DEV Community: Amrita Kaur

GhostStory AI 👻: Bringing Haunted Stories to Life

Amrita Kaur — Tue, 27 Oct 2026 14:26:21 +0000

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

What I Built

I built GhostStory AI, a spooky story generator inspired by haunted houses, mysterious forests, and supernatural adventures.

Users can enter a story idea, choose a mood, and generate a sample story. The project features a dark, Halloween-inspired interface designed to create a mysterious atmosphere.

This project was my way of exploring how a simple web application can turn creative ideas into an interactive experience.

Demo

Try GhostStory AI here:

https://amritakaur1717-collab.github.io/ghoststory-ai/

Code

Explore the source code on GitHub:

https://github.com/amritakaur1717-collab/ghoststory-ai

How I Built It

I built this project using:

HTML to structure the website.
CSS to create the dark, spooky visual design.
JavaScript to handle user interactions and generate stories from predefined templates.

The current version does not use a real AI model yet. Connecting an open-source language model is a possible next step.

Why Does Open Innovation Matter?

Open innovation makes it easier for developers to learn from existing projects, share ideas, and build on each other's work.

As a beginner, exploring open-source tools and projects helps me understand how applications are built and how I can improve my own work. In the future, I would like to integrate an open-source AI model to generate more original stories.

The Spirit of It

Every mysterious story begins with a little curiosity about the unknown.

I wanted to create a place where imagination meets spooky adventures, from haunted houses to mysterious forests. GhostStory AI is a small step toward making storytelling more interactive and fun.

This project is just the beginning, and I hope to make its stories even more creative in the future. 🌙

LazyLearn AI- Your Smart Study Companion📚

Amrita Kaur — Fri, 23 Oct 2026 16:33:54 +0000

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

What I Built

LazyLearn AI is a study assistant prototype designed to help students prepare for exams more easily. It provides a simple interface for turning study notes into summaries, practice questions, flashcards, quizzes, and easy explanations.

The goal is to reduce repetitive study preparation and make revision easier.

Demo

https://amritakaur1717-collab.github.io/lazylearn-ai/

Code

https://github.com/amritakaur1717-collab/lazylearn-ai/tree/main

How I Built It

I built the project using HTML, CSS, and JavaScript for the frontend, with Python and Flask for the backend. The interface is designed to let students select a study task and submit their notes for processing.

The AI integration and testing are still in progress.

Why Does Open Innovation Matter?

Open innovation makes AI technology more accessible and gives developers the freedom to learn, experiment, and adapt tools to their needs. My goal is to integrate open-weight AI into LazyLearn AI so students can prepare study materials more efficiently.

The Lazy Payoff

LazyLearn AI aims to reduce the effort students spend creating revision materials manually. Instead of preparing summaries, questions, and flashcards separately, students will be able to generate study resources from their notes in one place.

CareerCraft AI

Amrita Kaur — Thu, 15 Oct 2026 13:04:13 +0000

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

What I Built

🚀 CareerCraft AI — Your Smarter Resume Companion

CareerCraft AI is a web-based resume analysis tool designed to help students, freshers, and job seekers improve their resumes before applying for jobs.

Many applicants struggle to identify the right keywords for a job description and understand whether their resumes highlight the skills employers are looking for. CareerCraft AI aims to make this process easier through a simple, beginner-friendly interface.

What it does:

📝 Lets users enter their resume text and a target job description.
🔍 Identifies matching keywords and skills.
📊 Provides a resume keyword match score.
💡 Highlights missing keywords that users may want to address.
📱 Offers a responsive interface that works across different screen sizes.

The goal is to make resume preparation more accessible, especially for students and early-career professionals who may not be able to afford professional career coaching.

Who would pay for it?

Students, fresh graduates, job seekers, and career development services could benefit from a more advanced version with AI-powered feedback, tailored improvement suggestions, and multiple resume analyses.

CareerCraft AI currently serves as a browser-based prototype, with AI-powered analysis planned as a future enhancement.

Demo

Live demo: https://amritakaur1717-collab.github.io/CareerCraft-AI

The project can also be run locally by opening index.html in a web browser.

