This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass
🌿 WildQuest AI — Touch Grass, Powered by Open-Source AI
What I Built
WildQuest AI is an AI-powered outdoor adventure generator designed to turn ordinary walks into fun, meaningful nature explorations.
In a world where we spend so much time staring at screens, I wanted to build something that uses AI to encourage people to step outside and reconnect with the real world.
WildQuest AI generates personalized nature quests based on your location, available time, difficulty level, and interests. Whether you're visiting a park, walking around your neighborhood, or exploring your campus, it gives you small challenges that make the outdoors more interesting.
Some examples include:
- 🌱 Discovering different leaf shapes and natural patterns.
- 🐦 Listening carefully to birds and other outdoor sounds.
- ☁️ Observing clouds, the sky, and changes in the environment.
- 🚶 Completing mindful walking and movement challenges.
- 🔎 Noticing small details that we usually overlook.
Users can complete quests, track their progress, and turn an ordinary walk into a mini adventure.
The idea is simple: instead of using AI to keep people on their screens, use AI to give them a reason to leave them behind.
WildQuest AI is built for students, nature lovers, curious explorers, and anyone who wants to make spending time outdoors more engaging.
Demo
🌐 Live Website: https://abhiishh007-blip.github.io/WildQuest/
Explore the interface and see what WildQuest AI is about!
GitHub Repository: https://github.com/abhiishh007-blip/WildQuest
Code
Check out the complete source code and explore the project on GitHub:
🔗 https://github.com/abhiishh007-blip/WildQuest
The project uses a simple web stack with HTML, CSS, and JavaScript for the frontend, alongside Node.js and Express for the backend and AI integration.
The codebase is designed to be easy to understand, modify, and extend.
How I Built It
I built WildQuest AI using HTML, CSS, JavaScript, Node.js, Express, and Ollama, with the goal of making open-weight AI useful beyond a conventional chatbot.
The project uses the qwen2.5:3b model through Ollama for local AI inference.
Here's how it works:
- User input: The user selects a location, adventure duration, difficulty level, and preferred activities.
- Backend processing: A Node.js and Express server validates the preferences and constructs a prompt.
- Local AI inference: Ollama runs the language model locally to generate personalized outdoor quests.
- Structured output: The backend processes the model's response into quest data.
- Interactive experience: The frontend displays the quests and lets users track their progress as they complete them outdoors.
Technology Stack
- HTML5 — Page structure.
- CSS3 — Responsive styling and visual design.
- JavaScript — User interactions, quest rendering, and progress tracking.
- Node.js and Express — Backend and API routes.
- Ollama — Local model runtime.
- Qwen2.5 3B — Open-weight language model used for quest generation.
- localStorage — Preserving supported progress in the browser.
One of the most interesting parts of this project was connecting a local language model to a practical application. Instead of generating content for users to consume endlessly on a screen, the AI generates activities that encourage real-world exploration.
Why Does Open Innovation Matter?
Open innovation matters because AI should not be limited to applications that depend on closed, paid APIs.
By using an open-weight model through Ollama, WildQuest AI demonstrates how developers can build AI-powered experiences while maintaining more control over their technology stack.
This approach makes experimentation more accessible and gives developers the freedom to customize prompts, explore different models, and adapt the project to their needs.
It also offers several practical benefits:
- Local inference: The default AI workflow runs on the user's own machine.
- Less dependence on hosted AI services: Quest generation does not require a third-party cloud inference API.
- Privacy-conscious architecture: User preferences can be processed locally without sending them to a hosted AI provider through the default generation flow.
- Customization: Developers can experiment with different compatible models and improve the quest-generation experience.
- Community collaboration: Anyone can inspect the code, suggest improvements, and contribute new ideas.
Open innovation also makes it easier for students and independent developers to experiment with AI without having to build everything from scratch.
For me, this project is an example of how open-source AI can power something small but meaningful: helping people rediscover the world around them.
My Agent Session
I don't have a DevRelay session link to share for this submission.
Prize Categories
My primary focus is the Open-Source AI challenge: using an open-weight model and local inference to build a practical application.
Final Thoughts
WildQuest AI started with a simple question:
What if AI could help us spend less time looking at screens and more time experiencing the world?
This project is my attempt to explore that idea.
I'm excited to keep improving it, experiment with more open models, and make outdoor exploration more engaging through technology.
🌿 Touch grass. Notice more. Explore differently.
Thanks for checking out WildQuest AI!
Top comments (0)