold.
Hold the shaka — deletes characters, then words, then lines. Both hands 🤙🤙 = delete lines → select all.
Both hands pinching — drag and drop files, select text, anything.
Say commands to trigger actions instead of typing. Dictation supports multiple languages.
click · right click · command click
press enter · press delete · press tab · press escape · press up/down/left/right
command z · control c · shift left · option delete · command shift z
Clone, build, run. No accounts needed.
git clone https://github.com/TomYang-TZ/Gstrl.git
cd Gstrl
make install
make runRequires macOS 14+, a webcam, and Swift 5.9+. Permissions auto-prompt on first launch. Claude Code CLI optional for AI agent.
All processing on-device. Zero latency. Zero cloud.
AVCaptureSession at 30fps (configurable to 120fps) feeds frames to Apple Vision.
VNDetectHumanHandPoseRequest identifies 21 joints per hand, every frame.
Pinch detection, velocity-based swipes, and combo tracking turn poses into CGEvents.
Hold a fist to activate speech. Dictate text or say "press enter", "command z", "click" to trigger actions. Dictation supports multiple languages.