L

llm

MediScann — offline, CPU-first CLI that reads prescriptions and medical reports and uses a local LLM (ollama) to summarize the problem, list medications, suggest informational options, and flag warnings. No cloud, no telemetry.

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.

Fully offline document Q&A system using PyMuPDF4LLM, Ollama, and llama.cpp. Dual LLM backend with pre-commit quality gates.

A Streamlit-based research paper assistant that uses AI (RAG + PyMuPDF4LLM) for document summarization, Q&A, and multimedia analysis with local-first inference via Ollama.

A local-first Retrieval-Augmented Generation chatbot for PDF Q&A built with Streamlit, LangChain, ChromaDB, and llama.cpp

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.