Grass Quest
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built Grass Quest is a photo scavenger hunt where the game master is a local AI. You press one button and get a mission, like "find a leaf with a hole in it" or "three different shades of green in one frame." Then the phone goes in your pocket and you go look for it. When you find it, you take one…
Grass Quest is a photo scavenger hunt game designed for individuals to engage with their surroundings while avoiding the distraction of staring at their phones. The game utilizes an AI, specifically a local Gemma model through a platform called Ollama, to generate missions and judge photos taken by the user. The user initiates the game by pressing a button to receive a mission, such as finding a leaf with a hole or capturing three distinct shades of green in a single frame.
Once the user locates the item, they take a photograph and submit it, where the same model evaluates the image and determines if it meets the mission's criteria. The user interface is simple, featuring a difficulty selector, a mission button, a photo uploader or camera option, and a judge button. The missions are randomly generated and assigned high temperature to ensure variety.
The app filters out any unsafe, illegal, or invasive content. Upon submission, the photo is resized to fit the model's requirements, sent to the AI for assessment, and the model returns a verdict along with what it perceived and a brief comment. The entire process is local, meaning no photos are uploaded to external servers and each use is free of charge.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
