Touch Grass: Snap Nature, Learn in Seconds, Get Back Outside 🌿
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built Most modern apps are engineered to maximize your screen time—rewarding infinite scrolling, intrusive notifications, and continuous engagement. Touch Grass is built with the opposite philosophy: a digital field companion designed to get you off your phone and back into the wild as quickly as…
Touch Grass is a digital field companion app designed to encourage people to disconnect from their phones and connect with nature. The app uses open-weight vision models like Qwen2.5-VL:7B to identify plants and wildlife from photos, providing users with concise, structured information about their discoveries. Users can snap photos or choose from their camera roll, and the app returns a field-guide card with common and binomial names, classification, confidence level, field recognition marks, lifespan, habitat, global range, fun facts, safety warnings, and look-alike alternatives.
The app also presents randomized outdoor prompts to encourage users to continue engaging with their surroundings. Touch Grass prioritizes privacy, runs locally with Ollama, and is open-source on GitHub. It has won prizes for best use of Render and best use of Google's open-weight Gemma model for local edge inference.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.