🌱 GO. — An AI That Wants You to Stop Using It | Touch Grass Challenge
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass I Built an AI That Wants You to Put Your Phone Away 🌱 What I Built GO. — AI for Leaving the Screen is a small web app built around a simple idea: Ask AI. Then leave. Most AI tools are designed to keep us on screens longer. GO. tries to do the opposite. The user chooses a vibe, duration, company, and place ,…
This submission is for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass. The app, called GO., is an AI that encourages users to put their phones away and engage in offline activities. The AI asks the user to choose a vibe, duration, company, and place, then generates a short offline mission designed to get them away from their device and into the real world.
Examples include taking a walk, exploring a nearby area, doing a creative activity without a phone, talking to someone, or spending 20 minutes outside without checking a screen. After generating a mission, GO. starts a countdown and prompts the user to put their phone away.
The project is built with HTML, CSS, and JavaScript on the frontend, and uses local/open AI rather than relying on a proprietary AI API. The architecture includes a browser, local backend, Ollama, an open-weight model, and offline mission generation. The AI receives information about the user's selected activity, available time, whether they are alone or with others, preferred location, and optional constraints. It then generates a short, practical mission aimed at encouraging the user to stop using their device.
The frontend also features a responsive UI, mission generation for multiple activity categories, countdown before leaving the screen, mission completion, and local mission history using localStorage. There is a safety guide requiring no account to use the app. The AI is only the starting point, with the experience intended to end by encouraging the user to stop interacting with the application.
The project emphasizes open innovation, allowing the AI to operate outside a closed ecosystem. With open-weight models and local inference, the mission-generation system can run directly on the user's own computer, enabling developers to inspect AI usage, experiment with different models, modify prompts, run inference locally, build new mission-generation strategies, and contribute improvements without relying entirely on a proprietary API.
This approach aligns with the project's philosophy of treating AI as a tool, not another attention-capturing platform.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
