O

open-source

LocalSlate is an offline-first, CPU-optimized AI incident processing system that converts unstructured text, audio, and voice reports into structured actionable data using a FastAPI backend, local AI workflow, and MySQL persistence.

An open-source, modular public transport routing engine built with Python 3.13+. It abstracts external transit APIs behind a resilient service layer to compute efficient multi-modal routes with integrated caching and strict compliance.

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

AgriGuard AI is an AI-powered, offline crop disease detection and agricultural advisory system that uses computer vision and deep learning to identify crop diseases from images, estimate disease severity, and provide treatment and prevention recommendations. Designed for farmers and agricultural professionals, the system operates without an internet connection, ensuring reliable field deployment in remote areas while promoting sustainable and precision agriculture

AgriDoc is a CPU-first, offline-first web app that helps India's farmers digitize and manage their critical agricultural documents — Pattadar Passbooks, Adangal records, PM-KISAN certificates, Rythu Bandhu slips, and more.

ClauseGuard is an AI-powered offline legal document analyzer that detects risks, simplifies contracts, and protects user privacy.

Local AI: Offline Meeting Intelligence System is a CPU-optimized, offline-first application that transforms unstructured meeting audio recordings into structured and actionable data. Using Faster-Whisper for local speech transcription and Qwen2.5 GGUF via llama.cpp for information extraction, the system converts audio files into structured JSON containing meeting summaries, topics, action items, and next steps. All processing is performed entirely on the user's device without internet access or GPU acceleration, with results stored locally using SQLite and displayed through an interactive Streamlit dashboard.

ZenShe – Women's Safety & Emergency Assistance Platform*

ZenShe is a women-centric safety application designed to provide quick access to emergency assistance during critical situations. The platform enables users to register trusted emergency contacts, share their live location, and trigger SOS alerts when they feel unsafe.

AI-powered open-source repository onboarding assistant that analyzes GitHub repositories and provides onboarding guidance using Gemini and Ollama.

Local-first RAG chatbot for university documents using PyMuPDF4LLM, FAISS, Groq and Llama.cpp.

Fuel Rescue System is an on-demand emergency fuel delivery platform designed to assist vehicle owners who run out of fuel while traveling. The platform connects users, petrol pumps, and delivery personnel through a centralized system that enables quick fuel requests, efficient order management, and real-time delivery tracking.

When a user experiences a fuel shortage, they can open the application, share their current location, select the required fuel type and quantity, and submit a request. The system automatically identifies nearby petrol pumps based on the user's location and sends the request to available operators. Petrol pump staff can review the request details, including customer information, delivery address, fuel requirements, payment details, and estimated distance before accepting the order.

Once accepted, the request is assigned to an available delivery agent. Delivery personnel can view customer contact information, navigation routes, fuel quantity, payment status, and order details through a dedicated delivery dashboard. The system allows delivery agents to update order statuses such as Accepted, On The Way, Reached Location, and Delivered, ensuring complete visibility for both customers and petrol pump operators.

AI-powered document chatbot with RAG, FAISS vector search, OCR support, Local AI (Ollama), and BYOK integrations for Gemini and Groq.

AI Expense Tracker is a smart personal finance management application that helps users track, categorize, and analyze their daily expenses using Artificial Intelligence. The application enables users to record transactions, monitor spending habits, and gain valuable financial insights through interactive dashboards and AI-powered analytics.

Unlike traditional expense trackers, this platform uses AI to automatically categorize expenses, identify spending patterns, generate personalized savings recommendations, and answer finance-related queries through a conversational interface. Users can upload receipts, manually enter expenses, or import transaction data for seamless expense management.

The application supports both cloud-based AI models and local AI inference solutions such as Ollama, allowing users to maintain privacy while benefiting from intelligent financial analysis. It also provides a Bring Your Own Key (BYOK) option, enabling users to connect their preferred AI providers using their own API keys.

Offline, CPU-first AI that transforms unstructured documents into structured, searchable data using local language models.

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

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

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

Uncover Truth is a full-stack, AGPLv3-licensed logic puzzle web application built using a modern JavaScript monorepo architecture. The project combines a React-based frontend, a Node.js/Express backend, and shared game logic to deliver an interactive puzzle-solving experience focused on reasoning and deduction.

The system is designed with production-grade engineering practices, including automated testing, code quality enforcement, security scanning, and CI/CD compliance pipelines using GitLab.

⚙️ Key Features 🧩 Interactive logic puzzle gameplay with shared puzzle engine ⚛️ Modern frontend built with React and Vite 🖥️ Lightweight Node.js + Express backend 📦 Monorepo structure with shared utilities between client and server 🧪 Automated testing using Vitest with coverage reporting 🔍 Code quality enforcement via ESLint, Prettier, and Knip 🔐 Security scanning using Gitleaks and npm audit 📊 CI/CD pipeline with compliance checks (GitLab-ready) 📄 Open-source governance: LICENSE, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT 🏗️ Architecture client/ → React frontend (Vite) server/ → Express backend API shared/ → Shared puzzle logic used by both client and server test/ → Unit and integration tests CI/CD → GitLab pipeline with lint, security, test, and compliance stages 🚀 Purpose

This project is designed to demonstrate real-world full-stack engineering practices, focusing on:

Clean architecture in monorepos Secure and compliant development workflows Automated testing and coverage enforcement Production-ready CI/CD pipelines Open-source governance standards

CivicPlus is a citizen grievance management platform built with React, TypeScript and Node.js.

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.