LazyMate AI

🦥 LazyMate AI — Work Smarter, Rest Easier

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady.

What I Built

I built LazyMate AI, a student-friendly productivity website that helps people manage their daily tasks without feeling overwhelmed.

Sometimes, we have so many things to do that even deciding where to start becomes difficult. LazyMate AI is designed to make that easier by allowing users to:

• 📝 Add, delete, and organize daily tasks.
• 🎯 Set priorities for different tasks.
• ✅ Track completed tasks and overall progress.
• 💾 Save tasks in the browser using local storage.
• 🧠 Generate a simple, low-stress task plan using a locally running AI model.

The goal is simple: spend less energy organizing your work and more time doing what matters.

Demo

🌐 Live Website: Try LazyMate AI

The website provides a simple dashboard where users can manage tasks and monitor their progress.

Note: The AI planning feature requires Ollama and the selected model to be running locally. The deployed GitHub Pages website cannot access Ollama running on your personal computer automatically.

Code

💻 GitHub Repository: Aiman00-coder/LazyMate-AI-

The project is built using three separate files:

• index.html — Website structure
• style.css — Styling and responsive design
• script.js — Task management, browser storage, and AI integration

How I Built It

I used HTML, CSS, and JavaScript to build the website and create an interactive dashboard.

For the AI component, I designed the application to connect to Ollama with the Llama 3.2 model, allowing the assistant to generate task plans using local inference instead of a paid AI API.

The JavaScript sends unfinished tasks and their priorities to the local model when the user requests a plan. The model then suggests a manageable order of tasks, small steps, and breaks.

This approach also gave me an opportunity to learn about browser storage, asynchronous JavaScript, API requests, and connecting an AI model to a frontend application.

Why Does Open Innovation Matter?

Open innovation makes it easier for developers and students to experiment with AI without depending entirely on paid, closed APIs.

By using a locally running model, LazyMate AI can keep task data on the user's machine during AI processing, offer more control over prompts, and make it possible to experiment with different compatible models.

It also helped me understand that building an AI-powered application doesn't always require an expensive API subscription.

The model needs to be downloaded first, and its license should be checked before describing it as fully open-source.

My Agent Session

I developed this project with AI-assisted coding and used the experience to explore how a frontend application can connect to a local AI model.

I haven't included a DevRelay session link yet.

The Lazy Payoff

LazyMate AI is built around one idea: you don't have to do everything at once to make progress.

Instead of repeatedly deciding which task to start, users can organize their tasks, identify priorities, and request an AI-generated plan.

The project is an exploration of how small automations can reduce decision fatigue and make everyday productivity feel more manageable.

Prize Categories

This project focuses on the challenge's Slow and Steady theme through task management and AI-assisted planning.