Touch Grass: I Built an AI Nature Companion to Help You Unplug

Anshika Trivedi — Sat, 10 Oct 2026 13:45:45 +0000

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

What I Built

I built Touch Grass — AI Nature Companion, a web-based project that encourages people to take a break from screens and reconnect with nature.

The website uses AI-powered image classification to help users explore the natural world. It also provides garden suggestions and outdoor missions that encourage users to step outside, observe their surroundings, and spend more time in nature.

The project is designed for students, developers, and anyone who spends too much time in front of a screen. Instead of just telling people to take a break, it gives them simple and engaging activities to try outdoors.

Demo

🌿 Live Website: https://anshikatrivedi-builds.github.io/-Touch-Grass-AI-Nature-Companion/

Code

💻 GitHub Repository: https://github.com/anshikatrivedi-builds/-Touch-Grass-AI-Nature-Companion

The project is built as a web application using HTML, CSS, and JavaScript.

How I Built It

I built this project using HTML, CSS, and JavaScript, keeping everything in a single index.html file to make it easy to run and deploy.

For AI-powered image classification, I used Transformers.js, which allows machine-learning models to run directly in the browser. This makes it possible to explore AI without needing to build a separate backend server.

The website also includes rule-based garden suggestions and predefined outdoor missions to encourage users to interact with nature.

I deployed the website using GitHub Pages and configured GitHub Actions to automate the deployment workflow.

As a beginner exploring AI and open-source development, this project helped me learn how to combine web development, browser-based AI, and deployment tools in one practical application.

Why Does Open Innovation Matter?

Open innovation makes AI more accessible to developers, students, and people who are just starting their journey.

By using open-source tools and browser-based AI, I could experiment with machine learning without depending entirely on a closed, paid AI API or maintaining a dedicated backend for inference.

It also makes projects easier to learn from, modify, and improve. Other developers can explore the code, suggest improvements, and build new features on top of it.

I believe open innovation helps turn ideas into real projects while making technology more accessible to everyone.

My Agent Session

I built this project with AI-assisted development as part of my learning journey.

I haven't added a DevRelay agent session link yet.

Prize Categories

Open-Source AI
AI-powered application

DEV Community: Anshika Trivedi