DEV Community: Aadya Dwivedi

AFTERIMAGE — An Archive for Things That Refuse to Disappear

Aadya Dwivedi — Fri, 30 Oct 2026 07:37:04 +0000

AFTERIMAGE: An Archive for Things That Refuse to Disappear

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine

What I Built

AFTERIMAGE is an interactive digital archive inspired by abandoned computer systems, analog horror, forgotten memories, and the Día de los Muertos tradition.

The idea behind the project is simple: what if a computer could preserve the things that people leave behind?

Instead of building another generic AI chatbot, I created a fictional archive where users can explore memories, generate mysterious stories, and preserve personal tributes.

The project has four main features:

Ghost Terminal: An AI-powered terminal that generates fictional, eerie story continuations based on user prompts.
Memory Vault: A personal archive where users can save, view, delete, and export memories.
Digital Ofrenda: A digital tribute space inspired by Día de los Muertos, allowing users to preserve names, memories, and personal messages.
Lost Frequencies: A collection of fictional radio transmissions that make the archive feel like a forgotten communication system.

I interpreted the Ghost in the Machine theme as the idea of something seemingly forgotten still leaving traces behind.

AFTERIMAGE turns that idea into an interactive experience.

Demo

The project is designed to run locally in a browser using Visual Studio Code and Live Server.

aadyadwivedi67-oss.github.io

A public deployment.

Code

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

Project files:

index.html — Website structure and sections.
style.css — Visual design, animations, and responsive layout.
script.js — Application logic, AI integration, memory storage, and interactions.

The source code can be published as a GitHub repository.

How I Built It

I built AFTERIMAGE using HTML, CSS, and JavaScript, with open-source AI running directly in the browser.

The AI component uses:

DistilGPT-2: An open-weight language model used for generating fictional text.
Transformers.js: An open-source JavaScript library that allows machine-learning models to run directly in the browser.
localStorage: Used to preserve memories and digital tributes locally in the browser.

The Ghost Terminal loads the DistilGPT-2 model through Transformers.js and uses it to generate story continuations based on user input.

One important design decision was avoiding a custom AI backend, paid API keys, and Ollama.

The model runs in the browser. Its initial download requires an internet connection, and cached assets may allow subsequent use without downloading the model again.

The other features use JavaScript and browser storage to provide an interactive archive experience.

Why Does Open Innovation Matter?

Open innovation was important to AFTERIMAGE because I wanted to experiment with AI without making the entire project dependent on a closed, centralized API.

Using an open-weight model and an open-source JavaScript framework made browser-based AI experimentation possible without requiring a paid API key or a dedicated AI server.

It also makes the project easier for other developers to inspect, modify, and extend.

For a project centered around memories and personal archives, keeping data stored locally is another meaningful design choice.

Open-source tools make it possible to experiment, learn, customize, and build without needing access to expensive infrastructure.

The Spirit of It

AFTERIMAGE is built around the idea that not everything disappears completely.

Old photographs, forgotten messages, unfinished stories, and memories can all leave traces behind.

I wanted the website to feel like discovering an old computer that still has something left to tell.

The visual direction combines a vintage digital archive with the atmosphere of a forgotten shrine. The Ghost Terminal represents the machine, the Memory Vault represents what people preserve, and the Digital Ofrenda represents the things we choose to remember.

The goal was not simply to make an AI generate text. It was to give that interaction a setting, a purpose, and a story.

Some things disappear. Others become afterimages.

Thanks for participating in Hacktoberfest Open-Source AI Challenge Week 4.

EaseFlow: Less Planning, More Living — Open-Source AI for Everyday Tasks

Aadya Dwivedi — Thu, 22 Oct 2026 16:06:52 +0000

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

What I Built

EaseFlow is a browser-based AI productivity tool that turns messy brain dumps into organized, actionable task lists.

Instead of spending time sorting through assignments, reminders, errands, and unfinished work, users can write everything down in one place and let EaseFlow help organize it.

The application supports priority labels, task categories, completion tracking, filtering, and manual task creation.

It is designed for students, busy people, and anyone who wants to spend less time organizing their day.

The goal is simple: reduce the friction between knowing what needs to be done and getting started.

Demo

Live demo: [https://aadyadwivedi67-oss.github.io/easeflowsloth/]

The application can be demonstrated by entering a messy task list, generating an organized plan, and completing tasks directly in the browser.

