Touch Grass — Brutalist Open-Source AI That Shuts Your Screen Off in 15 Seconds
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass Touch Grass: The Brutalist Open-Source AI for the Real World This Week's Theme: Touch Grass — Build something with open-weight models or open-source AI that gets people off the screen and into the world. 🔗 Live Demo: touch-grass-blond.vercel.app — Try it now, no install required. 🐙 GitHub:…
This article is about an open-source AI called Touch Grass, which is designed to help people disconnect from their screens and spend more time outdoors. The AI is part of a project called Canopy OS and was created as part of the Hacktoberfest Open-Source AI Challenge. It is a brutalist, edge-native AI system that runs offline and does not require an internet connection.
The AI was built with several key principles in mind. Firstly, it should work even when there is no cell signal, such as when hiking in remote areas. Secondly, it should keep users' personal data private, especially when it comes to sensitive information like their location. Thirdly, it should allow for regional fine-tuning and model swapping, so that it can be adapted to different environments and needs. Lastly, it should be free to use, with no cost to run or per-token billing.
The AI comes with four core tools: a trail acoustic bio-identifier, a fall foliage run club and micro-adventure route builder, an edge frost-date and wild sowing almanac, and a 15-second screen-to-dirt protocol. These tools are designed to help users explore the outdoors and immerse themselves in nature. The interface of the AI is designed to be brutalist-lite, with high-contrast colors, monospaced labels, and a focus on simplicity and usability.
The overall goal of the AI is to encourage people to disconnect from their screens and reconnect with the natural world.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
