Filters

AI Models

Data

Redis Qdrant

Platforms

Streamlit Replit Vercel

Upcoming AI Hackathons
For Innovators & Creators

Meta Llama 4 Applications

Browse applications built on Meta Llama 4 technology. Explore PoC and MVP applications created by our community and discover innovative use cases for Meta Llama 4 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

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

RouteLM: Adaptive Model Routing Engine

An intelligent AI model router that automatically selects the best LLM for each request based on configurable routing strategies such as cost, latency, capability, and availability.

Cin-Cout

Gemini 3 FlashQwen3Llama 4+6

Frugal Route

FrugalRoute is a hybrid LLM router that answers most queries with a free local model (MI300X + Ollama) and only escalates to a paid Fireworks model when necessary — cutting remote token spend while holding accuracy above a floor.

Thread-Ripped

AMD Developer CloudClaude CodeGemma+2

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

MEIA-LAB (Multi-Agent Earnings Intelligence calls)

MEIA-LAB is a multi-agent AI platform that auto-verifies earnings call claims against SEC filings in real-time. Whisper ASR, Vision OCR, and Filing agents cross-examine audio, slides, and 10-Qs powered by AMD GPUs cutting analyst research time by 90%.

MEIA Labs

AMD ROCmAntigravityOpenAI+10

NeuroBridge: AI Fraud Triage & Smart Routing

An AI-powered security layer for L2-to-fiat gateways. It leverages AMD compute for real-time anomaly detection and Fireworks.ai for smart, token-efficient routing, giving merchants instant, human-readable fraud alerts.

DOW Project

AMD Developer CloudAgentOpsLlama 4

Metis

A local-first hybrid AI agent that answers tasks with a free on-device model and escalates to paid cloud models only when a calibrated confidence gate says it must — maximum accuracy at minimum token cost.

Kingdom of Science

AMD Developer CloudAMD ROCmClaude Code+5

SafeO

SafeO is an Arabic-aware, multi-agent cybersecurity engine that blocks malicious ERP inputs in real time powered by Gemma 3 on AMD via Fireworks AI.

KrishnaCode

AI/ML APILlama 4Llama 3.1+6

Token-Efficient Hybrid AI Gatekeeper

An intelligent, Dockerized hybrid AI proxy gateway that dynamically routes prompts between local Ollama edge nodes and Fireworks AI cloud tiers based on task complexity to minimize token spend.

LifeInvaders

AMD Developer CloudLlama 4AI/ML API+2

Dual Pitcher AI Agent

A hybrid AI Agent that can handle variety of natural language tasks across multiple disciplines, using either local or Fireworks AI models as efficiently as possible.

NPA

AI/ML APIAMD Developer CloudClaude Code+5

KAVACH

KAVACH is a self-healing security pipeline that auto-detects, diagnoses, patches, and sandbox-verifies web app vulnerabilities using a local LLM, with a 5-layer safety stack and deterministic fallback.

Segmentation Fault

AMD ROCmQwen3Llama 4

no-cap.ai

Give it a clip and it writes four captions formal, sarcastic, humorous_tech, humorous_non_tech. All four come from the same real description of what happened, not four separate guesses, so they stay accurate while sounding nothing alike.

Metox

GroqAI/ML APIChatGPT+6

Photon

A Dockerized video captioning agent for Track 2. It samples frames with ffmpeg, gets a factual scene description from a VLM, then generates captions in four styles via one LLM call. Provider-agnostic (Fireworks/Groq), resilient with retries and fallbacks.

top-k

AI/ML APIQwen3-VLQwen3+2

CodeForge OS

CodeForge OS is a multi-agent AI platform that transforms software ideas into production-ready blueprints. Specialized AI agents collaborate to generate requirements, architecture, implementation plans, testing strategies & deployment roadmaps in minutes.

Cooked GNG

CodexGemini 3 proGemini 3 Flash+4

HireFlow

HireFlow turns a raw job description and a pile of resumes into a structured hiring recommendation — through a relay of 4 specialized AI agents that collaborate in a Band chat room.

