Filters

AI Models

Data

Redis Qdrant

Platforms

Streamlit Replit Vercel

Upcoming AI Hackathons
For Innovators & Creators

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.

OmniCaption

OmniCaption is a Dockerized, dual-model hybrid video captioning pipeline extracting visual and auditory evidence to synthesize grounded, stylized descriptions (formal, sarcastic, humorous) powered natively by AMD Instinct MI300X and local ROCm compute.

VoxPersona

AI/ML APIAMD ROCmAMD Developer Cloud+2

Central Finite AI

An AI operating system for IT operations that investigates incidents, generates T24 core-banking OFS messages and routines from plain language, and routes every action through human approval before it runs.

Citadel Labs

AI StudioAssistants API

Voxly

Voxly is a context-aware dictation app that turns rough speech transcripts into polished, accurate text using personal vocabulary and project context.

Banana Duck Dev

ChatGPTCodexGemma

TruthTone: One Truth, Four Voices

TruthTone creates formal, sarcastic, humorous-tech, and humorous-non-tech captions from short videos while preserving factual accuracy and event order through evidence-grounded AI verification.

RockSolid

AI/ML APIAntigravityCodex+1

. SmartTender A

BidCraft AI uses artificial intelligence to analyze tender documents, extract key requirements, generate compliance checklists, draft proposal sections, and help businesses prepare stronger, more accurate government and private sector bids.

MORAN

Generative AI StudioGenerative AgentsGithub Copilot+2

Codyssey Captionate: Cognitive Video Telemetry

An aesthetic cognitive captioning workspace and real-time audio telemetry platform powered by Fireworks AI and AMD Cloud computing. Featuring multi-style subtitle tuning, instant Firestore sync, and dynamic interactive Recharts sentiment tracking.

Codyseey

AI StudioAI/ML APIAMD Developer Cloud+12

Raccoon Vision Translator

Watches a clip and writes four captions in four different voices: formal, sarcastic, tech humor, casual humor. All four come from the same fact-checked scene description, using Gemma 4 through Hugging Face.

Ryzen from the Dumpsters

HuggingFace HubGemmaWhisper+1

VoxFrame: Multimodal Narrative Synthesis Engine

VoxFrame is a multimodal AI engine that translates video files into highly accurate, tone-specific descriptions. Using FFmpeg, Groq Whisper v3, and Fireworks AI, it verifies visual context to eliminate hallucinations and outputs styled narratives.

CognitiveFrames

AMD Developer CloudQwen3-VLWhisper+1

Agentic Microcontroller Tester

Agentic Microcontroller Tester Agentic Microcontroller Tester

Projector_Searcher

AMD ROCmAntigravityGemma 2+2

A+ Medical Staff Allocation

A+ Medical Staff Allocation System helps healthcare administrators efficiently assign medical staff to shifts and departments, track availability and qualifications, and generate reports to ensure assistance in staff allocation using AI

Free Dev

AMD Developer CloudClaude CodeChatGPT

Siela

Siela is an agentic AI operating system that unifies leads, tasks, meetings, outreach, reminders, and team workflows. It understands context, takes action, and lets users manage work directly through WhatsApp.

etc

GemmaQwen3AWS+5

DSS BACKGROUND HANDSHAKES PROTOCOL

DSS Digital Signature Soveriengty. Background handshake Protocol

NEOXZ CORE

AMD Developer CloudGemini 3 FlashMongoDB+6

PronounceAI

Pronounce AI helps broadcasters and journalists confidently pronounce unfamiliar names, places, and organizations. Powered by AI, it delivers phonetic guides, IPA, presenter tips, and intelligent caching for faster, more reliable newsroom preparation.

Breath

AMD Developer CloudDeepSeek V3

RE-EVOLVE ON HGI

RE-EVOLVE ON HGI is an Intelligence Operating System that orchestrates multi-agent AI workflows through intent-driven planning, adaptive routing, persistent memory, governance, and specification-driven engineering for heterogeneous AI infrastructure.

CENSA

AgentOpsAI/ML APIAI Studio+13

UN DocFormat Agent

An AI document-compliance agent that turns raw English drafts into fully formatted UN Secretariat reports enforcing real DGACM/UN Editorial Manual rules using MiniMax M3 on AMD Instinct (via Fireworks AI) for fixes that need editorial judgement compliance

The Innovators

AI/ML APIAMD Developer CloudAnthropic Claude+2

TextSink — Four Voices. One Truth.

