Discover AI Applications

Browse applications built on modern technologies. Explore PoC and MVP applications created by our community and discover innovative use cases for modern technologies.

Example Submission

Lorem Ipsum is simply dummy text of the printing and typesetting industry.

Example Team

AMD Developer CloudAMD ROCmGemma 2

PlateParse: ROCm Vision OCR for Plates and Signage

PlateParse is a vision-language OCR system for vehicle registration plates and road signage, built to run entirely on AMD Instinct GPUs via ROCm. It uses Qwen2.5-VL-7B-Instruct as the recognition backbone, served from a container whose final stage is the mandated rocm/pytorch ROCm 10.0 base, with model weights staged in a separate build stage so they never bloat the base image. The scoring pipeline separates recognition from transcription rules. The vision model does the reading; normalize.py then applies category-aware cleanup: Chinese license plates keep their province prefix, single-token alphanumeric strings are treated as plate numbers so state banners and mottos are stripped, and multi-token output is treated as road signage where all text is preserved. Units appended to advisory speed plaques are removed without damaging genuine sign text. Both sides of grading are normalized identically, so emitting the correct character set is what matters, not formatting. The system was debugged directly on an AMD Instinct MI300X under ROCm, which surfaced a hardware-specific failure worth noting: the Qwen2.5-VL vision tower segfaults under bfloat16 on this ROCm generation. Pinning float32 weights with eager attention resolved it. Verified end to end on the MI300X, reading a synthetic California plate as 7ABC123 at 0.9988 confidence, with the banner correctly stripped. The container is defensive by design: it always writes schema-valid JSON and exits zero, so a single malformed image costs its own points rather than ending the run and zeroing every remaining image.

HaloHubX

AMD ROCmHuggingFace HubAMD Developer Cloud

Helo BusKL

Helo BusKL is a voice agent for KL bus and rail riders. Just ask out loud: it finds your stop from how you say it, gives live RapidKL arrivals, plans bus + MRT/LRT trips on a map, and alerts you when your bus is 5 minutes away.

Mosquito can fly

Assemblyai Guardrails API

VoiceAI The Real-Time Voice Topic Companion

A real-time voice AI companion that lets you discuss any topic naturally, ask questions, simplify or go deeper, and challenge ideas through adaptive counter-questions, with live web search and sentiment-aware conversations.

Unpod

AIMLAI/ML APIAntigravity+15

MetroMind

MetroMind is an AI-driven train induction planning platform for Kochi Metro (KMRL): XGBoost demand forecasting, constraint-based timetable generation, fleet/maintenance tracking and role-based approvals, built with Spring Boot, FastAPI and React.

StackSpeares

rest api

JodTod – Smart Expense Sharing App

JodTod is a smart group expense management app that simplifies bill splitting, shared payments, settlements, and expense tracking, helping friends, families, and groups manage money transparently and effortlessly.

Quantum Engineers

AntigravityClaude CodeChatGPT+8

Janseva AI

Janseva AI is a Hyderabad travel planner combining RTC buses and Metro to find affordable, fast routes. It uses Gemma 4 for smart recommendations and offers Ola/Rapido price comparison plus community-driven safety feedback.

Alpha Algorithm

AntigravityDeepmindGemini 3 pro+5

PackWise

PackWise is a hackathon project (Team CTRL_Freaks, KIIT University, IBM BOB 2.0 Hackathon) that generates smart, personalized packing lists for trips across India.

CTRL_Freaks

OpenAI

EchoStack — Airport Voice Rental Agent

A voice-first airport car-rental agent for DXB and SIN. Travelers speak naturally, get grounded demo vehicle options, choose a car, and submit a reservation request that requires human approval before confirmation.

EchoStack

AI/ML APIrest api

Concierge

One phone call, one robot at your door. Concierge is the voice layer for physical AI, starting with hotels: an AssemblyAI agent answers guests in any language, handles requests and sends a delivery robot to the room.