Code

GitHub repository: https://github.com/amritakaur1717-collab/CareerCraft-AI.git

The project is built using:

HTML — page structure
CSS — responsive layout and visual design
JavaScript — resume keyword analysis and score calculation

The current version uses browser-based, rule-driven keyword matching. Integration with an open-source AI model is a planned next step.

How I Built It

I built CareerCraft AI using HTML, CSS, and JavaScript, focusing on creating a clean, responsive, and easy-to-use experience.

The current prototype compares keywords in a resume against a target job description, calculates a match score, and identifies relevant terms that may be missing.

I chose a lightweight frontend approach to keep the project easy to run, understand, and contribute to.

AI integration is the next milestone. I plan to explore open-weight language models and open-source inference tools to provide contextual resume feedback, suggest improvements, and help users tailor their resumes to specific roles.

This would move CareerCraft AI beyond simple keyword matching toward more meaningful, AI-assisted career guidance.

Why Does Open Innovation Matter?

Open innovation matters because career tools should be accessible to people regardless of their financial background.

Open-source technologies make it possible for developers to learn from existing work, experiment with different approaches, and build useful tools without starting from scratch. They also create opportunities for contributors to improve functionality, accessibility, privacy, and performance.

For CareerCraft AI, open innovation creates a path toward exploring open-weight models and self-hosted inference instead of depending entirely on a closed AI API.

It could also make the project easier to customize for different industries, educational institutions, and communities.

My goal is to keep CareerCraft AI approachable for beginners while building toward a more capable, transparent, and accessible career assistant.

Prize Categories

Challenge: Hacktoberfest Open-Source AI Challenge — Week 2: Side Hustle

Project: CareerCraft AI

I'll confirm any additional partner prize categories after checking their eligibility requirements.

Thanks for checking out CareerCraft AI! 🚀

I'm excited to keep improving the project and explore how open-source AI can make career preparation more accessible.

Building a 100% Private, Offline-Ready Speech Translator for Hacktoberfest 2026

Amrita Kaur — Sun, 04 Oct 2026 20:18:07 +0000

*This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend

What I Built

I built Speech Translator, a privacy-first, offline-capable web application designed to bridge communication gaps for a loved one. Specifically, I built this for an elderly family member who struggles with language barriers during healthcare visits and daily conversations.

Speech Translator bridges communication gaps for loved ones. Built with HTML and JavaScript, it combines browser speech APIs with local open-weight AI for 100% private, offline-ready, and cost-free translation with zero cloud tracking, ensuring your conversations remain secure and entirely on your device. It eliminates the friction of traditional translation apps by offering an intuitive, high-contrast interface with real-time speech-to-text and text-to-speech output.

Demo

Live Website: https://amritakaur1717-collab.github.io/Speech-Translator/
GitHub Repository: https://github.com/amritakaur1717-collab/Speech-Translator.git

Code

You can explore the clean, lightweight codebase directly through the GitHub repository link above. The application is built using a minimal structure containing HTML and JavaScript files.

How I Built It

The application is structured into a lightweight, modular setup using HTML and JavaScript (with no external CSS dependencies).

Speech Processing: It harnesses native browser Speech Recognition and Speech Synthesis APIs to handle voice input transcription and clear audio playback for translated text.
Local AI Inference: For intelligent, context-aware translations, the app connects seamlessly to local open-weight AI models (such as Llama or Mistral running via Ollama).
Architecture: The frontend handles real-time audio event listeners and updates the DOM dynamically while communicating with the local API backend for high-speed linguistic conversion.

Why Does Open Innovation Matter?

Open innovation is the absolute backbone of this project because of two non-negotiable requirements: data privacy and accessibility.

Absolute Privacy: Personal health discussions and everyday family chats are deeply sensitive. A closed, proprietary cloud API would send voice data and translations to third-party servers where they could be logged or tracked. Open-source local inference ensures that data never leaves the local device.
Cost-Free & Offline Resilience: Relying on commercial cloud translation or LLM APIs introduces recurring subscription fees or rate limits. Open-weight models running locally allow unlimited, free translations even when an internet connection is unstable or entirely unavailable.

My Agent Session

Agent Development Session: [Link to your DevRelay session or session logs, if applicable]

Prize Categories

Open Source AI Integration
Privacy & Security Innovation
Best Accessibility Tool