TextSink watches a video & speaks in 4 perfect tones. Gemma 4 grounds every clip in visual facts, then writes formal, sarcastic, humorous-tech and humorous-non-tech captions. Plus live styled closed captions and two AIs arguing about what they're watching

Banksy Ai

GemmaAMD Developer Cloud

ForgeMind AI–Intelligent Software Architecture

ForgeMind AI is an AI-powered software architecture assistant that transforms project ideas into complete technical blueprints, including system architecture, security recommendations, development roadmaps, and implementation guidance and etc.

Neo Dev

AI StudioAI/ML APIChatGPT+11

TRIARC

Token-efficient multi-agent router: classifies each task, picks the cheapest Fireworks model that can handle it, and escalates to a stronger tier only when confidence is low.

TRIARC

Claude CodeAntigravityAMD Developer Cloud

RollCaller

Testtesteststeststststtststsstssssssssssssssssssssssssssssssssssss

Black-Cat Hacking

GemmaOpenAI

ClassPilot: AI Co-Pilot for Live Classes

ClassPilot is an AI co-pilot for live online classes: it turns a teacher's notes into slides, converts a rough idea into a graded MCQ quiz, broadcasts it live, and returns a full results sheet the moment the quiz ends.

ClassPilot

AI/ML APIClaude Code

Drupal AI Factchecker — Claim-Level Truth on AMD

Native Drupal module that fact-checks claims against a university's own corpus, scores AI-writing likelihood, and finds verbatim plagiarism — all inference running on local AMD hardware (ROCm).

Drupal AI Router

AMD Developer CloudAnthropic ClaudeClaude Code+2

Solwash DT

A high-performance solar fleet intelligence and dispatch automation platform that calculates real-time soiling losses and automates technical field routing via WhatsApp, accelerated by an AMD ROCm pipeline and live Firebase architecture.

Solwash DT

AMD ROCmGemini AIGemini 3 Flash

DebateGenius AI – Smart AI Communication Coach

DebateGenius AI is an AI-powered communication coach that helps users practice debates, improve critical thinking, receive real-time AI feedback, and track their progress through interactive debate sessions.

Amd debate

GPT 4oAMD Developer CloudOpenAI

Yojana AI — Multilingual Government Scheme Finder

AI-powered tool that matches Indians with government schemes they qualify for — in 8 Indian languages, powered by AMD MI300X GPUs.

Vectrasource

Anthropic ClaudeClaude CodeVercel+2

VIDEO CAPTIONING

Models are accessed via Fireworks AI API credits. Fine-tuning is explicitly permitted — you may also train your own captioner and use it alongside or instead of prompting. Use open datasets, build your own, or both. used will be revealed on launch day.

team lablab winners

AI Studio

CAR(Cool AMD Router)

A token-efficient Track 1 AI agent that routes benchmark prompts locally, selects allowed Fireworks models by task type, and returns concise answers in the required Docker JSON format.

Not the previous team

ChatGPTCodex

Captionforge ai

Give it a clip and it writes four captions formal, sarcastic, humorous_tech, humorous_non_tech. All four come from the same real description of what happened, not four separate guesses, so they stay accurate while sounding nothing alike.

Metox

GroqAI/ML APIChatGPT+6

Neuralcrew-Incident-Response

NeuralCrew deploys 4 AI agents on Band SDK to automate enterprise incident response. Triage classifies, Technical investigates, Comms drafts updates, Resolution closes with post-mortem. Reduces MTTR from 30+ minutes to under 2 minutes automatically.

NeuralCrew

LangChainOpenAICrewAI+1

ContextChain: Structured Agent Handoffs

ContextChain replaces lossy context dumps with Episodic Memory Objects (EMOs) — a structured handoff primitive that preserves decisions and provenance across multi-agent pipelines. Demoed on a 4-agent procurement workflow with live SSE streaming.

Agentic Titans

AI/ML APIFeatherlessGPT-3.5+4

Synapse Fleet

Autonomous compliance intelligence — from regulation drop to board decision in minutes.

The Almonds

GroqBand IntergrationsCustom GPTs+1

30apps loaded