The latest articles on DEV Community by Sasi-019 (@sasi019). https://dev.to/sasi019 https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4158861%2F71b26118-613e-48f9-8037-91bd0542eed1.png https://dev.to/sasi019 en Sasi-019 Sun, 04 Oct 2026 18:25:07 +0000 https://dev.to/sasi019/memomate-an-ai-personal-assistant-built-for-a-friend-1plh https://dev.to/sasi019/memomate-an-ai-personal-assistant-built-for-a-friend-1plh <p><em>This is a submission for the <a href="https://dev.to/challenges/hacktoberfest-weekend-2026-10-01">Hacktoberfest Weekend Challenge: Build for a Friend</a></em></p> <h2> What I Built </h2> <p>I built <strong>MemoMate</strong>, an AI-powered personal productivity assistant for a friend who wanted a simpler way to manage everyday tasks, reminders, lists, and important information.</p> <p>Instead of opening different apps for different tasks, the user can interact with MemoMate using natural language.</p> <p>For example:</p> <ul> <li>"Remind me to submit my assignment tomorrow at 10 AM."</li> <li>"Create a shopping list."</li> <li>"Add milk to my shopping list."</li> <li>"Show my lists."</li> <li>"What do I have tomorrow?"</li> <li>"Remember that my project deadline is next Friday."</li> </ul> <p>MemoMate understands these requests and turns them into actions such as creating reminders, managing lists and list items, saving memories, and retrieving information.</p> <p>The goal was to build something that feels more like talking to a personal assistant rather than filling out forms.</p> <h3> Main Features </h3> <ul> <li>AI-powered natural-language interaction</li> <li>Reminders and recurring reminders</li> <li>Shopping and custom lists</li> <li>Add, complete, and remove list items</li> <li>Calendar and upcoming events</li> <li>Personal memory</li> <li>Notifications</li> <li>Voice interaction</li> <li>User-specific data and actions</li> <li>Deployed web application</li> </ul> <h2> Demo </h2> <p>Try the live application:</p> <p><strong><a href="https://memomate-frontend-vjt2.onrender.com" rel="noopener noreferrer">🚀 Try MemoMate Live</a></strong></p> <h2> Code </h2> <p>The complete source code is available on GitHub:</p> <p><strong><a href="https://github.com/Sasi-019/MemoMate" rel="noopener noreferrer">💻 View MemoMate on GitHub</a></strong></p> <p>The repository contains both the React frontend and FastAPI backend.</p> <h2> How I Built It </h2> <p>MemoMate is built as a full-stack application.</p> <h3> Frontend </h3> <ul> <li>React</li> <li>Vite</li> <li>JavaScript</li> <li>CSS</li> </ul> <p>The frontend provides the assistant interface along with pages for reminders, lists, calendar information, and notifications.</p> <h3> Backend </h3> <ul> <li>Python</li> <li>FastAPI</li> <li>SQLAlchemy</li> <li>PostgreSQL / SQLite</li> <li>JWT-based authentication</li> </ul> <p>The backend handles users, reminders, lists, list items, memories, and AI-powered assistant requests.</p> <h3> AI </h3> <p>For the AI layer, I used <strong>Hugging Face</strong> with an open-weight <strong>Qwen</strong> model.</p> <p>The AI is not given unrestricted control over the database. Instead, MemoMate uses an action-based architecture.</p> <p>The basic flow is:</p> <div class="highlight js-code-highlight"> <pre class="highlight plaintext"><code> text User request ↓ AI / Intent Recognition ↓ Structured Action ↓ Validation ↓ Action Engine ↓ Database ↓ Response to User </code></pre> </div> devchallenge weekendchallenge hf26challenge