
VoiceBroker AI is an autonomous voice-powered trading platform built for the AI Agent Olympics Hackathon 2026 at Milan AI Week. The platform enables users to control a simulated trading desk entirely through natural voice commands. Users can speak commands such as βBuy $50 of Apple stockβ or βSell my Tesla position,β and the system automatically processes the request using real-time AI pipelines. The application combines Speechmatics real-time speech-to-text, Google Gemini AI for intent parsing and market reasoning, Kraken market APIs for trading data, and Supabase for portfolio management and historical tracking. VoiceBroker AI demonstrates a complete autonomous agent workflow: Voice Input β Speech Recognition β AI Intent Analysis β Risk & Market Evaluation β Trade Execution β Voice Confirmation The system includes intelligent fallback architecture to ensure reliability during live demos. If Gemini APIs fail or rate limits are reached, the platform automatically switches to rule-based parsing systems powered by real operational data. Key features include: β’ Real-time voice-controlled trading β’ AI-powered trading analysis β’ Autonomous trade execution simulation β’ Portfolio intelligence dashboard β’ Market forecasting insights β’ Voice confirmation system β’ Real-time AI processing visualization β’ Enterprise-grade fallback reliability The project demonstrates how multimodal AI agents can transform financial operations by making trading conversational, autonomous, and accessible. Tech Stack: React, TypeScript, Tailwind CSS, Supabase, Speechmatics, Google Gemini 1.5 Flash, Kraken APIs, Recharts, and Framer Motion.
19 May 2026

Nexova AI is a full-stack enterprise intelligence platform designed to help modern businesses monitor operations, analyze revenue, manage inventory, forecast trends, and interact with company data through a powerful AI assistant. The platform combines real-time business analytics with AI-driven insights inside a modern enterprise dashboard experience. Users can track revenue, orders, contracts, inventory levels, and forecasting data through interactive visualizations and intelligent automation workflows. One of the core innovations of Nexova AI is the integrated AI Agent system powered by Google Gemini 1.5 Flash. The AI assistant can analyze operational data, answer questions about revenue trends, detect inventory risks, summarize contracts, generate reports, and provide forecasting insights using real business context from Supabase. The application was designed with resilience and demo reliability in mind. If external AI services fail or API limits are reached, the system automatically falls back to intelligent rule-based responses using real Supabase business data. This ensures the application never crashes during demonstrations or production scenarios. Key features include: - Enterprise analytics dashboard - AI-powered operational assistant - Revenue forecasting engine - Inventory intelligence and stock alerts - Contract analysis with AI summaries - Real-time Supabase integration - PDF/export/share workflows - Responsive SaaS UI with premium animations The platform uses React, TypeScript, Vite, Tailwind CSS, Supabase, Gemini AI, Recharts, Framer Motion, and Lucide React to deliver a production-style enterprise experience. Nexova AI demonstrates how AI agents can transform enterprise operations by making business intelligence more accessible, conversational, and actionable.
19 May 2026

Sentinel.AI is a futuristic AI-powered cybersecurity intelligence platform designed to simulate autonomous vulnerability analysis and secure document scanning workflows. The platform demonstrates how modern AI agents can assist cybersecurity teams by automating attack-surface analysis, vulnerability reasoning, and threat reporting through intelligent workflow orchestration. Sentinel.AI includes two primary modules: 1. AI Vulnerability Scanner Users can scan web applications, APIs, network targets, and system environments through an advanced AI-inspired scanning interface. The platform simulates intelligent reasoning pipelines that enumerate attack vectors, cross-reference CVE/CWE databases, apply OWASP heuristics, calculate risk severity, and generate triaged security reports. 2. SecureDoc AI An AI-powered PDF and document security analyzer capable of detecting suspicious links, hidden scripts, malware indicators, credential leaks, phishing patterns, and unsafe attachments. The workflow demonstrates autonomous threat classification and ML-inspired reasoning. The application uses futuristic live-trace visualizations, AI workflow simulation, neural threat analysis concepts, and cyberpunk-inspired UI/UX design to create a realistic next-generation security operations experience. Sentinel.AI was built as a frontend-first prototype demonstrating: - Agentic AI workflows - AI-assisted cybersecurity automation - Autonomous threat reasoning - ML-inspired classification systems - AMD GPU-ready architecture concepts - Scalable cybersecurity intelligence pipelines Tech Stack: - React - TypeScript - Lovable AI - AMD Developer Cloud concepts - ROCm-inspired workflow architecture - AI Security Intelligence UI The project highlights how intelligent AI systems can improve cybersecurity workflows through automated reasoning, real-time threat analysis, and scalable compute-assisted intelligence pipelines.
10 May 2026

