🏮 Memory Lantern: Keeping Family Stories Alive with Local AI
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine
What I Built
I built Memory Lantern, an AI-powered family memory archive inspired by the Día de los Muertos theme.
We all have memories that we never want to forget. Sometimes, a small story about our grandparents, a childhood moment, or a family celebration means more than any photograph.
But these stories often remain scattered in notebooks, messages, or simply in our minds.
Memory Lantern is my attempt to create a digital space where people can preserve those moments.
With Memory Lantern, users can:
- Save personal and family memories with titles, dates, names, and categories.
- Organize and search their saved stories.
- Use AI to turn simple notes into meaningful stories.
- Ask questions about their saved memories using an AI assistant.
- Keep their memories stored locally in their browser.
The main idea is simple: Technology should not only help us remember information; it should also help us preserve the moments that make us who we are.
Demo
🔗 Live Demo: https://vedantshukla-cracker.github.io/Memory-Lantern/
Code
💻 GitHub Repository: https://github.com/vedantshukla-cracker/Memory-Lantern.git
The project currently uses three main files:
-
index.html– Website structure. -
style.css– Design and responsive layout. -
script.js– Application functionality, memory storage, search, and AI integration.
How I Built It
I wanted to build something simple enough to understand as a beginner but meaningful enough to solve a real problem.
I used:
- HTML for the website structure.
- CSS for styling and responsive design.
- JavaScript for memory management and application logic.
- Local Storage to save memories in the browser.
- Gemma 3 1B as the open-weight AI model.
- Ollama to run the model locally on my computer.
The most interesting part is the AI integration.
Instead of depending on a paid cloud AI API, I connected the application to a locally running Gemma model through Ollama.
There are two main AI features:
1. AI Story Polishing
Users can write a simple memory in their own words. Gemma helps improve the language and makes the story more expressive while keeping the original meaning.
2. AI Memory Assistant
Users can ask questions about their saved family stories. The application provides the saved memory context to Gemma, which generates answers based on the available information.
The project uses Ollama's local API to communicate with the model. No separate cloud AI service is required by the current implementation.
Why Does Open Innovation Matter?
For a project like Memory Lantern, privacy is especially important.
Family stories can contain personal details, names, and meaningful experiences. I didn't want the basic experience to depend on sending this information to an external AI service.
Using an open-weight model with local inference gave me more control over how the AI works and where the data is processed.
It also provides some important advantages:
- Privacy: Memory content and AI requests stay on the local machine in this implementation.
- Offline AI: After downloading the model, AI inference can run without an internet connection.
- Accessibility: Users don't need a paid cloud AI subscription or API key.
- Flexibility: The model and its configuration can be changed as the project develops.
- Learning: Running an AI model locally helped me understand how frontend applications communicate with AI systems.
Open innovation makes AI development more accessible to students and independent developers like me. It gives us an opportunity to experiment, learn, and build useful applications without depending entirely on closed platforms.
My Agent Session
I haven't recorded a DevRelay session for this project yet.
The Spirit of It
While building Memory Lantern, I kept thinking about one thing:
What happens to the little stories that our grandparents tell us? What happens to the memories of family celebrations, childhood adventures, and the people who made our lives special?
Photographs can preserve faces, but stories preserve feelings.
I wanted to build something that could help people keep those stories alive and pass them on to future generations.
Memory Lantern is not just about storing text. It is about making sure that meaningful moments don't get lost with time.
Because people may leave, photographs may fade, but the memories we preserve can continue telling their stories. ❤️
Prize Categories
- Best Use of Gemma – Using Google's Gemma 3 1B open-weight model through Ollama for AI-powered story polishing and memory-based conversations.
I am also submitting Memory Lantern for the overall Hacktoberfest Open-Source AI Challenge.
Built with ❤️ and a little help from AI.
Top comments (0)