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.

Verity — Fact-Checking for the Rest of Us

Verity turns any claim into a traceable verdict. Multi-model consensus checks headlines, stats, and posts against real sources in seconds running live on AMD GPU's via Fireworks AI ,Gemma and Huggingface's APIs, open and inspectable, not a black box.

Verity

HuggingFace HubGithub CopilotCodex+3

Claption

Claption turns short videos into accurate captions in four tones: formal, sarcastic, humorous-tech, and humorous-non-tech, using Fireworks AI with a judge-and-repair loop.

2Clouds

AI/ML APIQwen3Generative AI Studio

Video Captioner

Vision-based video captioning pipeline using Gemma 4 31B. Analyzes video frames,nbuilds scene understanding, generates 4 caption styles with automatic quality scoring.

CrazyCherry

AI/ML APIWhisperGemma+1

Vdcap.AI

An AI-powered video captioning platform that generates 4 distinct caption styles (Formal, Sarcastic, Tech-Humor, Casual-Humor) and burns them using FFmpeg, displayed in a synchronised 4-quadrant player with rich export options.

Imaginary_coders

AI/ML APIrest apiQwen3-VL+1

PrepAI

AI-driven interview-prep platform with CrewAI agents, FastAPI orchestrator and a Vite/React frontend; integrates Fireworks LLM via litellm, curriculum/web/database tools and agent workflows to generate practice sessions, quizzes and evaluation pipelines.

is AI real or artificial

AgentOpsAMD ROCmAntigravity+6

Context-Aware Video Captioning

An adaptive AI video agent that intelligently extracts frames and generates highly creative, persona-driven captions (formal, sarcastic, tech, and meme humor) using the Qwen Vision model.

purpleCat

AntigravityQwen3-VLOpenAI+2

Probably runs on Samsung S25

Hybrid AI router that intelligently routes user queries between deterministic tools, local OpenVINO models, and Fireworks AI, optimizing for accuracy, latency, and cost while minimizing unnecessary remote API calls.

Rage Quitters

AI/ML APIChatGPTCodex+26

Kaaval Assurance: Verify, Don’t Predict

Kaaval is the control gate between enterprise AI models and real-world actions: it enforces company policy, escalates failures, and produces an audit receipt for every decision.

KaavalAi

AMD Developer CloudAMD ROCmGemma

Cognexa – Hybrid AI Routing Platform

Cognexa is a hybrid AI routing platform that intelligently classifies user requests, executes simple tasks locally, and escalates complex queries to Fireworks AI only when needed—reducing latency, API costs, and unnecessary token usage.

Horcrux

AMD Developer Cloudrest apiAntigravity+2

Neuro-Genesis Engine

A neural network that grows its own brain mid-training. When loss spikes, a local Gemma-2-2b-it LLM writes, validates, and hot-swaps in a new expert module — no human, no restart. Verified on real AMD ROCm hardware.

Dev Duo

AMD ROCmAMD Developer CloudGemma 2+3

Crossfire :- CUDA to ROCm Migration Agent.

Autonomous AI agent that ports CUDA to AMD ROCm, validated on MI300X. Gemma 4 12B + HIPIFY-first. AMD Hackathon ACT II.

Crossfire

AMD Developer CloudAMD ROCmGemma+2

GlazeSmith : AI Digital Twin for Ceramic Glazes

GlazeSmith is a physics-grounded digital twin for ceramic glazes. It predicts how a recipe fires - crazing risk, surface, color - then renders the result live on a rotatable 3D vase, verified end-to-end. Classifiers trained on AMD ROCm.

LA FABRICA

AMD Developer CloudAMD ROCmGemma+6

Preflight AI

A dual-model DevSecOps Chaos Engine. Preflight AI mathematically maps Terraform architectures and offloads massive Monte Carlo failure simulations to an AMD MI300X GPU to prevent catastrophic cloud outages before the code is merged.

Blizzards

AMD Developer CloudAMD ROCmAntigravity+4

NexusOps – Autonomous Industrial Maintenance

NexusOps is a multi-agent AI platform that autonomously triages industrial incidents, analyzes telemetry, performs RAG-powered diagnostics, validates inventory availability, and generates explainable maintenance plans with human-in-the-loop approval.

ZenAgents

AgentOpsAntigravityChroma+6

FrameSense: Multi-Style Video Captioning Agent

A containerised agent that samples keyframes from any video clip and generates four tonally distinct captions — formal, sarcastic, humorous-tech, and humorous-non-tech — grounded in what is actually on screen.

Bang bang sauce

AI/ML APIAnthropic ClaudeGemini 3 Flash

Deadline hero

Deadline Hero ai is project design to complete tasks at time it also have some Cool features like voice nagociation

Misty

AI StudioAntigravityChatGPT

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

Veta QA

Veta is an autonomous AI agent swarm for visual, functional, and accessibility testing of Android apps and mobile web, featuring a complete sub-agent architecture running 100% of AI inference on AMD GPUs.

0x1

AgentOpsAMD Developer CloudAMD ROCm+4

Wayfinder | Hybrid Token-Efficient Routing Agent

Multi-model router using Gemma 4, DeepSeek V4 Pro, GLM 5.2 via Fireworks AI and local llama.cpp. Task-aware selection with automatic fallback, live model pricing UI, and 100% accuracy at $0.002/benchmark. Gemma Prize eligible.

ByteForge

AMD ROCmGemmaStreamlit+2

AI Driven Customer Success Onboarding Workspace

The AI-Driven Onboarding and Customer Success Workspace is a dual-purpose platform that accelerates user ramp-up through interactive, scenario-based evaluations.

NovaSphere

AI/ML APIAI Studio

Local-First Cascade Router — Track 1 v3f

A local-first AI agent that solves tasks across all 8 capability categories using a free local model wherever it can prove correctness, escalating to Fireworks only when verification fails — minimizing token cost while maximizing accuracy.

Ocellus

Gemma

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

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

MonadLabs

MonadLabs converts all data into data specialized for agents, integrates directly in company workflows, and reduces hallucination and token spending up to 85%. As API Bills surge into billions, it is the only way for enterprises to use AI efficiently.

MonadLabs

AI/ML APIOpenAIHuggingFace Hub+8

Solaris Potiguar

Solaris Potiguar is an AI-powered decision support platform that helps small rural producers optimize solar energy usage through weather forecasts, multi-agent reasoning, and automated daily recommendations accelerated by AMD infrastructure.

Solaris Potiguar

GemmaGPT 4o

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

Fairwind

Fairwind is a hybrid token-efficient routing agent for AMD Developer Hackathon Act II Track 1. It classifies each task into one of 8 categories and answers it via the cheapest reliable tier available.

Heisenberg

Anthropic ClaudeClaude CodeLLaMA

CloakWellAI - AI Safety DLP Platform

Cloakwell AI is a local-first DLP (Data Loss Prevention) platform that intercepts AI prompts, classifies PII (Personally Identifiable Information) and sensitive data in real-time, by routing queries to private AMD GPUs running Gemma 2.

Flying Tigers

Anthropic ClaudeClaude CodeAMD Developer Cloud+2

ROCmify - Automated CUDA to AMD ROCm Migration

ROCmify automatically converts CUDA codebases to AMD ROCm. It fixes what it can for free with deterministic rules, only escalates to an LLM as a last resort, and won't guess at inline PTX, catching bugs like hardcoded warp sizes no compiler can see.

Maverick_soul

AMD Developer CloudAMD ROCmClaude Code+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

30apps loaded