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.

PrepAI

AI-driven interview-prep platform with CrewAI agents, FastAPI orchestrator and a Vite/React frontend; integrates Fireworks LLM via litellm, curriculum/web/database tools and agent workflows to generate practice sessions, quizzes and evaluation pipelines.

is AI real or artificial

AgentOpsAMD ROCmAntigravity+6

Zeyno: Adaptive Query Router

A local-first AI routing agent that uses a fine-tuned DistilBERT classifier to choose cheap or stronger Fireworks models, reducing routing token cost while preserving accuracy across eight task categories.

TEAM DARI

AMD Developer CloudAI/ML APIHuggingFace Hub

CaptionDB

CaptionDB is an AI-powered video caption and scene analysis platform that automatically detects scenes, extracts keyframes, understands visual context, and generates high-quality captions using a scalable asynchronous AI pipeline.

CaptionDB

AntigravityChatGPTCursor

ChipPilot AI – AI Engineering Workspace

ChipPilot AI is an AI-powered engineering workspace that accelerates ASIC, FPGA, and Analog IC development by generating RTL, creating testbenches, reviewing designs, assisting verification and expert semiconductor guidance.

ASICVision

Assistants APIChatGPTLlama 3.1+1

ReelBudget

Reelbudget is an AI pre-production tool for indie filmmakers and enterprise marketing teams. Powered by the AMD MI300X, it instantly turns text briefs into true animated video storyboards and budget estimations, saving weeks of planning.

Magneto

AI/ML APIAMD Developer CloudAnthropic Claude+9

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

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

WANKEP

Neuro-Genesis Engine

A neural network that grows its own brain mid-training. When loss spikes, a local Gemma-2-2b-it LLM writes, validates, and hot-swaps in a new expert module — no human, no restart. Verified on real AMD ROCm hardware.

Dev Duo

AMD ROCmAMD Developer CloudGemma 2+3

aionVIS: Agentic Vision Model Training

aionVIS turns one plain-English sentence into a trained, deployable object-detection model. An agent swarm generates its own training images, labels them, verifies its own labels, and trains the detector on a single AMD MI300X. Zero human annotation.

aionVIS Founders

AMD Developer CloudAMD ROCmGemma+1

RasoSynthTune: Text-to-Dataset & Fine-Tuning

RasoSynthTune is an autonomous multi-agent data refinery. It discovers extracts filters and constructs fine-tuning datasets, running end-to-end verifications and native model distillation on AMD Instinct GPUs via Fireworks AI

Raso

AMD Developer CloudAMD ROCmGemma+7

CodeEnforcer

AI-powered GitHub PR review agent that analyzes code diffs using DeepSeek Coder on AMD Instinct MI300X GPU. Paste any PR URL and get instant structured code review with bug severity labels and fix suggestions.

ENFORCERS

AMD Developer CloudAMD ROCmAntigravity+1

Local-First Cascade Router — Track 1 v3f

A local-first AI agent that solves tasks across all 8 capability categories using a free local model wherever it can prove correctness, escalating to Fireworks only when verification fails — minimizing token cost while maximizing accuracy.

Ocellus

Gemma

TalentCore AI

An autonomous multi-agent recruitment platform powered by CrewAI and FastAPI that converts candidate CV PDFs into tailored technical interview rooms, evaluates responses using custom rubric matrices, and runs locally via AMD ROCm software layers.

Team one

CrewAIAMD ROCmLlama 3

AMD Hybrid Token-Efficient AI Agent

A hybrid AI agent that intelligently routes tasks between deterministic local solvers and LLM inference, reducing token usage while maintaining fast, accurate, and scalable responses across diverse task types.

radSnap

OpenAIAssistants APIAutoGen+1

WhisperLens

Containerized video captioning agent with AMD ROCm PyTorch support.

Vision Scions

GemmaGemini AIWhisper+1

MonadLabs

MonadLabs converts all data into data specialized for agents, integrates directly in company workflows, and reduces hallucination and token spending up to 85%. As API Bills surge into billions, it is the only way for enterprises to use AI efficiently.