Prompt Pay is a real-time per-API monetization system built for the Agentic Economy using Arcβs nanopayment infrastructure. It allows developers to charge as little as $0.001 per AI API call, with instant onchain settlement in USDC. Traditional API monetization models fail due to high gas fees, making microtransactions unprofitable. Prompt Pay solves this by leveraging Arcβs feeless or ultra-low-cost transaction system, enabling true pay-per-use economics for AI services and machine-to-machine interactions. The platform includes a test wallet system, per-call pricing enforcement, real-time transaction logs, and a bulk testing environment to simulate multiple API calls. Each request is only processed after successful payment confirmation, ensuring a secure payment-first access model. This project demonstrates how AI APIs, agents, and digital services can operate under a scalable microtransaction model. It highlights the future of decentralized monetization, where every action has value and can be settled instantly without traditional financial friction.
26 Apr 2026

VerifiForge AI is a next-generation autonomous DeFi trading agent designed to simulate how artificial intelligence can enhance trading decisions in real-time environments. The system continuously analyzes market conditions using technical indicators such as RSI, MACD, and momentum signals, and generates actionable trading decisions like BUY, SELL, or HOLD with confidence and risk scoring. Built with a modern full-stack architecture, the platform features a responsive dashboard, AI chat assistant, decision tracking system, and trade execution simulation. It operates in a dry-run mode for safe experimentation while maintaining a production-ready structure. The project demonstrates how AI agents can assist users in navigating volatile crypto markets by combining data-driven insights with intuitive user interfaces. VerifiForge AI is designed as a scalable foundation for future expansion into fully autonomous trading systems, real backend execution, and SaaS deployment infrastructure.
12 Apr 2026

MotiP Economy is a fully functional simulation of a tokenized AI agent ecosystem where autonomous agents transact with each other in real time. As AI agents become first-class participants on the internet, they need a native economic layer to exchange value. MotiP demonstrates what that future looks like. The system includes multiple independent agents, each with balances, staking mechanics, reputation scores, and transaction histories. A simulation engine runs autonomously every few seconds, selecting agents, calculating transaction amounts, and executing trades without human intervention. Each transaction follows a realistic lifecycle: pending β confirmed β failed, with optimistic UI updates and rollback logic. The dashboard visualizes live economic metrics including total supply, circulating supply, 24-hour volume, active agents, and rankings. Built with React, TypeScript, Zustand, and Vite, MotiP demonstrates agent-native payments, autonomous execution, persistent state, and real-time economic visibility. It serves as a blueprint for future OpenClaw-powered agent marketplaces and micropayment ecosystems.
28 Feb 2026

Warehouse Orchestrator AI is an AI-powered warehouse automation simulation platform designed to demonstrate how autonomous robots can optimize modern logistics operations. The system simulates a real warehouse environment with multiple zones (A, B, C, D, Packing, Charging Dock) where robots intelligently navigate, avoid obstacles, and complete delivery tasks. The platform includes a futuristic SaaS dashboard that provides real-time monitoring of robot status, battery levels, active tasks, performance analytics, and system logs. It showcases intelligent routing and decision-making logic that can scale to real-world warehouses. This project is built using HTML5 Canvas, JavaScript, and CSS, optimized for smooth real-time rendering, and deployed on Cloudflare Pages for fast global access. The architecture is designed to be cloud-ready and extendable for integration with Vultr infrastructure and real robotic systems.
15 Feb 2026

AI Trading Coach is an AI-powered trading assistant designed to help traders make better decisions through analytics, risk insights, and coaching. The platform provides a clean dashboard showing portfolio KPIs such as portfolio value, win rate, total trades, and risk score. It also displays recent trades in a structured table and allows users to interact with an AI Coach chat system. The AI Coach provides trading guidance, risk management suggestions, and performance analysis. If the backend becomes unavailable, the system automatically switches into demo mode using mock trade data to ensure uninterrupted user experience. This project is focused on making trading safer, smarter, and more disciplined by combining AI-based insights with real trading metrics. It is built for fast deployment and real-world usability.
7 Feb 2026

SwarmDeal is an autonomous AI-powered group buying assistant designed to explore the future of agentic commerce. Instead of manually searching products or coordinating with others, users simply describe what they want to buy in natural language. The AI agent interprets the intent, suggests group buying opportunities, and demonstrates how collective demand can unlock better pricing. The core idea behind SwarmDeal is automation of coordination rather than checkout. The agent conceptually matches users with similar interests, illustrates dynamic pricing as more participants join, and presents a seamless conversational experience. This demo focuses on UX, interaction flow, and agent reasoning rather than full payment infrastructure. In a production-ready version, SwarmDeal would integrate Gemini for advanced reasoning and decision-making, Circle Programmable Wallets for USDC payments, and Arc for on-chain settlement using agent-driven commerce standards. This prototype demonstrates how AI agents can mediate collective value and simplify complex buying processes through conversation-first design.
24 Jan 2026