Public showcase

People overproduce at noon, underproduce at night, and the whole system leans on a centralized grid that charges high fees, wastes potential local supply, and fails to reward cooperative behavior. Buyers don’t know if they’re being overcharged. Sellers don’t know if they’re being exploited. And nobody has tools to simulate or understand the consequences of different trading rules or market mechanisms. The project is built to attack this chaos by: • letting communities share energy peer-to-peer instead of funneling everything through a big utility • using game-theoretic pricing, AI agents, and transparent rules so no one gets scammed • providing simulation and visualization tools so users can test market mechanisms before deploying them • making the system stable, incentive-aligned, and resistant to freeloaders, hoarders, and all the other delightful human behaviors that ruin shared resources In short: The world is moving toward decentralized clean energy, but there’s no mechanism ensuring fairness, efficiency, or trust. This project tries to create that mechanism. Whenever you’re ready to interrogate the “creator,” I’ll sit in the metaphorical witness box and pretend I’m not slowly vaporizing on the inside.

Imagine a world where learning to trade doesn’t start with loss, fear, or blind guesses, but with confidence, practice, and real understanding. MINT is the bridge between curiosity and competence in the financial world. It creates a living market classroom where beginners don’t just watch charts they trade them, test them, and learn from them without risking real money. We built a time-machine for traders a platform that replays real historical markets, lets users place virtual trades, analyzes their decisions, and teaches them why they were right or wrong. MINT transforms confusing charts into conversations, turning data into intuition through AI guidance, simulations, and interactive lessons. In simple terms: We turned the stock market into a safe playground for learning. MINT converts chaos into clarity, hesitation into confidence, and theory into real skill. Because once people can practice without fear, they don’t just learn trading they master it. MINT where beginners become investors, and fear becomes strategy.

building a supercomputer from idle computers for heavy tasks which take a long time to run on one computer

TripGenie – AI Travel Copilot TripGenie is an AI-powered travel companion that plans, re-plans, and guides travelers in real time. It offers intelligent itineraries, voice assistance, and sustainable travel recommendations using live data.

We have a built a system wherein villagers or any person can easily know where can he/she get water from nearest water source. Our project tackles this very problem by introducing sms system where user prompts the unique water source id and a bot replies to the user whether the water is available or not by searching the database which keeps updating every hour by a sensor employed by us. This is a simple yet powerful solution to solve this very problem

ATLAS is a single-session Al scrapbook tool that transforms a small batch of ordered photos into a continuous, ghostwritten story. You quickly validate Al-generated captions for each photo, and ATLAS uses that verified context to craft a cohesive, hallucination-free narrative. The result is an interactive digital flipbook where every page pairs your memories with rich, personalized storytelling.

we built a website where users can check bus details using their ticket id or either by chosing the pickup and destination point. They can also book their fare and check recent logs of buses with their estimated arrival time.

Insight Spark is a smart feedback and survey platform that enables real-time feedback collection, summarization, and visualization across three interactive dashboards — for students, teachers, and societies. Teachers and societies can easily create and upload feedback forms related to events, workshops, or classes. These forms automatically appear on the student dashboard, where students can submit their responses. Once feedback is submitted, the platform’s backend instantly analyzes and summarizes all responses using AI and displays live visual analytics — helping teachers and societies gain quick, actionable insights into participant satisfaction, engagement, and suggestions. Insight Spark bridges communication gaps by transforming raw feedback into meaningful, data-driven insights — all in real time.

We built a complete digital lost-and-found system for Thapar University featuring: ->A public inventory of found items uploaded by admin. ->A secure claim system for students to prove ownership. ->A full admin dashboard to register items, archive them, and manage claims. ->Firebase-powered authentication, database, and storage. ->Fully responsive frontend hosted on Vercel. It replaces the messy physical lost-and-found registers with a modern, reliable, scalable solution accessible to every student.

Imagine a workforce that keeps an entire planet’s economy running: delivering food, moving people, shipping packages, freelancing skills; yet remains financially invisible because their earnings don’t follow Earth’s traditional “monthly paycheck” ritual. HyperGig+ is the universal translator between this new workforce and the banking systems that can’t understand them. We built a digital identity layer for gig workers; one that reads their earnings from multiple platforms, analyzes their work patterns, calculates their financial stability, and converts it all into a trustable credit score. In simple terms: We taught banks how to understand the gig economy. HyperGig+ turns chaotic, multi-source income into a clean financial fingerprint. Once gig workers become visible; they become creditworthy. Once they become creditworthy; they become empowered. HyperGig+ a bridge between two species who till date never spoke the same language: gig workers and the financial system.

