GrassLock: An In-Browser Open-Weight AI that Forces You to Touch Grass

Description and use

GrassLock forces users to step outside and show a nature object to unlock the app, ensuring brief screen‑time breaks while keeping data local.

Problem

Users spend excessive screen time without outdoor breaks.

Outcome

GrassLock enforces brief outdoor breaks by requiring users to show a nature object to the camera before accessing app content, preserving privacy and eliminating server costs.

Workflow

• Open GrassLock in browser on phone or laptop
• App blocks access to reward states
• User walks outside and points camera at grass, houseplant, or tree
• TensorFlow.js MobileNet classifies live camera frame
• If classification contains botanical keywords, lock clears
• App records completion of outdoor break

Evidence

The camera feed never leaves the user's device. No image frames or GPS coordinates are sent to an external server.

Source

Running open‑source weights locally means zero server bills, zero token pricing, and no dependency on paid API keys.

Source

Because inference executes client‑side using WebGL, users can load the web app and head out into trails or remote parks without needing high‑speed mobile data.

Source