This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass 🌿 NatureQuest AI — Less Scrolling, More Exploring!
NatureQuest AI is an AI-powered outdoor adventure web app designed to encourage people to spend less time scrolling on their screens and more time exploring the real world.
The idea is simple: instead of spending free time endlessly browsing social media, users can generate fun outdoor quests and complete small activities in nature.
NatureQuest AI is designed for students, nature lovers, and anyone who wants to build healthier digital habits while reconnecting with the environment.
The goal isn't to eliminate technology. It's to use technology as a starting point for real-world experiences.
🌐 Live Website:
[https://mightybeaman95-lgtm.github.io/Naturequest-AI/](https://mightybeaman95-lgtm.github.io/Naturequest-AI/)
Try the interface, explore the quest system, and discover how gamification can make outdoor activities more engaging.
Note: The deployed GitHub Pages version is static. AI generation through the local Ollama backend requires running the backend separately.
💻 GitHub Repository:
https://github.com/mightybeaman95-lgtm/Naturequest-AI The project is built with HTML, CSS, and JavaScript, with a Node.js and Express backend for AI integration.
The repository includes the frontend interface, quest interactions, progress tracking, nature journal, and backend integration with a locally running AI model.
I built NatureQuest AI using familiar web technologies and an open-weight AI model that can run locally.
Technology stack:
The backend sends the user's selected interests, difficulty level, and location type to the locally running Qwen2.5 3B model through Ollama. The model generates a structured quest that can be displayed in the web interface.
For example, a user interested in nature photography can receive a challenge to photograph different natural patterns, while someone interested in wildlife can try observing birds from a safe distance. The application also includes demo quests as a fallback when the AI backend is unavailable.
Building this project helped me explore how open-weight models can be integrated into a practical web application instead of relying entirely on a hosted AI API.
Open innovation makes AI development more accessible, flexible, and transparent.
For NatureQuest AI, using an open-weight model through Ollama offers several advantages: A closed API can be convenient, but open-weight models make it possible to experiment with how AI runs, where it runs, and how it can be adapted.
For a project about reconnecting people with the real world, I wanted AI to be a useful tool behind the experience—not another reason to stay glued to a screen. I developed this project through an iterative AI-assisted coding workflow, from planning the features and designing the interface to implementing quest generation and local AI integration.
Agent session: Not linked yet.
Primary challenge: Touch Grass — Hacktoberfest Open-Source AI Challenge, Week 1.
The project explores local inference with an open-weight model using Ollama and Qwen2.5 3B.
Note: Additional partner prize categories should be listed only if the project meets their specific eligibility requirements.
🌍 My vision: Use AI to inspire people to explore more, notice the natural world, and spend meaningful time away from their screens.
Step outside. Complete a quest. Touch grass. 🌿