# 🌿 WildHunt AI β€” Turn AI Into a Reason to Go Outside > Source: > Published: 2026-10-07 08:08:40+00:00 *This is a submission for the [Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass](https://dev.to/challenges/hacktoberfest-week1-2026-10-05)* 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 surroundings, and come back only when they have something worth showing the AI. The core loop is: Choose a Hunt ↓ Get a mission ↓ Go outside ↓ Find the target ↓ Take a photo ↓ Local AI verifies it ↓ Unlock the next discovery WildHunt supports different exploration styles such as: 🌿 Nature πŸ™οΈ Urban Explorer 🎨 Colors πŸͺ¨ Texture πŸ‘€ Observation πŸ“ Landmark Hunt The important part is that the AI isn't simply performing generic image classification. It evaluates the submitted photo against the specific mission the user was given. For example, if the mission is to find a naturally yellow object outdoors, the AI checks whether the photograph actually satisfies that mission. Most AI products compete for your attention. WildHunt uses AI to give your attention back to the physical world. Who is it for? WildHunt is designed for anyone who wants a lightweight reason to explore: -Students taking a break from studying -Developers spending too much time at their desks -Families looking for simple outdoor activities -People exploring a new neighborhood -Anyone who wants to turn a walk into a small adventure πŸŽ₯ Video Demo: [https://drive.google.com/file/d/17hSBEzV7f4hfPKQCj0GlNb3MraOQQwBd/view?usp=sharing](https://drive.google.com/file/d/17hSBEzV7f4hfPKQCj0GlNb3MraOQQwBd/view?usp=sharing) The demo shows the complete WildHunt-AI experience: 1.Starting a hunt 2.Receiving a mission 3.Capturing a discovery 4.Sending the image to the local vision model 5.Receiving mission-specific verification 6.Continuing the hunt The application runs as a responsive Progressive Web App, so it can be used directly from a phone browser without requiring a native mobile application. πŸ”— GitHub: **The screen gives you the mission. The real world gives you the answers.** **WildHunt AI** is a privacy-first outdoor scavenger-hunt PWA that uses **local open-weight vision AI** to turn real-world exploration into an interactive game. Choose a hunt. Get a mission. Go outside. Photograph your discovery. Your own machine's vision model checks whether the image satisfies the mission β€” without sending the photo to a WildHunt cloud backend. Most AI products compete for your attention. The product is intentionally designed around a simple loop: ``` Choose Hunt ↓ Receive Mission ↓ Go Outside ↓ Find Something Real ↓ Take a Photo ↓ Local Vision AI Verifies It ↓ Discovery Unlocked ↓ Next Mission ``` The screen is only the starting point. **The real world is the game board.** WildHunt is designed… WildHunt is fully open source. The repository includes the application source, AI integration, safety logic, documentation, tests, contribution guidelines, and project architecture. WildHunt is built around local open-source AI rather than a paid proprietary AI API. Tech Stack React + TypeScript Vite Progressive Web App Ollama Granite 3.2 Vision Zod IndexedDB / browser storage Browser camera APIs Vitest The application communicates with a locally running Ollama instance: WildHunt PWA β”‚ β”‚ Mission + Image β–Ό Local Ollama β”‚ β–Ό Granite 3.2 Vision β”‚ β”‚ Structured verification β–Ό WildHunt The verification response is validated using a schema similar to: { "matched": true, "confidence": 0.91, "evidence": [ "yellow flower", "outdoor vegetation" ], "explanation": "The image clearly shows a yellow flower outdoors." } The AI receives the actual mission context, so verification is based on whether the image satisfies that particular challenge. Privacy by design There is no requirement for: Paid AI APIs Cloud image storage A database server User accounts Analytics Tracking The goal is to keep the experience as local and private as possible. The architecture also keeps the AI provider behind an abstraction layer, making it possible to add other local or browser-based vision providers in the future. Open innovation is especially important for a project like WildHunt-AI because the entire idea is about changing the relationship between people and AI. A closed AI API could have made the image verification feature easier to implement, but it would also introduce dependency on a proprietary service, ongoing API costs, and potentially require sending personal photographs to an external provider. Using open-source/open-weight technology made a different architecture possible: The AI can run locally. That means a user's outdoor discoveries don't have to become somebody else's cloud dataset just to determine whether they completed a scavenger-hunt mission. It also makes the project more accessible to contributors. Developers can inspect the AI integration, experiment with different local vision models, improve verification logic, add new hunt types, and build alternative inference providers without being locked into a single commercial API. For me, open innovation isn't just about making the code public. It's about making the architecture replaceable, inspectable, and hackable. WildHunt was developed with an agent-assisted workflow, and the development process is documented through the project's agent session.