Code

GitHub repository: [https://github.com/aadyadwivedi67-oss/easeflowsloth.git]

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

Technologies include HTML5, CSS3, JavaScript ES modules, Transformers.js, and the open-weight Xenova/flan-t5-small model.

How I Built It

I built EaseFlow as a browser-based application rather than relying on a dedicated AI backend.

The frontend is written in HTML, CSS, and JavaScript. Transformers.js loads the Xenova/flan-t5-small model for text generation in the browser.

Users enter a brain dump, and the model attempts to rewrite it into clearer tasks. JavaScript then creates task cards, assigns basic priority and category labels, and updates progress tracking.

A local rule-based fallback keeps the core task-organizing workflow available when the AI model cannot load.

Why Does Open Innovation Matter?

Open innovation makes this project more flexible and accessible.

Using an open-weight model allows developers to experiment with AI without depending on a proprietary inference API or paying per request. Browser-based inference also means that task text does not need to be sent to a separate AI inference service.

The source code can be inspected, modified, and extended. Developers can change the task organization rules or experiment with compatible models.

The application still needs an internet connection to download its model on first use, and complete offline operation is not guaranteed without additional configuration.

For a productivity tool that may handle personal reminders, reducing unnecessary data transmission is an important design choice.

My Agent Session

Optional. Add a DevRelay agent session link here if you record one.

The Lazy Payoff

EaseFlow is designed to reduce the small but repeated effort of sorting and prioritizing everyday tasks.

Instead of manually rewriting every reminder into a structured list, users can start with a brain dump and review the suggested actions.

The potential payoff is less time spent organizing and a clearer starting point for the work itself.

Actual time savings have not yet been benchmarked, so this submission describes the intended benefit rather than claiming measured results.

Prize Categories

Open-Source AI

Browser-Based AI

Closing Note

EaseFlow explores a simple idea: AI should help people spend less energy managing their work and more energy doing what matters.

By combining open-weight AI with a lightweight web application, the project aims to make everyday automation approachable, inspectable, and adaptable.

ListingLift — Turn Your Products into Must-Haves

Aadya Dwivedi — Thu, 15 Oct 2026 09:27:20 +0000

ListingLift: Better Product Listings, Bigger Side-Hustle Dreams

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle.

What I Built

Meet ListingLift — a product listing assistant designed for small business owners, handmade creators, and side hustlers who want to present their products more effectively online.

Selling online isn't just about having a great product. It's also about describing it in a way that catches attention. Writing product titles, descriptions, and social media captions for every item can be time-consuming, especially when you're running a small business on your own.

ListingLift aims to make that process simpler.

What it offers:

Product titles designed to grab attention.
Product descriptions that highlight key features.
Social media captions for promoting products.
Multiple writing styles, including Friendly, Playful, Professional, and Luxury.
The ability to generate alternative versions and copy the results.

The goal is simple: help small sellers spend less time struggling with words and more time building their businesses.

Demo

Live Demo: View ListingLift

Code

GitHub Repository: Explore the source code

ListingLift is built with HTML, CSS, and JavaScript, keeping the initial version lightweight and easy to explore.

How I Built It

I built ListingLift using HTML, CSS, and JavaScript.

HTML structures the product input form and listing workspace.
CSS creates the responsive interface and visual identity.
JavaScript handles product inputs, writing-style selection, listing generation, regeneration, and copy-to-clipboard functionality.

The current prototype uses predefined JavaScript templates to generate listing content. Connecting an open-weight AI model is a planned next step, so the current version should be considered an early prototype rather than a fully AI-powered application.

My next goal is to integrate an open-source language model to generate more original, context-aware listings based on each seller's product details.

Why Does Open Innovation Matter?

Small businesses deserve access to useful technology without needing a large budget or a dedicated technical team.

Open innovation makes it possible for developers to learn from existing tools, improve their projects collaboratively, and build solutions that others can inspect, adapt, and extend.

For ListingLift, an open approach could make future AI integration more flexible and help keep the project accessible to independent sellers and developers.

I want ListingLift to grow beyond a simple listing generator into a practical tool that helps more people turn their ideas into sustainable side hustles.

What's Next?

Integrate an open-weight language model.
Improve listing quality with product-specific context.
Add reusable templates for different marketplaces.
Expand customization options for different seller needs.
Continue improving accessibility and mobile responsiveness.

