Touchgrass.local — An AI Coach That Gets You Outside
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built Touchgrass.local is a small AI-powered browser app that encourages people to step away from their screens and spend some time outdoors. Users describe how their day has gone, and an open-weight language model running directly in the browser gives them one small outdoor mission along with a…
Touchgrass.local is an AI-powered browser app created for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass. The app encourages users to step away from their screens and spend time outdoors by generating one small outdoor mission with a friendly nudge. Users describe their day, and an open-weight language model runs directly in the browser, providing the mission and visual feedback.
Once the mission is completed, the user marks it as done, and a field of CSS grass grows on the screen. The app tracks completed missions and streaks using localStorage, ensuring privacy and no reliance on APIs or backends. The project is built with HTML, CSS, JavaScript, and WebLLM by MLC AI, supporting various open-weight models such as Gemma 2 2B, Qwen 2.5 1.5B, and Llama 3.2 1B.
The open-source nature of the project allows developers to experiment with different models, learn from it, and contribute improvements.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
