WildQuest AI (Touch Grass): On-Device AI Scavenger Hunts That Get You Outside
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built WildQuest AI turns a short walk into a nature-discovery game. Pick a session of 3, 5, or 7 missions (roughly 5-20 minutes), and each mission asks you to find something real outside — a leaf, a flower, bark, the sky. You open your camera, photograph what you found, and an on-device AI model checks…
WildQuest AI is a nature-discovery game that transforms a brief walk into an engaging scavenger hunt. This app provides users with a short list of missions, such as spotting a leaf, a flower, bark, or the sky, and encourages them to photograph the objects they discover. Utilizing an on-device AI model, the app checks each photo to determine if it matches the target.
With no ads, scores, or accounts, the app focuses on providing a simple reason to step outside and enjoy the natural world. It is designed for individuals seeking a brief break from their screens, parents keeping children engaged during walks, or remote workers needing a few minutes of fresh air between meetings. The live app can be accessed through https://touch-grass-sepia-theta.vercel.app/.
The application is compatible with Progressive Web Apps (PWAs) and can be added to a user's home screen for offline functionality. The code is available on GitHub at https://github.com/Gautam5514/Touch-Grass. The app was developed for the DEV Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass. Screenshots feature real photos with placeholder scores from a test build, while the real model performance is validated through tests/e2e/real.spec.ts and documented in EVALUATION.md.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
