G

gitlab

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

Offline-first, CPU-first AI reader companion that narrates and analyzes stories locally using Ollama and structured feedback JSON.

Scan any invoice or bill image — AI extracts the data, builds your financial dashboard. Fully offline. CPU only.

https://vent-box.lovable.app/

HealthCamp OS: A multi-tenant platform for NGOs and doctors to manage health camps. Features Gemini AI triage, volunteer management, and responsive impact reporting.

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.

Smart Cab Finder is an AI-powered ride comparison platform that helps users compare fares, estimated arrival times, and ride options across multiple cab providers. The application includes an intelligent AI assistant for ride recommendations, supports Bring Your Own Key (BYOK) integrations, and is designed to support local AI inference through Ollama. To improve accessibility, the platform provides multilingual support in English, Hindi, and Telugu. Built using Python and Flask, the project follows secure development practices with automated testing, CI/CD pipelines, security scanning, and compliance-driven documentation.

Dream2Play AI is an AI-powered platform that transforms natural language prompts into playable games, stories, characters, missions, and worlds with support for cloud AI, local AI inference ( Ollama ), and BYOK.

Kisan Mitra AI is an AI-powered multilingual farming assistant that helps farmers with crop recommendations, disease detection, weather updates, market prices, and government scheme information.

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

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.

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 Receipt & Expense Tracker

The AI Receipt & Expense Tracker is an offline application that lets users scan receipts and automatically extract important details like shop name, date, items, GST, and total amount using OCR and AI. The data is stored in a local SQLite database and used to generate simple monthly expense reports, helping users easily track and manage their spending without manual entry.

StoryMirror CLI is a CPU-first command-line application that transforms unstructured stories into meaningful insights through local AI processing. It provides story analysis, multilingual text-to-speech (TTS), runtime performance metrics, and customizable terminal themes, all while running on a local FastAPI backend.

Designed for offline and resource-efficient environments, StoryMirror performs inference on the CPU without requiring a dedicated GPU, making it suitable for developers, students, and writers who need an accessible AI-powered storytelling tool.

Key Features 📖 Analyze stories from text or files 🎙️ Generate multilingual text-to-speech narration 🎨 Customize the CLI with multiple themes 📊 Monitor CPU usage, memory, and inference performance ⚡ Run entirely on a local FastAPI backend 💻 CPU-first design with no GPU dependency 🌐 Supports offline or local deployment 🚀 Simple command-line interface for quick workflows

FieldSync - Structured data extraction system in Python

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.

LectureLens is a secure, localized, multi-modal ingestion pipeline that transforms raw educational assets into structured, high-retention study matrices. Built entirely on an offline-first philosophy, the system intercepts dense lecture audio streams and multi-page technical PDFs, running them through an isolated edge-computing layer to generate interactive flashcards, core concept maps, and dynamic glossaries without leaking sensitive user data to third-party cloud vectors.