Filters

AI Models

Data

Redis Qdrant

Platforms

Streamlit Replit Vercel

Upcoming AI Hackathons
For Innovators & Creators

OpenAI GPT-5 Applications

Browse applications built on OpenAI GPT-5 technology. Explore PoC and MVP applications created by our community and discover innovative use cases for OpenAI GPT-5 technology.

AuraOS

Aura is a sovereign, neuro-symbolic AI operating system that turns natural-language intent into transparent, governed action through local parsing, agent collaboration, bounded experimentation, verifiable learning, and human-controlled decision gates.

AuraOS

AI/ML APIAI StudioAnthropic Claude+16

ResearchOS

ResearchOS is a multi-agent AI research laboratory that autonomously retrieves academic evidence, analyzes literature, identifies research gaps, and generates evidence-grounded research reports.

Limarco48

ChatGPTDeepSeek V3GPT-5+1

Frugal Router: Cost-Aware Multi-Model AI Agent

A category-aware router for the 8 Track 1 task types: sentiment/NER/factual questions go to a bundled local model or the cheapest Fireworks tier; math scales by difficulty; code and logic puzzles route straight to frontier.

Lisan AL Gaib

AMD Developer CloudAMD ROCmDeepSeek R1+9

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

VectorTokenizer

VectorTokenizer is a semantic, hybrid-routing AI agent that replaces brittle regex rules with real-time vector embeddings. It processes routine tasks on a zero-cost local Phi-3 model while securely escalating complex workloads to frontier cloud APIs.

Gemini 3 proGPT-5

Smart_route_ai

Hybrid token-efficient AI agent that analyzes prompt complexity and routes requests to either a local Qwen model or a Fireworks-hosted LLM, reducing API usage while preserving response quality and explainable decision-making.

noobmasters

AI/ML APIAMD Developer CloudAnthropic Claude+13

RugPullRadar

On-chain rug-pull risk scanner for ERC-20 tokens - five auditable signals plus a plain-English verdict served by an LLM on AMD Instinct.

AMDeus Ex Machina

AMD ROCmAMD Developer CloudGPT-5+2

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

ColdChain Sentinel

ColdChain Sentinel turns noisy cold-chain sensor evidence into explainable fault predictions and human-first inspection guidance, using offline AMD GPU-trained STBL without making autonomous shipment decisions.

SignalForge AI

AMD Developer CloudAMD ROCmAI/ML API+2

BoundaryForge

BoundaryForge AI evaluates regulated financial AI before deployment using Gemma 4 adversarial prompts, OpenAI/Claude targets, independent judges, and AMD ROCm validation to produce risk findings, certificates, and audit evidence.

BoundaryForge

AI/ML APIAMD ROCmAWS+7

AITinerary

Turn any travel idea into a complete trip. AITinerary uses AI to convert your preferences and Instagram/YouTube inspiration into personalized itineraries, hidden gems, budget planning, recommendations, and an intelligent travel companion.

Ctrl-C*Ctrl-V

AI/ML APIOpenAIAssistants API+16

Esillio: The operating system for human biology

Esillio is a local-first biological memory layer. We leverage AMD Instinct™ GPUs and ROCm to distill Gemma 4 into a micro-artifact that runs fully offline on consumer CPUs, creating a highly defensible, patient-owned moat.

Astrokitty

AI StudioAMD ROCmAMD Developer Cloud+12

Multi-Agent-Hackathon-Suite

Built three AI hackathon agents: a cost-efficient task router (local-first, escalates to Fireworks only when needed), ROCm Ready (ports CUDA to AMD GPUs with hipify), and a local video captioning agent generating four caption styles per clip.

Forever_inovators

AI/ML APIAnthropic ClaudeClaude Code+9

ISEEKAIGO

Building Human-like AI companions with human-inspired cognition and self-learning capabilities that grow, adapt, and evolve through experience.

ISEEKAIGO

AMD Developer CloudAI/ML APIAI Studio+27

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

TokenRouter : Smart AI Routing Agent

An AI agent that classifies each task and routes it to the optimal Fireworks model — using the most capable model only when accuracy demands it, and the cheapest model everywhere else to cut token usage.