TruSheild PRO is a next-gen AI deepfake forensics engine built to defend creators, brands, and governments against the rise of hyper-realistic synthetic media. Unlike traditional detectors that rely on single-model heuristics, TruSheild PRO uses a multi-modal transformer pipeline combining visual forgery detection, voice-clone identification, lip-sync analysis, semantic drift tracking, and diffusion fingerprinting. The system extracts signals from frames, audio, spectrograms, gestures, semantics, and LLM-based linguistic patterns, fuses them with a weighted trust-score engine, and produces a complete forensic report with heatmaps, radar-diagnostics, and explainability. We built two versions: Creator Edition — simple interface for influencers, journalists, and everyday users. National Security Edition — an expanded, high-sensitivity model designed to evolve into a government-grade forensic toolkit. Our philosophy: “India needs trustworthy media verification. As citizens first, we built TruSheild PRO to contribute to digital safety at scale.” Jai Hind 🇮🇳

Recypher AI is an intelligent waste segregation and disposal guidance platform designed to simplify and improve everyday waste management using artificial intelligence and interactive assistance. The project addresses the widespread confusion people face when deciding whether an item is recyclable, organic, or hazardous, which often leads to incorrect disposal, contamination, and environmental pollution. The system consists of an Android application powered by on-device AI that allows users to scan any waste item using their phone camera. A TensorFlow Lite model instantly classifies the item and provides clear, easy-to-understand disposal instructions. If the item requires responsible disposal, the app displays nearby waste and recycling centers sorted by distance and guides the user to the appropriate location through integrated map navigation. To further enhance accessibility and real-time support, Recypher AI includes an AI-powered chatbot that acts as a virtual waste management assistant. Users can ask questions such as “Where should I throw this item?” or “Is this recyclable?” and receive instant, simplified responses. This chatbot bridges the knowledge gap for users who may not always rely on scanning and helps educate them on best waste practices. To ensure real-world accountability, Recypher AI integrates QR-based disposal verification. When a user reaches a disposal...

This platform is a disaster relief coordination system that uses OpenStreetMap (OSM) for real-time tracking of victims, volunteers, shelters, and resources. Volunteers’ locations are displayed live, enabling efficient routing and task assignment. It uses various algorithms to prioritize urgent requests, predict resource shortages, and form smart volunteer teams. By combining geospatial mapping with AI insights, the system ensures faster, data-driven disaster response, improving coordination and saving lives.

WealthPlay is a calm, beginner-friendly way for students and young earners to learn about money without the fear of losing it. Instead of overwhelming users with jargon or real financial risks, WealthPlay creates a safe space where they can practice real-life money decisions through simulations, scenarios, and soft-gamified progress. The platform is guided by a supportive AI mentor that explains concepts in simple language, helps users reflect on choices, and builds confidence step-by-step. From managing a first salary to planning an emergency fund, WealthPlay turns financial learning into something intuitive, safe, and empowering. Our goal is simple: make financial confidence accessible to everyone, especially those who are just starting their money journey.

Students today juggle a messy mix of information—handwritten lecture notes in notebooks, scattered PPTs, random screenshots, and stacks of PDFs. While each piece is valuable, they rarely connect into a single, usable source of truth. Instead, knowledge remains fragmented across formats and devices. As a result: • Students waste hours searching for “that one slide” or flipping through half-filled notebooks • Revision becomes inefficient because insights are scattered rather than structured • Connections between lecture notes, research papers, and classroom slides are easily missed • Valuable personal notes often remain trapped on paper, inaccessible for digital use Even those who try to stay organized face challenges: • Manual digitization of notes is time-consuming and error-prone • Existing OCR tools capture text but fail to preserve meaning or context • There is no seamless way to merge handwritten content with digital material into a single knowledge base There is a clear need for a solution that: • Uses OCR to capture and digitize handwritten notes with accuracy • Aligns these notes with digital slides, textbooks, and research papers to create a unified view • Generates query able summaries, turning fragmented material into a dynamic, searchable “living textbook” • Supports semantic alignment,...