This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass
What I Built
🌿 WildQuest — Touch Grass. Level Up.
WildQuest is an AI-powered outdoor adventure platform that turns ordinary walks into real-world quests.
Users choose their mood — Curious, Calm, or Challenge — and their available time. An open-weight AI model generates outdoor activities that encourage them to observe nature, discover their surroundings, and spend less time scrolling.
The platform includes XP rewards, quest completion tracking, and activity streaks to make outdoor exploration more engaging.
The idea is simple: use AI to inspire people to leave their screens behind and experience the real world.
WildQuest is designed for students, nature enthusiasts, and anyone who wants to spend more time outdoors.
Demo
🌐 Live Website: https://chrxg026.github.io/WildQuest/
Explore the interface, choose your mood, generate outdoor quests, and earn XP as you complete them.
Code
💻 GitHub Repository: https://github.com/chrxg026/WildQuest
Built with HTML, CSS, and JavaScript, with browser-based AI integration.
How I Built It
I built WildQuest using:
- HTML5 — application structure.
- CSS3 — responsive UI, animations, and visual design.
- JavaScript — quest generation, interaction, XP, and progress tracking.
- Transformers.js — running AI models directly in the browser.
- SmolLM2-135M-Instruct — a lightweight, open-weight instruction-following language model.
- LocalStorage — saving progress on the user's device.
Instead of using a hosted AI API or installing Ollama, the project uses Transformers.js to run compatible AI models in the browser.
Users can select their mood and available time, and the model generates personalized outdoor quests. JavaScript then displays the quests and manages rewards and progress.
The application does not require a paid AI API key or a separate inference server. The initial model and library downloads require an internet connection.
Why Does Open Innovation Matter?
Open innovation makes WildQuest more accessible, customizable, and privacy-conscious.
Using an open-weight model allows the application to run inference on the user's device rather than depending on a proprietary, hosted AI API. This removes the need for paid API credentials and reduces dependence on external inference services.
It also gives developers greater freedom to experiment with prompts, customize quest generation, and replace the model with another compatible option.
Most importantly, it makes local AI experimentation possible with familiar web technologies and without requiring users to install Ollama.
I want to explore a different use of AI: technology that encourages people to spend less time using technology.
WildQuest is my attempt to turn open-source AI into a bridge between the digital world and the outdoors.
My Agent Session
Not available for this submission.
Prize Categories
- Open-Source AI
- Touch Grass — outdoor exploration powered by AI
🌱 WildQuest — Less scrolling. More exploring. More living.
Top comments (0)