Wildhunt_AI
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built WildHunt AI is a privacy-first, open-source AI scavenger hunt that turns your phone into a guide for exploring the physical world. Instead of asking people to spend more time interacting with an AI chatbot, WildHunt gives them a reason to put the screen down, go outside, observe their…
WildHunt AI is a privacy-focused, open-source AI-powered scavenger hunt designed to encourage users to put down their phones and explore the physical world around them. The app functions as a responsive Progressive Web App, meaning it can be accessed directly through a phone's web browser without the need for a separate native application.
The core functionality of WildHunt revolves around a unique core loop: selecting a hunt, receiving a mission, going outside to find the target, capturing a photo, having the local AI verify the image against the specific mission, and finally unlocking the next discovery.
WildHunt caters to a diverse range of users, including students seeking a break from academic pursuits, developers looking to step away from their desks, families in search of simple outdoor activities, individuals exploring a new neighborhood, and anyone interested in transforming a mundane walk into an engaging adventure. The app supports various exploration styles, such as nature, urban exploration, color identification, texture analysis, observation, landmark detection, and more.
What sets WildHunt apart from other AI products is its commitment to using AI to enhance the user's connection with the physical world, rather than monopolizing their attention.
The AI behind WildHunt is not tasked with generic image classification. Instead, it evaluates the submitted photo against the specific mission assigned to the user. For instance, if the mission involves finding a naturally yellow object outdoors, the AI will verify whether the photograph truly meets the criteria set by the mission. This personalized approach ensures that the AI's role is to support and enrich the user's exploration experience, rather than serving as a mere distraction.
The application's versatility is further demonstrated through a demo video available at https://drive.google.com/file/d/17hSBEzV7f4hfPKQCj0GlNb3MraOQQwBd/view?usp=sharing. The demo illustrates the full WildHunt-AI experience, from initiating a hunt and receiving a mission to capturing a discovery and sending the image to the local vision model for verification. Once the image is verified, the user can continue the hunt, integrating the app into their daily routines seamlessly.
WildHunt AI is built using React and TypeScript technologies, with local open-weight vision AI models provided by Ollama. The project adheres to the MIT License, ensuring that users have the freedom to utilize, modify, and distribute the software according to the terms of the license.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