ROYAL RAVENS

AgentOpsAMD Developer CloudAMD ROCm+7

smart token efficient agent

A highly token-efficient, hybrid AI agent utilizing a local gemma:2b model via Ollama for zero-cost primary inference, intelligently routing complex tasks to Fireworks AI cloud models (Gemma 4 series) as a fallback to maximize accuracy and efficiency.

team name

Anthropic ClaudeGemini AIGemini 3 pro+5

NewsPulse - The Agentic Real-Time Radio Host

A highly interactive, ultra-low latency AI voice assistant that generates personalized news broadcasts and instant conversational deep-dives using GPT-OSS-120B (Fireworks AI) on AMD hardware.

CloudSurfer

rest apiClaude CodeGPT-5+2

Hybrid AI Router

A hybrid AI inference router that analyzes prompt complexity and routes requests to either a local LLM or Fireworks AI. The system optimizes token usage, latency, and inference cost while maintaining accurate responses.

Byte Build

AMD Developer CloudAMD ROCmClaude Code+13

BenchSieve

BenchSieve is a format-aware AI task router that reduces Fireworks token usage by solving safe prompts locally and tightly budgeting remote model calls.

MYSELF

GPT-5OpenAIGemini AI+3

TokenPilot: Adaptive Fireworks Model Router

TokenPilot intelligently routes each task to the most cost-effective Fireworks model while preserving answer quality through local checks, confidence scoring, caching, and controlled escalation.

tokenpilot-router

LangChainAMD Developer CloudCodex+2

Valid Route Hybrid Agent

A validator-gated hybrid AI agent for AMD Hackathon Track 1 that combines deterministic local solving with Fireworks escalation to maximize unseen-prompt accuracy while keeping token usage efficient and submission-safe.

Cognivox

AI/ML APIChatGPTCodex+3

Saral AI – Voice AI for Indian Clinics

Saral AI is a multilingual AI voice receptionist that answers calls, performs patient triage, books appointments, answers FAQs using RAG, and instantly sends structured WhatsApp case summaries—helping clinics and MSMEs never miss a lead.

bydhru labs

AMD Developer CloudGemini 3 FlashGPT-5+2

ROCm Migration Copilot

AI-powered tool that analyzes CUDA and PyTorch workloads and generates instant ROCm migration plans, benchmark checklists, and exportable reports for AMD Developer Cloud.

ByteForge_X

CodexAMD Developer CloudChatGPT+3

LabPiolet AI

LabPilot AI is an AI-powered laboratory safety assistant that identifies chemical, biological, and physical hazards, provides safety recommendations, and generates risk assessment reports to improve lab safety.

Fusion Minds

AMD Developer CloudAssistants APIChatGPT+9

CarbonPilot

Agentic carbon, energy, and water footprint analyzer for AI workloads. Built for AMD Developer Hackathon Act II — Track 3 (Unicorn / Open Innovation).

Chonky Bois

AMD Developer CloudAMD ROCmChatGPT+7

VoxRouter — Hybrid Token-Efficient Routing Agent

An AI router that sends each task to the cheapest model that can handle it — free local models via Ollama for simple tasks, remote models only when complexity demands it, with confidence-based escalation and a built-in benchmark score.

Alpha

AMD ROCmAnthropic ClaudeCloudflare Workers AI+6

Axiom - Aether

Axiom is a local-first Rust research runtime for online Test-Time Training (TTT), context compression, grounding checks, and self-healing execution loops.

B Team

AI/ML APIAMD Developer CloudAMD ROCm+6

SignSpeak AI Real-Time AI Sign Language Translator

SignSpeak AI is an AI-powered mobile application that converts spoken Indonesian into contextual English text and real-time sign language animations, enabling more natural, accurate, and accessible communication for the deaf community.

Le Minerale

GPT-5

DeliveryBoy AI

DeliveryBoy AI is an intelligent assistant for motorcycle couriers that optimizes routes, predicts demand, improves productivity, and increases road safety using AMD AI technologies and edge computing.

DeliveryBoy

AMD ROCmAssistants APIAI/ML API+4

30apps loaded