MonadLabs

AI/ML APIOpenAIHuggingFace Hub+8

ayaka-hand: the grip forms before you touch

An AI-driven prosthetic hand that sees what you're reaching for and pre-shapes the grip before contact. The only thing you decide is when to close, not how.

Ayakacorp

Anthropic ClaudeClaude CodeHuggingFace Hub+2

Zephyr: Adaptive Token Routing Agent

Zephyr is an adaptive AI routing agent that minimizes Fireworks token usage by intelligently choosing deterministic solvers, local LLMs, or Fireworks models while maintaining high answer accuracy through confidence-based routing and validation.

zephyr-ahtis

AMD Developer CloudChatGPTHuggingFace Hub

FinShield AI

FinShield AI is an AI-powered insurance policy intelligence platform that uses Multi-Agent AI and RAG to analyze policy PDFs, generate summaries, answer questions, explain clauses, assess risks, and compare policies with fast, accurate insights.

AgentForge AI

GroqLlama 3.1LangChain+2

TERA: Hybrid Token-Efficient Routing Agent

TERA is a hybrid routing agent optimized for AMD CPU environments. It achieves 95.1% accuracy while reducing remote API token usage by 46.3% through dynamic token budgeting, semantic caching, rule-based matching, and custom prompt compression.

Kshipra

AI/ML API

ForgeAi

Hardware-aware AI model optimization for AMD MI300X. Upload a PyTorch checkpoint, run a 7-phase pipeline (search, distill, prune, quantize, benchmark, Pareto, Optuna HPO), export an optimized model tuned to your latency, memory, and accuracy constraints.

O(1) Execution

AI/ML APIAMD Developer CloudAMD ROCm+7

AURA OS - The AI Operating Layer

AuraOS is an AI operating layer that seamlessly combines conversation, automation, and contextual intelligence to make interacting with your computer faster, smarter, and more natural.

Bizzapt

AI/ML APIAnthropic ClaudeChatGPT+5

WarRoom — Autonomous Competitive Intelligence

Give WarRoom one company URL: it autonomously discovers and classifies your competitors, scrapes their public pages, synthesizes an evidence-linked intelligence report where every claim cites its source, and lets you war-game your next move against them.

WarRoom

ChatGPTrest api

Finguard 3.0

Finguard 3.0 is an AI-powered financial operations platform for SMEs in Kenya. It automates reconciliation, forecasting, and tax compliance through an advanced multi-agent AI architecture.

Finguard

Gemma

PersonaLab AI: Test Ideas Before The World Does

An instant market simulation tool. Type any startup idea or ad copy to see how different customer personas would react, complete with sentiment charts, pricing opinions, and actionable launch recommendations.

PersonaLab-AI

AMD Developer Cloudrest apiChatGPT+5

GemmaRoute The Financial Firewall for EnterpriseAI

GemmaRoute is a 4-layer hybrid AI router that cuts LLM API costs by 80%. Local Gemma 2B on AMD ROCm handles trivial and simple queries for free. A Gemma quality judge auto-escalates to cloud only when response quality demands it.

Gemma Labs

StreamlitAntigravityVercel+8

Rune - A Hosted AgentOS

Rune is a self-hosted, event-driven AgentOS that runs autonomous AI agents on minimal hardware routing every request between a free local model and paid cloud tiers by actual complexity, so you never pay cloud prices for a "hello."

Kingdom Intelligence

AgentOpsAMD Developer CloudAMD ROCm+2

ForgeMind AI–Intelligent Software Architecture

ForgeMind AI is an AI-powered software architecture assistant that transforms project ideas into complete technical blueprints, including system architecture, security recommendations, development roadmaps, and implementation guidance and etc.

Neo Dev

AI StudioAI/ML APIChatGPT+11

TACTIC

Token-Aware Computational Task Intelligence Coordinator A hybrid AI inference engine that intelligently routes each request between symbolic solvers, local LLMs, and Fireworks cloud models to minimize token usage while maintaining high-quality responses.

Temp Equals 2

OpenAIAMD Developer CloudAI/ML API+2

30apps loaded