Touch Grass Quix
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built 🌱 Touch Grass is an AI-powered real-world scavenger hunt designed to get people off their screens and exploring the world around them. The idea is simple: AI generates five random riddles describing real-world objects. Players must find those objects and upload photographs to solve the puzzles.…
Title: Touch Grass Quix: An AI-Powered Real-World Scavenger Hunt
This submission is for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass. Touch Grass is an innovative AI-powered scavenger hunt that aims to get people off their screens and engage with the world around them. The concept is straightforward: AI generates five random riddles describing real-world objects. Players must locate those objects and submit photographs to solve the puzzles.
Each puzzle earns the player 1 point, with a maximum score of 5 points. Players can request hints without losing points or reveal answers prematurely, but doing so results in zero points for that particular puzzle.
The goal of Touch Grass is to transform a simple walk around campus, a park, or a neighborhood into a captivating AI-powered adventure. The demo video can be accessed at https://youtu.be/65kJiwxRiXQ, and the source code is available on GitHub at https://github.com/aanoop234/Hacktober-fest-week-1-challenge.
In terms of technology, Touch Grass is built using open-weight AI and modern web technologies. Gemma 3 4B is employed for generating riddles and validating image-based answers. Ollama is utilized to run the AI model locally, eliminating the need for paid AI APIs. The project is developed using React + Vite for a responsive, installable Progressive Web App, and Node.js + Express for game logic, photo uploads, AI integration, and score management.
Open innovation plays a crucial role in this project. By utilizing an open-weight model with Ollama, Touch Grass can explore local AI inference without relying on paid, proprietary AI APIs. This approach provides greater control over AI requests, allowing for experimentation on ordinary hardware. For Touch Grass, open innovation means the ability to explore how AI can be integrated into everyday experiences while gaining insight into prompt engineering, image understanding, structured outputs, and the limitations of local AI models.
The prize categories for this challenge are Best Use of Gemma, which is used to generate puzzles and verify answers.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.