H

Hackathon

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

MedScribe — Offline-first prescription & lab report digitizer. Converts photos of handwritten/printed medical records into structured, queryable data using local OCR (Tesseract) and a local SLM (Ollama, qwen2.5:1.5b) — no cloud APIs, fully CPU-only, works air-gapped. Built for the CPU-First Hackathon ("Local AI").

OriginAI transforms research papers into startup opportunities, investor reports and pitch decks using AI.

Offline-first lecture transcription and structured study data extraction CLI/PWA.

Shabdham AI is a Telugu-first Indian Sign Language learning and communication platform with voice-based sign translation and interactive learning modules.

Offline-first meeting transcriber using whisper.cpp and Qwen2.5 — fully local CPU inference, no cloud APIs, no GPU required.

Chalo Miya! is an AI-powered Hyderabad travel companion that helps users discover places, build personalized itineraries, and explore the city's rich culture with intelligent recommendations.

Image Text Extractor — Offline OCR text extraction from images using Tesseract, local Llama post-processing, and SQLite history. 100% local, no cloud APIs.

PaperLens Offline is an offline-first, CPU-optimized AI research paper analyzer that extracts structured knowledge from academic PDFs using local LLMs (Ollama), stores the results in SQLite, and enables fast local search without any cloud APIs.

AI Medical Record Extractor is an offline-first web application that converts unstructured medical documents into structured JSON data using CPU-only inference. It supports PDF, image, and text files while ensuring complete privacy by processing all data locally without cloud services. Built with FastAPI, React, and SQLite, the application provides a user-friendly interface for extracting patient information, diagnoses, medications, and other medical details. The project is designed to be lightweight, secure, open source, and accessible in low-connectivity environments.

offline-first, AI-powered FIR draft assistant. Uses local LLMs (Ollama) and on-device OCR to ecurely extract structured data from sensitive complaint documents without the cloud.

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.

NyayaBloom is an AI-powered Judicial Intelligence Platform designed to democratize legal knowledge and improve judicial transparency across India. The platform enables citizens, lawyers, law students, researchers, journalists, and judicial professionals to access legal information, understand judicial processes, explore case precedents, and improve legal literacy through a multilingual AI-powered ecosystem. Instead of replacing judges, courts, or legal professionals, NyayaBloom serves as an intelligent legal knowledge assistant that simplifies legal information and promotes informed civic participation.

MedStruct AI is an offline AI-powered medical document structuring system that extracts structured information from prescriptions using OCR and local LLMs.

AI-powered receipt management system that extracts, organizes, and securely stores receipt information using OCR and LLM technologies.

FieldSync - Structured data extraction system in Python

EcoSort AI is an offline-first, CPU-powered web application that transforms unstructured garbage images into structured waste intelligence. Using local AI inference, it identifies waste categories, generates structured JSON reports, and stores results in SQLite for analysis and retrieval. The system works without an internet connection, making it suitable for smart cities, municipalities, campuses, and remote environment

Offline-first, CPU-first receipt and invoice OCR, local Qwen categorization, structured expense reporting, and JSON/CSV export.

F2P Solver extracts mathematical formulas from PDF research papers and converts them into interactive Python simulations — entirely offline, on CPU. Upload a paper, and for every formula you get a callable Python function plus a live chart with sliders for each variable: drag a slider and the curve updates instantly, with no further AI calls. Built with Streamlit, pymupdf, ollama (Qwen2.5-7B), numpy, and Plotly. Runs on any Linux/macOS machine with a single command: ./run.sh.