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

## What I Built

I built TouchGrass AI, a local AI-powered outdoor activity companion that encourages people to take a break from their screens and reconnect with nature. 🌿

The idea is simple: instead of spending all day scrolling, users can generate small outdoor missions, complete them in the real world, and record their experiences in Field Notes.

Key Features

• 🌱 AI-Generated Missions: Get outdoor activity ideas powered by local AI.
• ✅ Mission Checklist: Track your progress as you complete activities.
• 📝 Field Notes: Record your experiences and reflections.
• 🌲 Nature-Inspired UI: A forest-green and mint interface designed around the idea of spending more time outdoors.
• 🔒 Local AI Inference: Uses Ollama with Gemma 3, so AI generation runs locally instead of relying on a paid cloud AI API.

TouchGrass AI is designed for students, people who spend a lot of time on screens, and anyone who wants a simple nudge to step outside.

Demo

GitHub Repository: https://github.com/ashandeepkaur27/TouchGrass-AI

TouchGrass AI currently runs locally on my computer. I’m including a short screen-recorded demo showing how users can generate outdoor missions, track their progress, and write Field Notes.

Demo video: [https://youtu.be/kPPGA8FwSwA]

Code

Explore the source code, README, screenshots, and setup instructions here:

TouchGrass AI on GitHub

The project is built with Python and Streamlit, with Ollama providing local AI inference.

How I Built It

I built TouchGrass AI using Python, Streamlit, and Ollama with the Gemma 3 model.

Streamlit powers the user interface, while Python handles the application logic and communication with Ollama's local API. When a user requests an outdoor mission, the application sends a prompt to the locally running Gemma 3 model and displays the generated response.

The app also uses Streamlit session state to manage mission progress and Field Notes during the current session.

My goal was to build a practical, beginner-friendly project that combines local AI with a real-world purpose. Rather than using AI just to generate text, TouchGrass AI uses it to encourage small offline activities.

Why Does Open Innovation Matter?

Open innovation made it possible for me to experiment with AI in a more accessible and transparent way.

Using the open-weight Gemma 3 model through Ollama allowed me to run AI locally without depending on a paid cloud AI API for text generation. This gave me more control over the development process and helped me learn how local AI inference works in a real application.

Open-source tools also made it possible to combine Python, Streamlit, and local AI into a project that others can explore, learn from, and improve.

I hope TouchGrass AI inspires other developers to build technology that helps people develop healthier relationships with their screens.

My Agent Session

I built this project using Python, Streamlit, and Ollama. I have not included a DevRelay agent session.

Prize Categories

Best Use of Gemma — TouchGrass AI uses Google's open-weight Gemma 3 model through Ollama for local AI-powered outdoor mission generation.

devchallenge #hf26challenge