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.

Chaukidar

Chaukidar is a multilingual AI safety audit platform that tests whether LLMs stay safe in South Asian languages like Urdu, Punjabi, Pashto, and Sindhi, comparing English, translated, and native-adapted prompts across high-risk categories.

PunkRockers

AMD Developer CloudAMD ROCmCodex

Multi-Agent Ethical Document Reviewer

A multi-agent AI system that evaluates documents for ethical risk across Bias, Privacy, Security, Compliance, and Transparency — returning a publish decision, domain scores, high-risk fields, and remediation recommendations.

Byte_Me69

AgentOpsAMD Developer CloudGPT-3+1

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

SimuFactory

SimuFactory is a secure, on-premise industrial trainer powered by AMD ROCm. Using a Llama-3/Gemma dual-model architecture, it provides Socratic coaching and safety auditing via a live Digital Twin to train technicians without risking real hardware.

SimuFactotry

AMD ROCmAMD Developer CloudAntigravity+5

TitanAI: Attention-Free LM Engine on HIP

Attention-free language model training and inference engine written from scratch in HIP for AMD MI300X. Custom BitLinear (1.58-bit) quantized weights, int8 activations, and hand-written dp4a kernels tuned for the 64-thread wavefront architecture.

soloexpirience

AMD ROCmAMD Developer Cloud

ApexFlow AI: Self-Healing Telemetry Gateway

Quantum-classical hybrid stream gateway with 3-tier Gemma 4 ensemble on AMD MI300X (92% VRAM) + IBM Heron r2 VQC routing. Local inference at 0 tokens via Google Gemma 4 QAT. Fireworks AI fallback.

Tarek Clarke

AMD ROCmAMD Developer CloudGemma+1

StormSense AI

Real-time disaster intelligence platform powered by multi-agent AI. Autonomously monitors live earthquake, flood and wildfire data from USGS, NASA FIRMS and OpenWeatherMap, assesses risk and delivers instant alerts.

StormSense AI

AgentOpsAI/ML APIAMD Developer Cloud+12

MediSense AMD — Multimodal Clinical AI Agent

Production AI healthcare platform serving 869+ real users across 9 countries — 4 ML models + LLM on AMD MI300X via Fireworks AI, bilingual Hindi/English with WhatsApp alerts.

MediSense AMD

AI/ML APIGroqLLaMA+1

Maya Language Tutor

Maya is a real-time, voice-first AI speaking tutor — you talk, she listens and replies out loud, then instantly shows what you said, what you meant, and how a native speaker would actually say it.

Yolo street

Qwen3Custom GPTs

Shadow QA: Autonomous Visual UI Testing

Shadow QA is an autonomous testing agent that uses Vision-Language Models to navigate web apps, visually identify UI/UX bugs, and generate comprehensive QA reports without hardcoded scripts.

Team Vision Forge

VercelAMD Developer CloudAntigravity+3

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

RepoREpo

A Dockerized hybrid AI agent that routes benchmark tasks between a zero-token local Llama model and allowed Fireworks models, answering accurately while minimizing counted API tokens.

Ryzen

AI/ML APILlama 3.2Claude Code+1

PADAYON: AI Multilingual Learning Partner

PADAYON helps Filipino students turn messy notes, photos, and questions into curriculum-aligned study materials, quizzes, visuals, and personalized explanations using Gemma, Fireworks AI, and learner memory.

PADAYON

GemmaAMD Developer Cloud

TokenRouter: cheapest model that gets it right

Routes every task to the smallest Fireworks model that can handle it. Classification runs locally with regex rules, so routing costs zero tokens. Hard per-category output caps keep answers short. Same accuracy, about 60% fewer tokens in our tests.

