R

react

https://hackathon-qd3o.vercel.app/

Offline AI-powered document extraction system built with React, FastAPI, and local machine learning models for secure document processing.

MyDocVault is a secure, offline-first AI platform designed to help users store, organize, understand, and manage government documents in a privacy-preserving environment. The application enables users to upload documents such as Aadhaar, PAN, Passport, Driving Licence, Voter ID, educational certificates, and other official records, while ensuring that all processing happens locally without relying on external servers or internet connectivity.

Powered by an intelligent document-aware assistant, MyDocVault extracts key information, summarizes documents in simple language, answers user queries based solely on locally stored documents, and provides guidance on the documents required for various government services. The system never fabricates information, clearly identifies missing details, and prioritizes user privacy by keeping all data offline.

Key Features 🔒 Offline-first and privacy-focused document management 📄 Secure storage and organization of government documents 🤖 AI-powered document understanding and summarization 🔍 Automatic extraction of important document details 📋 Government service document requirement guidance 📂 Intelligent document search and retrieval ⚠️ Identification of missing or incomplete documents 🛡️ Local processing with no external API or internet dependency 💬 Simple, conversational AI assistant for document-related queries 📊 Structured JSON extraction for document metadata

Tech Stack: React.js, Node.js, Express.js, SQLite, OCR, Local AI Models, HTML, CSS, JavaScript

Goal: To provide citizens with a secure, intelligent, and completely offline digital document vault that simplifies document management while ensuring maximum privacy and accessibility.

Voice-based AI salary negotiation simulator. Practice high-stakes negotiations against a stateful Gemini AI opponent with hidden BATNA, trust, tension and patience. Built with FastAPI + React + Vite.

Memento AI – A CPU-first, offline AI assistant that transforms documents, images, audio, video, and text into structured knowledge using local LLMs, SQLite, and Retrieval-Augmented Generation (RAG), with

Offline-first, CPU-optimized AI platform that transforms unstructured documents into structured, searchable data using local OCR, embeddings, llama.cpp, FAISS, and SQLite—no cloud inference or external APIs required.

Open-source crowdsourced wildfire and smoke tracking dashboard built for communities.

DriverOS is an AI-powered driver assistance and safety platform designed for commercial drivers, truck drivers, delivery partners, and fleet operators across India. The platform focuses on driver safety, health monitoring, emergency response, trip management, document storage, and real-time support services.

Offline-first, CPU-only PWA that converts spoken clinical notes from rural healthcare workers into structured patient records using Whisper.cpp and llama.cpp — fully functional with no internet connection.

This project is an offline-first, CPU-only AI app that converts unstructured inputs like documents or images into clean structured data locally on the user’s device. It uses local OCR, small on-device models, and SQLite storage to extract key details, validate them, and help users quickly turn messy files into usable records without needing the internet.

Offline Resume Parser is an offline-first, CPU-optimized AI application that converts unstructured PDF resumes into structured, machine-readable candidate profiles entirely on the user's device. The platform performs document extraction, AI-powered information extraction, validation, and local storage without relying on cloud services or internet connectivity.

Built with React, Vite, FastAPI, SQLite, PyMuPDF, Pydantic, and a locally hosted Small Language Model (SLM) via llama.cpp, the application provides a secure, privacy-preserving solution for recruiters and organizations handling sensitive hiring data. Its modern, responsive interface enables users to upload resumes, view extracted candidate information, browse resume history, and export structured JSON, all while running efficiently on standard CPU hardware.

A fast, modern deadline tracker that sorts tasks by urgency — built with React, Vite, and Tailwind CSS

ResearchLens is a research support and academic consulting project that helps students, researchers, M.Tech scholars, and PhD candidates throughout their research journey. The platform provides guidance on thesis writing, research paper preparation, journal publication (including Scopus and SCI-indexed journals), literature reviews, synopsis development, and academic documentation. Its goal is to simplify the research process and help scholars produce high-quality, publication-ready work.

AI-powered decision simulation platform — multi-expert adversarial debate with real-time streaming, structured scoring, and AI-synthesised verdicts. Built for the Swecha Internship Hackathon.

RideSync is a full-stack ride-sharing web application that connects drivers and passengers traveling in the same direction, helping users reduce travel costs, save time, and promote sustainable transportation.

QuestLog is a gamified productivity platform that transforms daily tasks into RPG-style quests. Users can create and manage Main, Side, and Daily Quests, earn XP, maintain streaks, unlock achievements, and generate AI-powered Daily Chronicles based on their progress. By combining task management with game mechanics, QuestLog makes productivity more engaging, motivating, and rewarding.

JalRakshak – Smart Water Leak Reporting System

JalRakshak is an AI-powered civic technology platform designed to help citizens report water leaks, pipeline damages, and water wastage incidents in real time. The system enables users to submit reports with location details, images, and descriptions, while helping authorities efficiently monitor, prioritize, and resolve water-related issues.

The platform incorporates intelligent features such as duplicate report detection, location-based issue mapping, automated prioritization, and analytics dashboards to improve response efficiency and reduce water loss. By creating a direct communication channel between citizens and municipal authorities, JalRakshak promotes community participation in water conservation and urban infrastructure management.

Key Features:

Real-time water leak and wastage reporting GPS-based location tracking and mapping Image upload and issue documentation Duplicate report detection and merging Priority-based issue management Administrative dashboard for monitoring and resolution Analytics and reporting for decision-making Secure, scalable, and open-source architecture

JalRakshak aims to support sustainable water management, enhance civic engagement, and assist local governments in addressing water infrastructure problems quickly and effectively.

Telugu Thodu is a full-stack web application built with React (frontend) and Node.js/Express (backend) that generates Telugu words starting with a user-supplied Telugu letter by calling the Gemini API. Generated results are saved to MongoDB for history and analytics. The app provides a polished, responsive UI, input validation for Telugu characters, and secure handling of the Gemini API key via environment variables.

Client application for the deployed backend server of Swecha Corpus collector

The Image Captioning project is an AI-based system that automatically generates textual descriptions for images. It combines computer vision and natural language processing (NLP) techniques to understand the content of an image and produce a human-readable caption.

The system uses deep learning models, typically a Convolutional Neural Network (CNN) for extracting image features and a Recurrent Neural Network (RNN) or Transformer-based model for generating sentences. This enables applications such as assisting visually impaired users, enhancing image search engines, and automating social media content tagging.