O

ollama

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").

An offline-first, CPU-optimized suite of classroom helper tools for teachers and students in low-connectivity areas. Powered by local OCR (PaddleOCR) and local Small Language Models (Qwen 2.5 via Ollama) to automate grading and flashcard generation entirely on a standard laptop

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.

Offline Medical Report Structurer

Project Description

Offline Medical Report Structurer is an AI-powered healthcare application designed to transform unstructured medical reports into organized, structured, and easy-to-understand data without requiring an internet connection. The system processes medical documents such as laboratory reports, prescriptions, discharge summaries, and diagnostic reports, automatically extracting key information including patient details, diagnoses, medications, test results, and clinical observations.

By leveraging Natural Language Processing (NLP) and document parsing techniques, the application converts complex medical text into a standardized format that improves accessibility, readability, and data management. Since the solution operates entirely offline, it ensures patient privacy, data security, and usability in low-connectivity environments such as rural clinics, hospitals, and healthcare camps.

Key Features

Offline processing with no internet dependency Automated extraction of medical information Structured JSON/database output for easy integration Support for multiple medical report formats Secure and privacy-focused data handling Quick search and retrieval of patient information User-friendly interface for healthcare professionals

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.

MedRepo is an offline, CPU-first AI application designed to convert medical Complete Blood Count (CBC) reports from PDFs or images into clean, structured JSON. The project prioritizes patient privacy by processing all data locally without requiring an internet connection or cloud services. It combines OCR and lightweight local language models to accurately extract and organize medical information for further analysis or integration with healthcare applications. Built with a modular architecture, MedRepo is easy to set up, extend, and maintain. The project aims to make medical report digitization faster, more secure, and accessible on low-resource devices while supporting future enhancements and broader diagnostic report formats.

Lightweight local-first RAG chatbot built with Streamlit, Ollama, ChromaDB, SQLite, and local quality checks.