Earth Detective: AI That Turns the Real World Into Your Investigation

Developer Vedant Shukla built Earth Detective, a browser-based outdoor investigation game that uses a locally hosted open-weight model via Ollama as an AI game master to generate environmental mysteries players solve by observing the real world. The app runs on plain HTML, CSS and JavaScript with no frontend framework, calls the local model through the Fetch API, and falls back to built-in missions when local inference is unavailable.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass https://dev.to/challenges/hacktoberfest-week1-2026-10-05 I built Earth Detective , an AI-powered outdoor investigation game designed to get people away from their screens and into the real world. Instead of spending the entire experience inside an app, players receive an environmental mystery and have to step outside to investigate it. They observe their surroundings, look for real-world clues, record their observations, and solve the case. Players can choose different investigation themes such as: The game includes missions, clues, hints, a timer, difficulty-based scoring, investigation history, and a final field report. The idea is simple: The real world becomes the dataset. AI becomes the game master. You become the investigator. The project is designed for students, curious explorers, and anyone who wants a more meaningful reason to go outside and observe the world around them. 🌐 Live Website: https://vedantshukla-cracker.github.io/Earth-Detective/ https://vedantshukla-cracker.github.io/Earth-Detective/ 💻 GitHub Repository: https://github.com/vedantshukla-cracker/Earth-Detective https://github.com/vedantshukla-cracker/Earth-Detective Earth Detective is built using: The application does not require a frontend framework such as React or Vue. The AI integration is designed around local inference using Ollama , allowing the project to work with an open-weight AI model running on the user's own machine. AI can be used to: The application also has built-in missions as a fallback, so the core experience remains usable even when local AI is unavailable. The basic architecture is: Earth Detective │ ▼ HTML + CSS + JavaScript │ │ Fetch API ▼ Ollama │ ▼ Open-Weight AI Model Open innovation makes it possible to experiment with AI without making the entire experience dependent on a closed cloud API. With local inference, the AI can run on the user's own machine, which gives the project more control over privacy, experimentation, and how the AI is integrated into the experience. It also makes the project easier to modify and extend. Developers can experiment with different open-weight models and build new investigation mechanics without redesigning the entire application around a proprietary API. For Earth Detective, this is especially important because the goal is not just to add an AI chatbot to a website. The AI is being used as a game master that creates reasons for users to interact with the physical world. Not included yet. 🌐 Website: https://vedantshukla-cracker.github.io/Earth-Detective/ https://vedantshukla-cracker.github.io/Earth-Detective/ 💻 GitHub: https://github.com/vedantshukla-cracker/Earth-Detective https://github.com/vedantshukla-cracker/Earth-Detective