Touchgrass.AI
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built I built TouchGrass AI , an open-source AI companion designed to help people spend less time on their screens and more time outdoors. 🌱 The idea is simple: use AI for a few seconds, then put the phone away. Users can choose an activity mode, available time, energy level, outdoor setting, and…
The submission for the Hacktoberfest Open-Source AI Challenge Week 1 is for an AI companion called TouchGrass AI. The purpose of this open-source application is to help users spend less time on their screens and more time outdoors. Users can select from three activity modes: nature, exploration, and gardening. TouchGrass AI generates a short, practical outdoor mission based on user preferences, such as activity type, available time, energy level, outdoor setting, and personal interests.
The app is designed to be privacy-focused, as it uses local inference to process AI requests without sending personal information to a third-party AI provider. The project also allows developers to experiment with different open-weight models, smaller models, quantized models, fine-tuned models, and local hardware. This open innovation approach makes the application more accessible and easier to modify and extend.
The project is built on Python FastAPI, Hugging Face Transformers, Qwen2.5-0.5B-Instruct, and supports Progressive Web App (PWA) support.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