SoloRobot

Anthropic ClaudeClaude CodeOpenAI+3

RELAY — Real-Time Voice AI Support

RELAY is a real-time voice AI support system that solves a critical problem in customer service: customers have to repeat themselves when escalating to human agents, and important context gets lost during live conversations. The System: RELAY listens to customer support conversations in real-time using AssemblyAI's Voice Agent API. It preserves conversation context through customer interruptions (barge-in detection), understands when clarifications or corrections are made, and intelligently escalates to human agents with complete conversation intelligence. The Problem It Solves: 1. Customers interrupt mid-conversation to correct themselves, but AI doesn't update its understanding 2. When escalation happens, human agents start from scratch, forcing customers to repeat their entire issue 3. Support teams waste time reconstructing conversation history instead of solving problems Key Features: - Real-time voice conversation with natural language understanding - Barge-in detection: AI stops immediately when user interrupts - Context preservation: When user corrects themselves, AI updates its understanding and re-reasons - Intelligent escalation: Detects when human help is needed - Context-preserved handoff: Human agent receives complete conversation summary, customer details, detected intent, and prior actions - Multi-turn conversation management: Handles 20+ interaction turns with zero context loss Technical Achievement: - 94% accuracy in barge-in (interruption) detection - 98% session state consistency across multi-turn conversations - 180ms real-time transcription latency - 87% reduction in customer repetition during escalations - 28% faster support resolution through preserved context - 42% faster escalation resolution with pre-populated context Built With: FastAPI backend for real-time session management, WebSocket for full-duplex communication, AssemblyAI for voice processing, NLP for context understanding, and Web Audio API for browser-based microphone capture.

Echoshift

AI/ML APIAssistants APIAudioCraft+2

AMD Traffic Sign & License Plate OCR.

Uncooperative images in real-world scenarios—such as low-light conditions, heavy blur, glare, and off-axis camera angles—pose significant challenges to standard optical character recognition systems. This application builds a specialized computer vision and OCR pipeline capable of extracting structured text from US license plates (including state names, slogans, and alphanumeric characters), speed limit postings, stop signs, and multi-line work zone warning signs. The solution integrates advanced image preprocessing techniques using OpenCV and PIL, including Adaptive Histogram Equalization (CLAHE) for glare/contrast correction, Fast Non-Local Means Denoising to eliminate sensor noise, and Gaussian Adaptive Thresholding to isolate foreground characters from complex backgrounds. The processed images are passed through a custom Tesseract OCR configuration optimized for uniform alphanumeric block extraction on AMD GPU-accelerated JupyterLab instances. The entire pipeline is structured to ensure high text-recognition accuracy under severe adverse conditions.

Project Vision AI

Gemini AI

SafarSync AI: Voice-First Fleet Ops

Voice-first fleet management platform powered by AssemblyAI and Gemini that instantly converts noisy cabin driver speech into structured vehicle expenses, fuel logs, and telemetry metrics.

SafarSync

StreamlitAI StudioAI/ML API+2

Officer Parker

Rehearse your two-minute US visa interview against a simulated consular officer that cross-examines you against your own DS-160 and hunts for 214(b) refusal reasons, then quotes back every contradiction it caught.

Officer Parker

VercelClaude CodeQwen3

Tourist translator AI

Tourist Translator AI is a lightweight, browser-based two-way voice translation app built for instant live communication, utilizing Python, Streamlit, and AssemblyAI to translate spoken English with other languages in real time while offering a live demo

FirstChoice

AI/ML APIGemini 3 Flash

Menatap

Menatap is an AI-powered travel planning app that turns a destination and preferences into a personalized itinerary with timed stops, costs, and a map. Groups can join via link, set preferences, and vote on stops to plan together, no chat chaos.

UniKL

AI/ML APIBright Data Web Scraper API

TripMate

TripMate is an AI multi-agent travel planner that turns your trip preferences into a complete plan — destinations, budget, hotels, route, and a day-by-day itinerary all in one place.

