Bringing in the OutsideQuest
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built OutsideQuest is a one-button, 70s-arcade-style desktop game that pushes you away from the screen and into the real world. Press NEW MISSION, and it checks the live weather outside; then a local LLM writes a short, safe photo mission to suit the conditions, like "Find three different shades of…
OutsideQuest is a desktop game designed to encourage users to step away from their screens and explore the real world. With just one button, players receive a weather-aware mission generated by a local language model based on the current weather conditions. They then take a photo with their webcam and submit it for judgment by a local vision model, which either approves with a witty reaction or rejects the shot. Users earn a daily streak for completing missions and strive to reach new heights.
The game utilizes open-weight models through local inference with Ollama, eliminating the need for API keys or cloud calls. Mission generation and photo judging are performed locally, with no network calls beyond the weather lookup. This open innovation approach allows users to run the game without incurring any costs or concerns about data privacy.
With its 70s-arcade-style visuals, including amber and phosphor-green text, Atari-style stripes, and a typewriter output, OutsideQuest offers a nostalgic gaming experience that seamlessly blends into modern technology. The resizable window and full-screen option further enhance the user experience, making it accessible and enjoyable on various devices.
The project demonstrates the power of open innovation, as it harnesses the potential of locally running AI models to create a game that respects user privacy and eliminates the need for costly subscriptions or cloud services. By providing a simple, engaging, and locally-driven gaming experience, OutsideQuest aims to inspire users to disconnect from their digital lives and reconnect with the world around them.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.