TouchBase：提醒用戶放下螢幕、投入線下生活的 AI 伴侶

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

What I Built

I built TouchBase, an AI-powered companion designed to help people step away from their screens and reconnect with the world around them.

We spend so much time scrolling, switching between apps, and staring at screens that we sometimes forget to take a walk, enjoy the outdoors, or simply spend time with the people around us.

TouchBase takes a different approach to AI. Instead of encouraging people to spend more time online, it helps them find meaningful reasons to go offline.

From suggesting short outdoor activities and mindful breaks to helping users build healthier daily routines, the idea is to make taking a break feel simple and enjoyable.

The goal isn't to make people feel guilty about their screen time. It's to remind them that there's a whole world waiting beyond the screen.

Code

GitHub Repository: https://github.com/afreensumai64/carekit

How I Built It

I designed TouchBase around the idea of using AI as a gentle guide rather than another source of distraction.

The application can suggest offline activities based on a user's available time, interests, and daily routine. For example, someone with ten free minutes might get a suggestion to step outside, stretch, or take a short walk without their phone.

The project is intended to use open-weight AI models and open-source tools so the AI experience can be adapted as the application evolves.

My focus is on keeping the experience simple, practical, and centered on actions people can take in the real world.

Why Does Open Innovation Matter?

There's something meaningful about using AI to help people spend less time interacting with technology.

Open innovation makes this approach more flexible. Open-weight models give developers the freedom to experiment with different models and deployment options, while open-source tools make it easier for others to inspect, adapt, and improve the project.

With a suitable model and local inference setup, the experience could also work without sending personal activity preferences to an external AI service.

Most importantly, open innovation lets developers explore a different kind of AI experience: one that supports healthier habits instead of competing for attention.

I believe technology should help us live better, not keep us glued to our screens.

Prize Categories

• Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass

Build with AI. Take a break. Go touch grass. 🌱