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.

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

ROCm Navigator

An autonomous, multi-agent platform that scans, migrates, validates, and optimizes CUDA applications to AMD ROCm. Features tree-sitter AST parsing, Gemma-based LangGraph translation, sandboxed Docker compilation, and a real-time Next.js dashboard.

Nigesh

AMD Developer CloudAMD ROCmGemma+2

SecureOps AI — AI-Powered DevSecOps Copilot

AI-powered security scanner that detects code vulnerabilities, generates production-ready fixes, and scans Docker containers for CVEs — all in one tool.

Team AIX

Kraken Websocket apiAMD ROCm

Hybrid Router for Token Optimization

A hybrid model-routing and caching orchestration engine that prioritizes local execution (Ollama) before cloud-bursting to Fireworks AI, verified via strategy-based checks and a self-healing reflection agent to minimize API costs.

Team X

AI/ML APIAntigravityChatGPT+1

Multi-Agent PDF-to-Manim Video Pipeline

Every dense paper you've ever given up on, rewritten as the 3Blue1Brown video that would have made it click. It is generated automatically, covering every page, not just the flashy parts. Weeks worth of animations done in minutes.

SlowMotion

AMD Developer CloudAnthropic ClaudeOpenAI

FlowForge: Natural Language to n8n Workflow JSON

FlowForge turns plain English into ready to import n8n automation workflows. We fine-tuned Gemma 3 4B on an AMD Radeon PRO W7900 using LoRA and real n8n templates taking the model from generating workflows to twenty percent fully valid schema JSON.

BIG JABRA Team

GemmaAI/ML APIAMD Developer Cloud+7

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

ModelForge AI

AI Buddy for Model Based Development, Build Smarter Stateflow & Simulink Models

CIRCUIT

AMD ROCmClaude CodeChatGPT+1

Lina Xu

I love engineering stochastic multi-agent execution graphs, optimizing bare-metal hardware primitives over non-uniform memory access distributed compute structures

MulinaLabs

ChatGPTAntigravityHuggingFace Hub

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

Abacus — Zero-Token Routing Agent

Local-first agent that answers every task on-box at ZERO Fireworks tokens: deterministic solvers (safe-AST math, lexicon sentiment, code execution) plus a bundled Qwen2.5-1.5B CPU model with grammar-constrained decoding and tight token caps.

JustAsh

AMD Developer CloudOpenAIAI/ML API+2

HydraRouter.ai

An autonomous code orchestration and infrastructure governance engine that protects production backends from sudden scope creep, simulates system load spikes, and self-corrects runtime logic using a hybrid local-cloud multi-agent pipeline.

Undercover Devs

AMD ROCmLangChainGemma+1

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

Pact — Hybrid Token-Efficient Routing Agent

Pact routes each task to the cheapest model that can handle it — heuristic triage (0 tokens) → cascade execution (cheap → medium → powerful) → heuristic quality gate (0 tokens). Only essential Fireworks tokens, zero waste.

Loom

AMD ROCmOpenAI

DeployBuddy: AI-Powered Deployment Blueprint Agent

DeployBuddy Intelligence analyzes your repo and generates optimal architecture, cloud provider, region, and cost recommendations — then emits a validated Blueprint your Deploy Agent executes automatically. No more guesswork on where or how to deploy.

apa ya

AI/ML APIQwen3Vercel+1

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

Scrub.it: Your AI-Powered Inline Text Polisher

Scrub.it is a Chrome extension that transforms raw text into optimized AI prompts directly inside any text field. Refine, rewrite, translate, and tailor prompts for ChatGPT, Claude, and Gemini without leaving your workflow.

KR4TOS

AntigravityAnthropic ClaudeChatGPT+4

Damascus — Self-Improving Agent Kernel on AMD

self-improving agent factory: Gemma 3 27B on an AMD MI300X attempts a frozen pytest benchmark, an improver rewrites its rules (AGENTS.md), and every update is eval-gated — bad rules auto-revert. Improvement is measured, never self-graded.

Damascus

AMD Developer CloudAMD ROCmGemma+1

Adaptive Cost-aware LLM router

RouteZero is a hybrid token-efficient AI agent that routes simple NLP tasks to a local 1.5B model at zero token cost, escalating only complex reasoning and code tasks to Fireworks AI.

Rockm

ChromaAnthropic ClaudeAMD Developer Cloud+4

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

Looma Assistant: Concurrent AI Orchestration Agent

Looma Assistant is a fault-tolerant AI agent utilizing Akka actors to dynamically route tasks across specialized models, maximizing accuracy and token efficiency for large-scale, automated data processing workflows.

The Fugees

VercelAMD Developer CloudGemini AI+5

Kernel Olympics — CUDA→ROCm Migration Copilot

Kernel Olympics is a multi-agent AI pipeline that automatically ports NVIDIA CUDA kernels to AMD ROCm/HIP — transforming weeks of manual engineering into ~2 minutes per kernel with 3-stage validation gates and real GPU verification.

Meteorite

AMD ROCmAnthropic ClaudeAMD Developer Cloud+4

DormMate AI

DormMate AI is an AI-powered kitchen assistant that helps students discover affordable, nutritious, and sustainable recipes based on their dietary preferences, budget, and available ingredients using Gemma-powered reasoning and pantry image analysis.

Ma er Doa Coders

AI StudioLlama 3.1Groq

Overfitters_General_Purpose_AI_Agent

A single Dockerized AI agent that classifies tasks across 8 categories, routes each to the right-sized Fireworks model, validates every answer, and guarantees zero missing outputs — built to pass the accuracy gate first, then win on token efficiency.

The Overfitters

AntigravityAMD Developer CloudAMD ROCm

Lumen AI

Lumen is an AI-powered RAG platform that combines document retrieval, LangGraph agents, and live web verification to deliver accurate, context-aware answers through a modern chat interface.

Onix

GemmaLangChainAntigravity+3

Audisor-amd-track1

Local-first AMD Track 1 agent that solves tasks with deterministic tools first and uses Fireworks AI rescue routing only when needed to preserve accuracy while minimizing tokens.

The_One_Shot

AMD Developer CloudCodexAMD ROCm+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

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

TokenEdge — Hybrid AI Routing Agent

TokenEdge is a verification-gated AI routing agent that solves tasks locally whenever possible and uses Fireworks AI only when necessary, minimizing scored tokens while maintaining accuracy.

nexico

AMD Developer CloudGemmaQwen3+5

RocPorter

RocPorter automates CUDA-to-ROCm migration by converting CUDA to HIP, analyzing compatibility, estimating engineering effort, and producing detailed migration reports that help developers confidently move workloads to AMD GPUs.

larpers

AMD Developer CloudAMD ROCmOpenAI+1

30apps loaded