Building PlantLens AI for the Hacktoberfest "Touch Grass" Challenge

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass

I built PlantLens AI, a privacy-focused, AI-powered botanical assistant. Users simply upload a photo of a plant or leaf, and the application provides an instant health assessment, identifies possible diseases or pests, and outlines practical care instructions (watering, sunlight, and origin data).

To meet the "Touch Grass" philosophy, the app is intentionally designed to make the screen the shortest part of the experience. Instead of keeping users trapped in an endless chatbot UI, the AI generates a single, specific outdoor action task (e.g., "Check the top two inches of soil for moisture" or "Inspect the underside of leaves for aphids"). Users are prompted to physically go outside, perform the task, and click a "✓ I Did It" button to celebrate spending time in the real world.

Simple, AI-powered plant health assistant powered by Gemma open-weight vision models. Spot leaf diseases early, get actionable organic care steps, and spend less time on screens caring for real plants.

Home gardeners, urban plant parents, and allotment growers often notice unhealthy foliage—wilting stems, powdery mildew, yellow chlorosis, or necrotic spots—but do not know:

Most existing garden apps lock users behind paywalls, aggressive paywalls, or endless screen interactions that disconnect them from their garden.

PlantLens AI provides instant botanical triage: