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.

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

Guitar Tutor AI

A gamified guitar learning platform that leverages AMD-accelerated AI for real-time audio grading, transforming daily practice into a competitive collectible card game.

Token Abusers

Anthropic ClaudeGemini 3 proAntigravity

Hybrid Token-Efficient AI Routing Agent

An intelligent AI routing system that dynamically selects the optimal language model based on prompt complexity, confidence, and token efficiency, reducing inference cost, latency, and token usage while maintaining high-quality responses.

Build Verse

AMD ROCmGPT-5OpenAI+2

Continuum: Coherent Spatial Audio Pipeline

An intelligent multi-agent pipeline that uses vision-language models and a novel memory engine to automatically generate temporally-coherent 3D spatial audio for video.

The Missing Layer

AMD Developer CloudAnthropic ClaudeAntigravity+1

WhisperLens

Containerized video captioning agent with AMD ROCm PyTorch support.

Vision Scions

GemmaGemini AIWhisper+1

LifeOS Agent: A Personal AI life assistant

LifeOS Agent is a modular, AI-powered personal OS that understands natural language, plans multi-step tasks, and proactively coordinates daily tools like alarms, calendars, and reminders through an extensible, plugin-based architecture.

taraisha

AI/ML APIGroqLangChain+2

TeamDiscovery

AI-powered pipeline that turns any video into 4 stylized captions — Formal, Sarcastic, Humorous Tech & Non-Tech — using Groq Whisper, Fireworks Vision, and DeepSeek-V4-Pro. Upload once, publish everywhere.

TeamDiscovery

AI/ML APIGroqDeepSeek V3+1

AMD-Gemma Video Captioner: Hybrid Multimodal Agent

A containerized video captioning pipeline using Kimi-2.6 VLM and DeepSeek-V4 Pro on Fireworks AMD GPU cluster. Features uniform keyframe sampling and single-call JSON styling to reduce API cost by 75% and latency by 4x.

Epoch Eclipse

AMD Developer CloudAI/ML APIDeepSeek V3

CaptionForge AI`

AI-powered multi-style video captioning for short clips using Fireworks Vision, frame sampling, and human review before publishing.

Teqprotech

AI/ML APIrest apiVercel+4

ToneLab

A pipeline that turns any 30s–2min video into four distinct captions formal, sarcastic, humorous-tech, and humorous-non-tech using Fireworks AI, scored by an LLM judge on accuracy and tone.

ctrl break

AMD Developer Cloud

Caption Pipe

A containerized multimodal video-caption pipeline that samples key frames, reasons over segmented visual evidence, builds a global factual summary, and generates grounded captions in multiple styles.

Pinna

DeepSeek V3Qwen3

Speech Transcription and Recording Assistant

ASTRA is a hybrid Windows transcription app that filters audio locally, supports offline Whisper, and connects online to a license-protected server that batches jobs, routes them across speech providers, and automatically falls back when one fails.

ProjectBuilder

CodexAI/ML APISpeechmatics api+14

SOCIELSA Hear

Personalized hearing assistance tool that uses a patient's clinical audiogram to customize AI-powered voice enhancement — built for the SOCIELSA audiology ecosystem, running on AMD GPUs.

SOCIELSA HEAR

AMD ROCmWhisperGemma+1

Ayah Video

Ayah Video turns any Quranic verse into a cinematic short-form video in 30 seconds — Arabic text, recitation audio, and cinematic background, all generated automatically.

aimers

Antigravityrest api

nuncio

Nuncio is a collaborative video personalization platform where AI agents research prospects, write personalized scripts, verify compliance, and render videos—coordinated in Band’s multi-agent workspace.

nuncio

Band Agentic MeshFeatherlessAI/ML API+1

StudioDesk

An automated multi-agent media pipeline that transforms long-form videos into platform-ready, timestamped viral shorts using a decentralized coordination network.

error 429

AI/ML APIAntigravityAnthropic Claude+4

AI Game Maker Studio

Type one sentence get a fully playable 2D game in ~60 seconds. AI Game Maker is a Game Engine that generates sprites, animations, a validated level, original music, and a running browser game from a single text prompt and support manual creation aswell.

AI Powerhouse

Gemini 3 proGemini 3 FlashClaude Code+2

Team Invincible

Speechmatics flowSDXL TurboQwen-Image-2.0+182

VoiceLens (AI Speech Confidence Coach)

VoiceLens is an AI-powered speech confidence coach that records your voice, transcribes it live, and delivers a detailed analysis of fluency, filler words, pace, clarity, and whether you should seek therapy.

Malhar

Anthropic ClaudeIBMOpenAI+1

AUDIAW

AUDIAW is a free and open-source music production software built to make professional audio creation accessible to everyone. It combines recording, editing, mixing, plugins, and live performance tools into one modern and powerful platform.

aloof_garage

Anthropic ClaudeCodexAntigravity+2

VoiceBroker AI — Autonomous Voice Trading Agent

VoiceBroker AI is a fully autonomous voice-powered trading assistant that converts natural speech into intelligent trading actions using Gemini AI, Speechmatics, Kraken APIs, and Supabase.

Team believer

AI StudioCodexMistral AI+1

CATALYST - Music Catalogue Analysis at Scale

Catalyst tells catalogue managers which songs to push, when and why. Built for catalogue funds and labels owning thousands of masters with one project manager and only forty hours a week.

Saint Philippines

FeatherlessClaude Code

Atmos - immersive player powered by music agent.

Atmos is a music experience that turns a simple moment into a visual, playable soundtrack journey.

OurChannel

Gemini 3 proGemini 3 FlashGemini AI+2

Team Invincible

ZillizYOLOv7YOLOv6+182

Frequence: Agentic Music Visualizer

An AI-powered music visualizer that uses an AMD MI300X and Qwen 2.5 to let users dynamically control visual aesthetics in real-time through natural language.

Frequence

AMD Developer CloudAMD ROCmQwen3+5

BrainSkribbl

Improve and evaluate your educational podcasts with brain-activity-optimized feedback using AI-predicted neural engagement.

Primitivo

AMD ROCmHuggingFace SpacesLlama 3.2+1

BineuralClaw

BineuroClaw is an inference-only Audio JEPA pipeline that turns speech into 256D acoustic latents, predicts 80‑band log‑mel spectrograms, and can reconstruct waveforms with HiFi‑GAN for analysis and demos on AMD MI300X.

Bineuro

Gemini 3 proAMD ROCmAMD Developer Cloud

NeuralMix

Two-stage AI audio engineer: Kimi-Audio hears your stems, a fine-tuned model trained on AMD MI300X prescribes exact professional FX parameters — specific dB, Hz, ms values, not vague advice.

BigNine

AMD Developer CloudQwen3HuggingFace Hub+2

AiJockey — Multimodal AI DJ

AiJockey turns 3-8 of your audio clips into a broadcast-quality DJ mix. A multimodal Qwen2-Audio Director hears each track, plans the set narrative, and a 5-agent pipeline (Planner → Executor → Probes → Improver) renders it on AMD MI300X.

vibeMix

AMD ROCmAMD Developer CloudQwen3-VL+2

AURA-DSP Autonomous Multi-Agent Audio Restoration

AURA-DSP is an autonomous multi-agent AI pipeline for digital signal processing. Utilizing AMD ROCm and vLLM, it intelligently separates, analyzes, and enhances audio tracks, optimizing complex engineering tasks through automated agentic workflows.

Pathfidher Studios

Qwen3-CoderAMD Developer CloudAMD ROCm

30apps loaded