SlowMate AI：由開放權重 AI 驅動的輕量級分步生產力助手

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

What I Built

I built SlowMate AI, a simple AI-powered task planner designed to make everyday tasks feel easier and less overwhelming.

Instead of looking at a big task and not knowing where to start, users can enter their task, select their available time and energy level, and get a manageable plan with smaller steps.

SlowMate AI encourages people to work at their own pace, avoid unnecessary stress, and make progress one small step at a time.

Demo

Try SlowMate AI here:

Live Website: https://tejasvimishra6.github.io/SlowMate-AI/

Code

GitHub Repository: https://github.com/TejasviMishra6/SlowMate-AI

The project is built using HTML, CSS, and JavaScript.

How I Built It

I built SlowMate AI using HTML for the structure, CSS for the design, and JavaScript for the functionality.

For the AI component, I used Transformers.js with the open-weight model LaMini-Flan-T5-77M (Xenova/LaMini-Flan-T5-77M). The model is intended to run in the browser, allowing the application to generate task-planning suggestions without relying on a conventional paid, closed AI API.

The application takes the user's task, available time, and energy level into account to help break work into smaller, more manageable steps. I also included a fallback plan so users can still receive a basic plan if AI generation is unavailable.

Why Does Open Innovation Matter?

Open innovation makes AI more accessible to students, beginners, and independent developers who want to experiment without depending entirely on expensive proprietary APIs.

By using an open-weight model and an open-source JavaScript library, I could explore how AI can be integrated into a simple web application while learning about browser-based inference.

SlowMate AI demonstrates how accessible AI tools can support everyday productivity and help people build healthier, more sustainable work habits.

My Agent Session

This project was developed with AI assistance for brainstorming, coding, debugging, and learning how to integrate an open-weight model into a web application.

Note: Add a DevRelay agent-session link here if you saved and shared a session.

The Lazy Payoff

SlowMate AI aims to reduce the effort needed to decide where to begin. Instead of planning every step manually, users can get a starting plan and focus on completing one manageable task at a time.

The goal isn't to do less meaningful work—it's to make getting started easier and progress more sustainable.

Prize Categories

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