🌿 TouchGrass AI: I Built a Local AI That Encourages People to Go Outside
What if AI could help us spend less time on our screens instead of giving us another reason to stare at them? That question inspired me to build TouchGrass AI , a local-first AI application that turns your interests, available time, and energy level into personalized outdoor missions. I built this project for the Hacktoberfest Open-Source AI Challenge — Week 1 , themed Touch Grass . 🚀 What I…
TouchGrass AI is a local-first AI application designed to motivate users to spend more time outdoors, rather than on their screens. Created for the Hacktoberfest Open-Source AI Challenge, this project aims to turn users' interests, available time, and energy level into personalized outdoor missions.
The app provides a simple experience where users can select their interests and available time, which are then sent to the backend. The backend then prepares a request for the local language model, Ollama with the Qwen2.5 1.5B model. The model generates an outdoor activity with actionable instructions based on the user's preferences.
To handle unpredictable AI output, the backend includes error handling and falls back to predefined missions if needed. The project's source code is available on GitHub under the MIT License. TouchGrass AI demonstrates the potential of local AI in providing a useful, engaging, and accessible experience without relying on remote AI services.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.