Bazooka223

AI/ML APILlama 4LangChain+3

Dzuka Agri: Global AI for Huge Farm Ops

Dzuka Agri equips huge commercial farms worldwide with multi-agent AI. Submit crop image, GPS & problem → agents (Crop, Pest, Climate, Market & more) collaborate for enterprise-grade actionable recommendations. Intelligence at scale

DZUKA AGRI-COPILOT

CodexAgentOpsAI/ML API+9

MediScan AI

MediScan AI is a Multi-Agent Radiology Assistant that analyzes chest X-rays using specialized AI agents for image screening, clinical reasoning, safety validation, and report generation to deliver fast, explainable diagnostic insights.

AI Ragnarok

rest apiLlama 4Groq+1

Band Review Board: Multi-Region Ad Compliance

A room of 10 specialist agents on Band that argue a marketing campaign against every market's ad rules at once, catching the cross-border conflict one legal team misses, in minutes instead of weeks, and proving every verdict with an audit trail.

Noelle

AI/ML APIBand Control PlaneBand Intergrations+13

Triumvirat

An interactive multi-agent workspace simulation dashboard where an Architect, Coder, and Tester collaborate autonomously to implement, test, and verify code features in real-time.

Albion

AntigravityLlama 4Gemini 3 pro+3

TechCare SafeGuard

TechCare SafeGuard is an autonomous 6-agent AI swarm that detects, diagnoses, contains, and learns from industrial equipment failures — compressing a 30–90 minute human response into under 60 seconds.

Hz Squad

AntigravityLlama 4Groq+1

TELMED AI DOCTOR

Telmed AI Doctor delivers instant medical diagnosis via text, voice & image analysis giving underserved communities 24/7 access to AI-powered primary care, medication management & pharmacy discovery on any device.

Pegasus

Gemini 3 proGroqAnthropic Claude+3

IBM-BOB-Haackathon-submission-BOB_RAG

This project uses the BOB Framework for AI-assisted development. DocRAG-MD is a lightweight, open-source medical question-answering system.

Steering Team

Llama 4Gemini AI

PHRAXIS - Voice to Production Quantum Opt System

PHRAXIS turns a spoken developer idea into a production-ready GitHub PR in under 4 minutes. IBM Bob reads the full codebase. IBM Quantum QAOA finds the optimal change path. IBM Watson STT and NLU extract structured intent. Voice to impact, end to end.

DRAGORITHM

IBM watsonx AssistantIBM GraniteLlama 4+1

PR Party

PR Party transforms GitHub pull requests into RPG encounters. Six AI specialist characters — each powered by IBM watsonx.ai — review your code for security, database, UX, architecture, tests, and documentation issues.

BobThePrompter

watsonx.aiAnthropic ClaudeLlama 4+4

Agentic Security & Observability Platform

Governance.AI is an AI governance and observability platform that helps developers monitor, trace, audit, and control autonomous AI agents using real-time governance workflows, policy enforcement, SDK integrations, and observability infrastructure.

Governnace_AI

AntigravityAI/ML APIAWS+14

SRE-Healer: Autonomous Remediation Agent

SRE-Healer is an autonomous AI agent that detects, diagnoses, and fixes server issues in real-time. Built with IBM Bob, it eliminates repetitive debugging tasks, allowing developers and SREs to focus on building impactful features faster.

Beyonce

IBMAutoGenrest api+2

EchoTwin – The Real-Time AI Communication Clone

EchoTwin is a real-time conversational AI agent that becomes your live communication twin. It doesn’t just transcribe or summarize—it actively listens, understands context, predicts intent, and speaks on your behalf in real time.

Leb-ai-dev

ChatGPTClaude CodeCodex+14

AluminatiAI

AluminatiAI GreenTune is an autonomous AI energy optimization platform that uses multi-agent systems and real-time GPU telemetry to reduce the cost, power usage, and carbon footprint of enterprise LLM training workloads.

AluminatiAi

AMD ROCmBERTClaude Code+8

VaultIQ: Governed Document Intelligence

VaultIQ is a multilingual Visual RAG platform that lets enterprises query image-based documents in Arabic or English — with grounded, page-cited answers and a built-in AI governance layer for full auditability.

Nexus Warden

Llama 4Claude CodeGemini AI+2

30apps loaded