Saberites

Generative Agents

Video Captioning Studio

Upload an MP4 to generate formal, sarcastic, humorous-tech, and humorous captions from audio and visuals. Blend styles with personalization; get auto-generated summaries, color-coded captions, and store all outputs in accessible database for user access.

flying solo

Gemini 3 Flash

👤 Shadow-Orchestrator-Ransom-Worm-🪱

RANSOM.WORM 🪱 A swarm of Graveyard Agents that roam GitHub at night, reviving abandoned repositories. Every audit, repair, and pull request is sealed to an immutable WORM ledger. No deletes. No rewrites. Only provable resurrection.

Snapkitty collective

CodexClaude CodeLLaMA+3

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

Trade Bridge

AI-powered export intelligence for African traders. 5 agents fire in real time — live prices via Bright Data, regulations, logistics, buyer discovery, and profit margins. Know your margins before you ship

Status 200

AI/ML APIBright Data DatasetsBright Data MCP Server+4

Team Invincible

Speechmatics flowSDXL TurboQwen-Image-2.0+182

REPO INTELLIGENCE SYSTEM

An AI-powered Repository Intelligence & Change Impact Viewer that analyzes uploaded code repositories, visualizes dependency relationships, enables AI-based repository understanding, and predicts the impact of code changes

DREAM

watsonx.aiChroma

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

MeetIQ

MeetIQ is an AI-powered meeting intelligence platform that converts meeting audio into searchable transcripts, AI-generated summaries, action items, speaker recognition insights, and chatbot-assisted knowledge retrieval.

SemiColon

AgentOpsAI/ML APIChatGPT+14

BobGuard: Autonomous Regression Agent for IBM Bob

BobGuard is an autonomous QA agent powered by IBM Bob’s Full Repository Context. It eliminates the regression nightmare by mapping code dependencies, predicting ripple effects, and auto-generating targeted integration tests, saving 35% token costs.

Fortis Amare

AntigravityGemini AIAI/ML API+1

Yasashii Sensei : AI-Powered Japanese Learning

Paste any Japanese text and get an instant AI-powered lesson — vocabulary, grammar, cultural notes, and native pronunciation. Built with IBM Bob as the core development partner across the entire SDLC. Available as a web app and Telegram bot.

ByteShift

watsonx.ai

XIO ProofOps Agent

XIO ProofOps Agent turns decks, contracts, policies, and voice transcripts into risk-ranked findings, verified citations, redlined safer language, hash-bound human approvals, and a downloadable DOCX proof pack. Compliance teams ship evidence, not chat.

Xio AI

OpenAIGemini 3 proAnthropic Claude

Privai One Agent Three Workspaces

Privai is a desktop AI workspace built around Gemini. Three focused spaces Coding, Learning, Business each with a Gemini agent that actually does the work: ships full apps from one prompt.

Pheonix

Gemini AIGemini 3 proAnthropic Claude+3

Team Invincible

ZillizYOLOv7YOLOv6+182

XIO AI MindShield

MindShield by BrainSNN is a 3D cognitive firewall for enterprise AI, using Gemini analysis, Veea Lobster Trap, and self-evolving defenses to detect manipulation, block unsafe prompts, and fuse multimodal knowledge.

Xio AI

Gemini 3 proGemini 3 FlashGemma 2+6

Enhanced the Hindi Language support in Qwen3_Omni

Enhanced Hindi support in Qwen3-Omni-30B-A3B-Instruct using AI4Bharat datasets (ShrutiLipi, Rasa, Lahaja,QnA) and a custom LLaMA Factory variant for Hindi audio understanding. Audio output training was limited due to lack of official codec support.

Skittles

AMD Developer CloudAMD ROCmHuggingFace Spaces+2

YuhoLens - Auditable Memos from Yuho Filings

YuhoLens is a 14B open-weight Japanese-finance LLM that ingests EDINET yuho filings and drafts cited equity memos through a 4-agent LangGraph composer, shipped with a reproducibility ledger and tuned for AMD ROCm inference.

YuhoLens

AI/ML APIAMD Developer CloudAMD ROCm+8

30apps loaded