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.

SovereignSwarm: Auto Multi-Tone Video Captioner

SovereignSwarm is an autonomous video captioning engine using Fireworks AI and OpenCV to extract chronological frames and generate structured, multi-tone captions (Formal, Sarcastic, Humorous Tech, Everyday) in an enterprise-ready JSON format.

Sovereign Swarm

StreamlitAntigravityGemma

CaptionDB

CaptionDB is an AI-powered video caption and scene analysis platform that automatically detects scenes, extracts keyframes, understands visual context, and generates high-quality captions using a scalable asynchronous AI pipeline.

CaptionDB

AntigravityChatGPTCursor

YouTube Growth Copilot

AI-powered YouTube analytics platform that transforms real channel data into actionable growth strategies using deterministic analytics, machine learning, and Llama-powered insights.

katana

AI/ML APIGroqLLaMA

ReelBudget

Reelbudget is an AI pre-production tool for indie filmmakers and enterprise marketing teams. Powered by the AMD MI300X, it instantly turns text briefs into true animated video storyboards and budget estimations, saving weeks of planning.

Magneto

AI/ML APIAMD Developer CloudAnthropic Claude+9

XYZ123

Generates accurate captions for short videos in four distinct styles—formal, sarcastic, humorous-tech, and humorous-non-tech—using AI-powered video understanding to create engaging, context-aware summaries with consistent formatting and tone.

xyz123

Qwen3GemmaChatGPT+2

ReachIQ AI - Competitive Intelligence Engine

ReachIQ AI's Video RAG engine ingests competitor YouTube videos, builds a vector knowledge base, and generates strategic competitive intelligence reports — powered by Gemma 3 4B running natively on AMD Developer Cloud via ROCm + vLLM.

InstinctAgent

AI/ML APIAMD ROCmGemma+5

ClipContext

Upload a clip. Get the top 5 titles, descriptions, and hashtag sets — picked by an AI discriminator from 10 independently generated candidates per category, grounded in what your video actually says and shows and whats currently trending on youtube.

Kira

AMD Developer CloudWhisperAI/ML API

GemmaForge: AI Re-Voicer & Video Generator

An AI platform that creates video parodies by re-voicing existing footage or generating 9:16 vertical short-form videos from scratch using Moonshot Kimi K2.6, FLUX.1, and Google Gemma models with an asynchronous multi-threaded Streamlit interface.

VibeCode Lab

Gemma 2Streamlit

Four Voices — Video Captioning Agent

A multi-model AI pipeline that analyzes video frames chronologically and synthesizes verified captions across four distinct tonal registers.

Just script it

Gemini 3 FlashGemini 3 proOpenAI+1

Dragon Den

A group of dragon friends come together to livechat.

Good Omens

AMD Developer CloudCodexQwen3+1

Persona Studio AI

PersonaStudio AI maps a video's core meaning via text transcription or Gemma 4 vision into a reusable "Content DNA" payload. Users can instantly transform this single blueprint into multi-platform content without ever re-analyzing the video.

Trionda

AMD ROCmAMD Developer CloudGroq+2

VoxBox

VoxBox is a consent-first voice cloning marketplace: actors publish AI clones of their voice under explicit, scoped consent, and renters pay per-generation to use them.

Pulsar

AMD Developer CloudAI/ML APIAnthropic Claude+2

track one project

A cost-aware AI agent that routes each question to the cheapest backend that can answer it correctly — a free local model for simple tasks, Fireworks only when accuracy demands it.

KAMEKAZI

Anthropic ClaudeChatGPTQwen3

CaptionForge AI–Multimodal Video Captioning Agent

CaptionForge AI is a production-ready multimodal video captioning agent that analyzes video, speech, OCR text, scene transitions, and temporal context to generate accurate captions in formal, sarcastic, humorous-tech, and humorous-non-tech styles.

Blue Horizon

AMD Developer CloudQwen3-VLYOLOv8

TernRoute

TernRoute reads a batch of natural-language tasks, determines their category and output constraints locally, and routes each task to an allowed Fireworks AI model. It spends no model tokens on routing and writes validated results atomically.

Paatras

Claude CodeAntigravity

AuraCaptioner: Grounded Multi-Style Captions

Two-stage video captioning agent: Chain-of-Verification grounding feeds four distinct-tone captions, with a self-judge regeneration pass and a fail-safe pipeline that guarantees valid, complete output on every run, even under model or infra failure.

AuraStorm

WhisperAntigravityAnthropic Claude+2

Prism - One clip, four voices, single Gemma brain

Prism refracts 1 clip into 4 caption styles: formal, sarcastic, tech-humor and everyday-humor. Gemma-4 authors every word, EmbeddingGemma verifies the facts, Gemma3n hears & transcribes, & a voice speaks (replace by T5Gemma STT). 4 Gemma models, 1 agent.

Bhramam

AMD Developer CloudGemmaHuggingFace Hub+1

CaptionForge AI

CaptionForge AI - A multimodal video captioning platform that generates captions in four styles (Formal, Sarcastic, Humorous-Tech, Humorous-Non-Tech) using AMD MI300X GPU-accelerated AI via Fireworks AI.

pookie rangers

AI/ML APIAI StudioAMD Developer Cloud+4

ChronosCap: Multi-Modal Semantic Video Captioner

A multi-modal video captioning agent that utilizes adaptive scene-change sampling, multimodal perception (VLM, Speech, OCR), and a unified semantic contract reasoning engine to generate four distinct, factually-accurate styled captions in a single pass.

RED_LAGS

AntigravityCodexGemini 3 Flash

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 video captioning engine that turns clips into accurate, style-specific narratives. It uses FFmpeg, Groq Whisper, and AIMLAPI-powered Gemini models to verify visual context before generating polished captions.

CognitiveFrames

WhisperGroqAI/ML API+2

Nexus Vision

A containerized video captioning agent that generates four distinct caption styles — formal, sarcastic, humorous_tech, humorous_non_tech — per clip using Fireworks AI vision models, built for AMD Hackathon Act II Track 2.

AI Monarchs

AntigravityOpenAIAMD Developer Cloud+1

Four Takes - The AI Captioning Studio

The only video captioning studio that QCs itself. Gemma locks the facts, then writes four calibrated voices — formal, sarcastic, tech & non-tech humor — each caption pre-judged for accuracy and tone before you see it. Gemma-first on Fireworks AI.

TheMaker

Gemini 3 proAnthropic ClaudeAntigravity+9

RocPorter

RocPorter automates CUDA-to-ROCm migration by converting CUDA to HIP, analyzing compatibility, estimating engineering effort, and producing detailed migration reports that help developers confidently move workloads to AMD GPUs.

larpers

AMD Developer CloudAMD ROCmOpenAI+1

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 V3OpenAI+1

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

Tetrlense ai: Style-Conditioned Video Captioning

Tetrlense ai is a style-conditioned video captioning agent built for the AMD Developer Hackathon. Using Fireworks AI's Kimi K2 model, it generates high-fidelity, adaptive video descriptions across four distinct styled personas with extreme low latency.

VectorForge AI

AMD Developer CloudAntigravityGemini AI+2

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

Hacienda - Video Captioning Agent

Hacienda is an autonomous video-captioning agent. It samples keyframes, builds a factual scene analysis with a vision model, then writes four distinct captions per clip - formal, sarcastic, tech humor, everyday humor - in Docker, minutes per batch.

Hacienda

OpenGPTsAnthropic Claude

30apps loaded