TouchGrass AI — Let AI Plan It, You Go Outside

"TouchGrass AI" is the title of a project featured in the Hacktoberfest Open-Source AI Challenge Week 1. The application is an AI-powered outdoor activity planner designed to encourage users to spend more time outside rather than on their screens.

Users can input their preferences such as activity type, available time, energy level, environment, solo or group preference, personal interests, and optionally a location or context. Based on these inputs, the AI generates a personalized outdoor mission with a title, description, duration, difficulty, outdoor steps, what to bring, safety guidance, and a screen-off challenge.

For instance, if a user enters a preference for walking for 30 minutes with a medium energy level at a college campus and an interest in nature, the AI might generate a mission like this: "30-Minute Campus Nature Hunt Walk for 5 minutes without checking your phone. Find three different types of leaves. Sit quietly and observe your surroundings. Listen for different natural sounds. Find something interesting in nature. Take a different route back to your starting point."

The goal is to minimize the screen time during the activity. The project is built using Python Flask, HTML, CSS, JavaScript, and the Ollama local AI integration. The GitHub repository for the project is available at https://github.com/NavyaPachigolla/TouchGrass-AI and a demo video can be viewed at https://youtu.be/uEIksufzbt0.

Open innovation is crucial for this project as it utilizes an open-weight AI model locally using Ollama, rather than relying on a closed cloud AI API. This allows the AI to run directly on the user's computer, keeping their activity preferences on their own device instead of being sent to a remote service. Additionally, the project eliminates the need for a paid proprietary AI API, making it easier to experiment with and run locally.