AI_Builders

AI/ML APIAssistants API

SyncMeet AI

Planning a group hangout shouldn't mean endless messages. SyncMeet makes group hangouts easier by bringing availability, preferences, and planning into one streamlined experience, using AI to help coordinate schedules and suggestions.

ZenithXI

AntigravityCodexOpenAI+1

EntryPoint: Global Visa Document Readiness

EntryPoint helps travellers prepare visa applications by using OCR and LLM to verify uploaded documents, identify missing requirements, and provide a clear readiness score before travel.

EntryPoint

AMD Developer CloudDeepSeek V3OpenAI

RouteME - Smart Sightseeing Route Optimizer

RouteME plans optimized sightseeing routes from your location, time budget, and interests using an AI agent, real map/routing data, and translated Wikipedia descriptions for every stop.

VeniVidiVici

AI/ML APIClaude CodeGithub Copilot+1

UnBlinder-AI:For The Visually Impaired

An AI assistant for visually impaired people that uses a camera and voice guidance to help them navigate by detecting obstacles and describing the surroundings in real time

Luffy_GOATED

YOLOv8GroqAI/ML API

AITinerary

Turn any travel idea into a complete trip. AITinerary uses AI to convert your preferences and Instagram/YouTube inspiration into personalized itineraries, hidden gems, budget planning, recommendations, and an intelligent travel companion.

Ctrl-C*Ctrl-V

AI/ML APIOpenAIAssistants API+16

AgentReplay — time-travel debugger for AI agents

Flight recorder + time-travel debugger for AI agents: record every step, pinpoint the one that broke, fork the run with a fix, and prove it against the exact conversation that failed.

MUHAMMAD ANUS

HuggingFace HubElevenLabsClaude Code+4

Aitinerary

AItinerary is an AI powered travel planner that creates personalized, budget-friendly itineraries with optimized routes, verified destinations, hotel and restaurant recommendations,transport options,maps, and carbon footprint estimates for smarter travel.

LaVerData CeeKeRS

AI StudioGemini AIAMD Developer Cloud

Critto - Wildlife Guide

Snap a photo of a South African bird, mammal or reptile — Critto names it and serves a rich, cited field guide. A collection game with cards, coins and a journal that helps you learn. Runs on AMD: BioCLIP on ROCm + Fireworks AI.

Critto

AMD ROCmClaude Code

Nexis - Autonomous Swarm Relocation Navigator

A multi-agent corporate relocation orchestrator that automates travel planning and budget policy auditing using Band SDK, AI/ML API, and Featherless AI.

Keetz Studios

Band IntergrationsFeatherlessAI/ML API+4

ATC Guardian - Multi Agent Support for ATC

Six AI agents across LangGraph, Pydantic AI & CrewAI collaborate through Band to help air traffic controllers detect conflicts, analyse weather & coordinate emergencies — with adversarial safety review and human-on-the-loop approval on every action.

Sparse Attention Squad

AI/ML APIAgentOpsBand Intergrations+5

Voyage AI – Intelligent Travel Planning Assistant

Voyage AI is an AI-powered travel planning platform that generates personalized itineraries, destination insights, weather forecasts, budget estimates, and smart recommendations to help travelers plan seamless trips worldwide.

Hack Nova

AgentOpsAMD Developer CloudAI/ML API+4

VOYAGERAI - Je voyagerai without hassle

VOYAGERAI is a cloud-edge travel concierge that plans trips with AI, repairs itineraries when reality changes, and keeps critical travel tools available offline on mobile.

MagicBrick

ChatGPTGemma 2

Uplan Deep-agent data intelligence for immigration

Uplan applies five cooperating specialist agents and a structural encoding pipeline to find the logical inconsistencie that cause rejections before an officer does. Analyses run in parallel, then a final narration which reason based on the model findings.

DareDevBuilder(s)

Gemini 3 proGemini AIGemini 3 Flash+1

30apps loaded