P

python

https://hydrolink-iota.vercel.app/

AI-powered scam detection for Indian citizens — multilingual, free, and instant.

SoundScape is an intelligent music discovery and streaming application that helps users explore songs based on mood, genre, and personalized recommendations through an immersive user experience.

Interview Simulator

A real-time AI interview coach built with a Bun backend and Groq AI integration. This project includes:

browser-based job description and persona setup resume upload and text extraction for PDFs/DOCX/TXT live streamed interview assistant replies via SSE transcript export and review features frontend mic support and keyboard shortcuts

Use this file as the folder-level description for the project.

An AI-driven civic tech ecosystem that replaces high-cost consulting with automated business intelligence. The platform features four core pillars:

Incentive Discovery: A profile-matching engine for business schemes. Loss Calculator: Converts eligibility into concrete numbers (e.g., "You are losing ₹12.5L over 3 years") to drive immediate action. AI Rejection Explainer: Allows users to upload a rejection letter/screenshot, translating bureaucratic jargon into a plain-English "Fix Checklist." MSME Exclusion Detector: A policymaker dashboard that tracks registration vs. application rates, highlighting high-exclusion zones on a visual map for targeted governance.

WardroAI is an AI-powered wardrobe assistant that analyzes clothing items from images, categorizes them, stores them in a local catalog, and recommends outfit combinations—all while running completely offline for privacy and speed.

this is a offfline software runs on ollama

offline-first, AI-powered FIR draft assistant. Uses local LLMs (Ollama) and on-device OCR to ecurely extract structured data from sensitive complaint documents without the cloud.

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.

Based on everything you've described, your project description could be:

SignBridge AI – Real-Time Sign Language Translation & Human Perception Platform

SignBridge AI is an advanced AI-powered human communication platform that translates sign language into text and speech in real time using computer vision, machine learning, and human pose analysis.

The system goes beyond traditional sign-language recognition by combining hand tracking, finger tracking, face analysis, body pose estimation, gesture understanding, and real-time AI inference to create a complete Human Perception Engine.

Core Features Real-Time Sign Language Translation Live webcam-based sign language recognition Converts gestures into readable text Converts translated text into speech Real-time inference pipeline Continuous gesture stream processing Advanced Hand Tracking 21-point hand landmark detection Single-hand and dual-hand tracking Finger position analysis Finger angle extraction Hand orientation estimation Dynamic gesture trajectory tracking Full Body Pose Analysis 33-point body landmark tracking Posture detection Motion analysis Human action recognition Gesture-body context understanding Face & Head Analysis Face landmark detection Head pose estimation Eye tracking Facial context understanding Face-hand interaction analysis AI Vision Engine

The platform integrates multiple computer vision modules:

Hand Detection Engine Body Pose Engine Face Tracking Engine Landmark Tracking Engine Gesture Recognition Engine Sign Language Translation Engine Speech Synthesis Engine

AI-powered PDF RAG Chatbot built with Streamlit, LangChain, FAISS, and Google Gemini for intelligent document question answering.

AI-powered multilingual software architecture generator supporting Gemini BYOK and Ollama(local setup) for startup planning and MVP design.

SafeRoute AI is a machine-learning-powered road safety platform that predicts accident blackspots, analyzes route risk, and recommends safer travel routes using FastAPI, Next.js, SQLite, and XGBoost.

ResearchLens is a research support and academic consulting project that helps students, researchers, M.Tech scholars, and PhD candidates throughout their research journey. The platform provides guidance on thesis writing, research paper preparation, journal publication (including Scopus and SCI-indexed journals), literature reviews, synopsis development, and academic documentation. Its goal is to simplify the research process and help scholars produce high-quality, publication-ready work.

AI-powered decision simulation platform — multi-expert adversarial debate with real-time streaming, structured scoring, and AI-synthesised verdicts. Built for the Swecha Internship Hackathon.

Failure Archive is a platform that documents and analyzes real-world failures—including startups, products, policies, inventions, and business decisions—to help users learn why they failed, extract key lessons, and discover strategies for turning similar ideas into successful ventures. It serves as a knowledge hub for entrepreneurs, students, researchers, and innovators by transforming failure stories into actionable insights and learning opportunities.

Opportunity Radar is an AI-powered platform that discovers startup opportunities, analyzes market trends, and helps entrepreneurs identify high-potential business ideas.

A dual-mode RAG (Retrieval-Augmented Generation) chatbot. Mode 1 uses hybrid search (pgvector + BM25) with Ollama for fully local, free LLM inference. Mode 2 uses a lightweight Find-Retrieve-Answer workflow with PyMuPDF4LLM and llama.cpp for structured PDF Q&A with zero embeddings or vector database.

GalliSwad is a robust street food discovery platform built with FastAPI and React.

The Image Captioning project is an AI-based system that automatically generates textual descriptions for images. It combines computer vision and natural language processing (NLP) techniques to understand the content of an image and produce a human-readable caption.

The system uses deep learning models, typically a Convolutional Neural Network (CNN) for extracting image features and a Recurrent Neural Network (RNN) or Transformer-based model for generating sentences. This enables applications such as assisting visually impaired users, enhancing image search engines, and automating social media content tagging.