Touch Grass AI: Offline AI That Turns Screen Time into Real-World Missions
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built Touch Grass AI is an offline-first application designed to help people step away from their screens and engage with the real world. Instead of recommending more content to consume, it generates personalized outdoor missions based on the user's mood, available time, energy level, budget, and…
Title: Touch Grass AI: Offline AI That Turns Screen Time into Real-World Missions
Touch Grass AI is an innovative offline-first application created for the Hacktoberfest Open-Source AI Challenge Week 1. Its primary mission is to help users step away from their screens and engage in real-world activities instead of consuming more digital content.
Instead of merely suggesting more content, Touch Grass AI generates personalized outdoor missions tailored to the user's mood, available time, energy level, budget, and surroundings. For instance, a user could input: "I'm bored, have 30 minutes, and don't want to spend any money." Based on this input, the AI could produce a mission like Mini Explorer, which would prompt the user to explore a nearby safe area, discover various leaf types, and observe details they typically neglect.
The core objective of Touch Grass AI remains consistent: utilize AI to promote real-world experiences rather than extending screen time. Although a demo is yet to be released, the application will eventually include a screen recording or live demonstration once it is functioning. The code behind this project is set to be accessible via a soon-to-be-opened GitHub repository.
The development of this application relies on Python for application logic, Streamlit for the user interface, Ollama for local model inference, and Gemma, an open-weight language model, which aids in creating personalized missions. The application is designed to execute AI inference locally, thereby eliminating the need for a paid cloud AI API. This approach allows the mission-generation process to convert user preferences into viable, time-limited outdoor activities.
The significance of open innovation is underscored by the ability to make AI more accessible. By employing open-weight models, local inference, and customizable tools, developers can experiment with AI more independently. This project demonstrates that technology doesn't always have to keep us tethered to our screens. Instead, it can facilitate our disconnection and encourage engagement with the world around us.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.