P

python

FieldSync - Structured data extraction system in Python

VoxSQL is an offline-first, CPU-first data assistant that converts unstructured or semi-structured student data into structured SQLite tables. Users can upload CSV, Excel, or text files and ask natural language questions like “show students from section A” or “show students with marks above 90.” The app converts the prompt into a safe SQL query, runs it locally, and displays the result as a table and JSON output. VoxSQL works without cloud AI APIs, uses local processing, and is designed for privacy-friendly offline data querying.

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

This project is about the noise pollution. This project helps people stay safe from the areas where noise pollution are more than 70DB, which is directly dangerous for the people who has the issues with noise. This project focuses about the real time problem of noise in Hyderabad.

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

CPU-first offline Streamlit study assistant that extracts local study files, generates summaries, flashcards, and MCQs, and stores progress in SQLite under AGPL-3.0-or-later.

CivicTruth is a Retrieval-Augmented Generation (RAG) platform that enables transparent, citation-backed question answering over legislative and policy documents.

Offline-first Local AI application that converts resume PDFs into structured JSON & CSV using PyMuPDF4LLM, Ollama and SQLite.

JanaSeva AI

JanaSeva AI is an AI-powered citizen assistance platform designed to simplify access to government services. Instead of searching through multiple websites, users can ask questions in natural language and receive step-by-step guidance, required documents, eligibility details, and official government resources for services such as Aadhaar, PAN Card, Voter ID, certificates, scholarships, and welfare schemes. The system reduces information overload and makes government services more accessible, especially for first-time users.

An AI-powered offline disaster relief intelligence system that enables emergency communication, resource management, and situational awareness in low-connectivity environments using machine learning and local data processing.

DocWise is a Python-based document processing and automation system.

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.

Our assistant addresses the challenge of navigating fragmented and massive match data from the IPL 2026 season. Currently, cricket fans and analysts struggle to extract specific match statistics or venue-specific performance metrics from raw CSV datasets without advanced data analysis tools.

This project is an offline-first, CPU-only AI app that converts unstructured inputs like documents or images into clean structured data locally on the user’s device. It uses local OCR, small on-device models, and SQLite storage to extract key details, validate them, and help users quickly turn messy files into usable records without needing the internet.

Offline-first CPU AI study assistant that converts PDFs, images, audio, and text into structured SQLite knowledge.

Water Issue Tracker - Civic complaint system using Streamlit

Local-first RAG platform with ChromaDB, Ollama, Groq BYOK, semantic retrieval, document intelligence, and business insights.

Multimodal RAG chatbot supporting PDF, Word, text, and image QA using Gemini and ChromaDB.

Student Study Planner is a Streamlit-based application that enables students to organize their studies efficiently through subject and task management, automated study planning, progress analytics, AI-powered study assistance, and English/Telugu language support.