The vision: make better product writing accessible to everyone, not just businesses with big marketing budgets.

Built with curiosity, open-source spirit, and a belief that small ideas can grow into big things.

my first try please support

Aadya Dwivedi — Fri, 09 Oct 2026 17:01:18 +0000

Aadya Dwivedi

Oct 9

Grounded: Turning “Touch Grass” into Tiny Outdoor Adventures 🌿

#devchallenge #hf26challenge

4 min read

Grounded: Turning “Touch Grass” into Tiny Outdoor Adventures 🌿

Aadya Dwivedi — Fri, 09 Oct 2026 16:57:08 +0000

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

🌿 What I Built

I built Grounded — Little Adventures Outside, a colourful, interactive website that encourages people to take a break from their screens and discover the little things waiting for them outdoors.

The idea is simple: sometimes, we want to step outside but don't know what to do, don't have much time, or just don't have the energy to plan something.

Grounded makes that first step easier!

Users choose their available time, energy level, nearby environment, and current mood. Based on these preferences, the website suggests a small outdoor adventure with simple steps and an optional mini-mission.

Some examples include:

🌼 Becoming a little nature detective and discovering patterns around you.
☁️ Looking at clouds and inventing stories about them.
🎨 Collecting colours from your surroundings for creative inspiration.
🐦 Observing birds and other wildlife from a respectful distance.
🌳 Exploring a familiar neighbourhood with fresh eyes.

I wanted the experience to feel less like a productivity app and more like opening a colourful children's storybook. That's why I used playful typography, pastel colours, doodle-inspired illustrations, and friendly activity cards.

Who is it for? Anyone who wants a small, approachable reason to step outside, especially students and people who spend much of their day looking at screens.

The goal isn't to make going outdoors another task to complete. It's to make it feel like a little adventure.

🚀 Demo

Try Grounded here: https://aadyadwivedi67-oss.github.io/GROUNDED/

Choose your preferences, generate an adventure, and see where a small outdoor break takes you!

💻 Code

The project is open source and available on GitHub:

Repository: aadyadwivedi67-oss/GROUNDED

Clone it using:

git clone https://github.com/aadyadwivedi67-oss/GROUNDED.git

The project is built with:

HTML5 for the page structure and interactive form.
CSS3 for the colourful, responsive storybook design.
JavaScript for preference handling, activity selection, and dynamic result generation.
Inline SVG for lightweight, doodle-style illustrations.

There is no backend or database required to run the current version.

🛠️ How I Built It

I wanted to create something that was simple to use but still felt playful and personal.

I started with the idea of a tiny outdoor adventure generator and built the interface around four questions: How much time do you have? How much energy do you feel you have? What kind of outdoor space is available? And what mood are you in?

I then created a collection of activities in JavaScript and added logic to select suggestions based on the user's preferences. The website adapts parts of the activity to the available time and lets users generate another suggestion without starting over.

The visual design was an important part of the process. Instead of using a conventional dashboard, I went for a children's-book-inspired look with pastel colours, rounded cards, playful fonts, and SVG illustrations.

I also kept the project lightweight so it could be run directly in a browser without a complicated setup.

A note about AI: The current published version uses a rule-based JavaScript generator; it does not yet integrate an open-source AI model. AI-powered activity generation is a possible future improvement, but I don't want to claim that a model was used when it wasn't.

🌍 Why Does Open Innovation Matter?

Open innovation makes it possible for people to experiment, learn, and build on each other's ideas without needing to start from scratch.

For a project like Grounded, an open-source approach means that other developers can explore the code, suggest new activities, improve accessibility, redesign the interface, or contribute an AI-powered recommendation system.

It also creates opportunities to learn from the community. A small project can become more useful when people with different skills contribute their perspectives.

In the future, I'd love to explore integrating an open-weight language model that can generate more varied activities based on a person's preferences, while keeping the experience lightweight and approachable.

For me, the important part of open innovation is not just having access to technology. It's having the freedom to understand it, experiment with it, and make something of your own.

🤖 My Agent Session

I don't have a shareable agent-session recording to include at the moment.

🏆 Prize Categories

This project is submitted to the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass.

I have not claimed any additional partner prize categories because the current version does not yet integrate an open-source AI model or agent framework.

🌿 Take a little break. Find a little wonder.

Thanks for checking out Grounded! I'd love to hear what tiny outdoor adventure you would add to the collection.