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.

RiskOps

RiskOps is a event triggered supply chain risk simulator with a domain adaptive Multi-Agent AI System analyzes catastrophic events across your vendor network in parallel and generates structured mitigation plans. Built for AMD ACT II Hackathon (Track 3).

The Nacxmeers

AI Studio

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

Penny — the Hybrid Token-Efficient Routing Agent

Penny routes each task to the cheapest Fireworks model that can still get it right — or to zero-token local solving when it doesn't need a model at all — re-deciding cost in real time per task instead of picking one model for everything.

HackX Association

OpenAIAMD Developer Cloud

Chronos AI

Most AI advisors hand you a confident paragraph and call it a day. Chronos builds a memory graph from your GitHub, docs, and real evidence, then runs a Multi-Agent Council to simulate your next big decision with probability scores and Expected Regret.

Jackathon

AMD ROCmAI/ML APIVercel

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

HealthOS — Turn Lab Reports Into Real Answers

HealthOS is an AI health consultant that reads your lab reports, tracks your health over time, and explains what your numbers actually mean — in plain language, not medical jargon.

kopotokkho

AI/ML APICodexClaude Code+6

Vishu

NVIDIAAntigravityClaude Code

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

WANKEP

Central Finite AI

An AI operating system for IT operations that investigates incidents, generates T24 core-banking OFS messages and routines from plain language, and routes every action through human approval before it runs.

Citadel Labs

AI StudioAssistants API

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

Petra

A video captioning pipeline that transcribes audio via Fireworks Whisper-v3 and generates captions in 4 styles (formal, sarcastic, humorous-tech, humorous-non-tech) using Fireworks LLM, with a Streamlit UI

HEXA-Ai

AgentOpsAI/ML APIAI Studio+1

Truce - the next freelancing ecosystem

AI negotiation infrastructure that transforms messy freelance conversations into trusted contracts through multi-agent reasoning, deterministic guardrails, and private Gemma inference on AMD GPUs.

AMD Developer CloudAMD ROCmStreamlit+6

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

Maerefa AI

An AMD-powered multi-agent AI platform that transforms any STEM topic into a complete, audience-adapted learning experience — explanation, quiz, wonder facts, and aniconic illustration — in one prompt.

Sour Lemon

CrewAIAntigravityAMD ROCm

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

YOUSUN Axion

YOUSUN Axion turns messy AI workloads into AMD-ready deployments by scanning code, detecting CUDA/ROCm issues, suggesting fixes, benchmarking improvements, and creating a professional readiness report.

Yousun Apexia

AI/ML APIAMD Developer CloudAMD ROCm+4

AI Caption Studio

AI Caption Studio is an AI-powered video captioning platform that analyzes video frames using multimodal vision-language models and generates accurate captions in Formal, Sarcastic, Humorous Tech, and Humorous Non-Tech styles for creators and developers.

Discord_MOD

GemmaAI/ML APIClaude Code+1

First Aid AI

AI-powered emergency first aid assistant that analyzes text, audio or video to assess emergencies, provides realtime first aid guidance in text or voice & automatically alerts emergency contacts, hospitals and ambulances with GPS location case summary.

Git Push Heroes

AI/ML APIAgentOpsDeepSeek V3+2

CaptionAI Intelligent MultiStyle Video Captioning

AI-powered video captioning platform analyzes videos and automatically generates accurate captions in four distinct styles. Built with React, FastAPI, Docker, and AMD Fireworks AI, it delivers fast, creative captions through an intuitive web interface.

Fatima Ahsan

Gemini AIGPT-3OpenGPTs

TriSphere

TriSphere is an AI-powered opportunity intelligence platform that uses GPU-accelerated AI agents to discover emerging market trends, identify trusted businesses, connect stakeholders, and enable secure USDC payments and verification on Avalanche.

vahnova

AMD Developer Cloud

KAIROS — Company Organizational Memory OS

AI that reads Slack, Gmail, Drive, Notion, Zoom, GitHub, and Jira to extract every company decision and the reasoning behind it — then answers "why" in under 4 seconds, fully sourced, and shares that memory with any AI over MCP.

AgentLab

AMD Developer CloudAnthropic ClaudeAntigravity+7

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

shrinkprompt

hrome Manifest V3 extension that shortens AI prompts on ChatGPT, Claude.ai, and Gemini — local regex fluff removal plus optional semantic compression via a containerized companion (Fireworks Gemma) or local Ollama.

Hack Haven

GemmaGemma 2Antigravity+1

Anchor Agent Offline AI Emergency Response System

Anchor Agent is an offline-first AI emergency response platform that uses voice commands and a hold-to-trigger emergency orb to classify threats, capture GPS, alert contacts, and initiate response protocols even without internet connectivity.

CR Tech AI

AMD Developer CloudVercel

Team AIAutomation Submission

Hackathon onboarding agent for lablab.ai that automates AMD credits, Fireworks setup, team routing, Discord invites, and GitHub workspace provisioning with secure AI workflows.

AIAutomation

kiroLangChainVercel

Cheap Route

CheapRoute serves LLM tasks locally on Gemma and pays for a frontier model only when needed. A confidence gate over log-probs, self-agreement, and format vetoes decides; most answers use zero remote tokens, and a wall-clock cap bounds every response.

SillyGeese

AMD Developer CloudAMD ROCmGemma+1

Ani: Multi-Agent Harvest Grading & Market-Matching

Ani turns one harvest photo into a routed sale before it spoils. Three AI agents: a Gemma 3 vision grader, a demand-and-price matcher, and a logistics router — grade the crop, match it to live Metro Manila demand, and dispatch it, on one AMD MI300X.

The ODYZEUS

AMD Developer CloudAntigravityClaude Code+9

Hybrid Token-Efficient Routing Agent

An autonomous, hybrid real-time routing agent optimized for standardized hardware environments. Using an aggressive speculative draft-and-verify local execution loop, it maximizes accuracy while maintaining near-zero remote token consumption

Blckhol3

AMD Developer CloudAgentOps

track1-agent:latest

ZeroRoute answers all 8 task categories with two bundled 3B models running entirely inside the container — zero Fireworks tokens by construction. Executed program-of-thought math, enumerated logic, and syntax-checked code keep accuracy high.

NGRAM

LLaMAQwen3AMD Developer Cloud

30apps loaded