Dayloom: What If AI Helped You Spend Less Time on Your Screen?

Amayl — Sat, 10 Oct 2026 14:34:05 +0000

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

Dayloom — A Web App

Dayloom is a web app that gives users a new offline activity every day. To make these activities more engaging, I created a memory-card feature that lets users upload photos of the tasks they completed. Dayloom then transforms those images into a Pinterest-inspired “Today’s Core” card that users can save as a personal memory.

For people in my generation, staying away from screens for too long can feel unrealistic. The memory-card feature provides a small dose of dopamine and motivation: users can turn off their screens, go outside, complete simple activities, and later upload their photos to create a visual keepsake.

The app stores generated activities in local storage until the following day. So users can safely close the website and disconnect from their screens without losing their tasks. Dayloom is designed for people who feel bored without their phones because they do not know what else to do. It gives them fun, simple activities to help them rediscover their spark.

Demo

Code

Amayl97 / Dayloom

A mindful daily challenge app that encourages people to step away from screens, explore the world around them, and turn their moments into a visual keepsake with local AI.

🌿 Dayloom — Less Scrolling, More Living

What if AI didn't ask for more of your screen time, but helped you spend less of it?

Dayloom is a web application built for the Hacktoberfest Open-Source AI Challenge — Week 1: Touch Grass.

In a world filled with endless scrolling, short-form videos, and constant digital stimulation, stepping away from our devices can be harder than it sounds. Dayloom uses open-source AI to inspire people to take a break from their screens, enjoy small real-world experiences, and turn those moments into memories worth keeping.

Instead of encouraging more screen time, Dayloom encourages you to go outside, slow down, and appreciate the little things around you.

✨ Features

🌱 AI-Powered Daily Activities: Generate five fun, peaceful, and achievable offline activities using Gemma 3 4B.
💬 Daily Motivational Message: Receive an encouraging message to inspire your day.
📸 Capture Your Moments: Upload photos…

View on GitHub

How I Built It

I built Dayloom using React, CSS, Spring Boot, and Gemma 3 4B through Ollama.

✨Open-Source AI with Gemma 3 4B

Dayloom uses Gemma 3 4B, an open-weight language model, running locally through Ollama. I integrated it with my Spring Boot backend to generate four fun, achievable offline activities and a motivational message to encourage users to step away from their screens.

Instead of using AI to generate more content for people to scroll through, I wanted to use it to inspire real-world experiences. The model helps make activity suggestions that turn the idea of touching grass into something practical, creative, and enjoyable.

✨From Offline Activities to Memory Cards

Once users have tried an activity, they can upload photos of their experience and turn them into a personalised memory card. The card combines their photos into a collage with the date and a motivational message, giving them a creative way to preserve and share their offline moments.

✨Putting It Together

React, JavaScript, and CSS power the frontend and user experience.
Java Spring Boot handles the backend and communicates with the AI model.
Gemma 3 4B + Ollama power AI-generated activities and motivational messages through local inference.
GitHub Copilot assisted me with code reviews, debugging, and GitHub workflow tasks as I developed and tested the application.

The biggest idea behind Dayloom is simple: AI doesn't always have to encourage more screen time. It can help us find inspiration to step away, experience something real, and turn those moments into memories.

Why Does Open Innovation Matter?

Open innovation made it possible for me to experiment with AI in a way that fits my project’s purpose and my resources as a student developer.

By using Gemma 3 4B through Ollama, I could explore local AI inference and integrate a language model into my Java Spring Boot backend without relying on a proprietary, hosted LLM API for activity generation.

This allowed me to learn how AI models can become part of a real application, from generating activity suggestions to returning responses through a backend API.

More importantly, Dayloom challenges the usual idea of using AI to generate more digital content. I wanted to build something that encourages people to put their devices down and experience the world around them.

Open-weight models make experimentation more accessible to independent developers and students like me. They give us more flexibility to explore, learn, and build ideas without making a commercial API the starting point for every project.

With Dayloom, I wanted to use AI to help people spend less time on screens and more time making memories.

Prize Categories

Best Use of Gemma
I used Gemma to generate fun, creative offline activities that encourage users to disconnect from screens and explore the world around them.

Best Use of GitHub Copilot
I used GitHub Copilot to troubleshoot issues, refine code, and speed up Dayloom's development while making my own design and implementation decisions.

DEV Community: Amayl