This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass I built OutsideQuest, an AI-powered outdoor quest generator designed to help people spend less time in front of screens and more time exploring the real world. 🌿
Sometimes we want to go outside but don't know what to do. OutsideQuest turns that decision into an adventure by generating outdoor quests based on the user's available time and preferred difficulty.
The goal is simple: make going outside more fun and encourage people to take meaningful breaks from their screens.
OutsideQuest is built with React and Vite, with Gemma running locally through Ollama.
I built OutsideQuest using React, Vite, Gemma, and Ollama.
I chose Gemma, an open-weight AI model, to generate outdoor quests based on user preferences. Ollama runs the model locally and provides an interface for the application to send requests and receive generated responses.
The generated quests are displayed in an interactive web interface where users can track tasks, use the timer, earn points, and revisit their history.
Building this project helped me explore local AI inference and learn how to integrate an open-weight model into a practical web application.
Open innovation makes AI experimentation more accessible to developers who want to build useful applications without relying entirely on hosted, closed-model APIs.
Using Gemma through Ollama gave me the opportunity to experiment with an open-weight model and integrate it into a real application. Local inference can also reduce dependence on external AI services and give developers more control over their AI setup.
For me, OutsideQuest demonstrates how open-weight AI can be used beyond traditional chatbots to encourage real-world activities and more mindful screen time.
Thanks for checking out OutsideQuest! 🌿
What outdoor quest would you try first? I'd love to hear your ideas!