Ruby Khupe@ruby_o_khupe326

TradeBridge is an AI-powered export intelligence platform built for African traders, starting with Botswana. Every day, smallholder farmers and commodity traders lose money because they don't know their real export margins before they ship — they guess on pricing, miss regulatory requirements, and underestimate logistics costs. TradeBridge solves this by deploying five AI agents simultaneously: a Price Agent that scrapes live commodity prices from global markets using Bright Data's Web Unlocker, a Regulation Agent that checks import duties and phytosanitary requirements, a Logistics Agent that calculates real shipping costs from Durban port, a Buyer Agent that identifies actual importers and wholesalers in the destination market, and a Profit Agent that calculates gross profit in Botswana Pula with a clear VIABLE or NOT VIABLE recommendation. Every analysis is stored in a Cognee-powered knowledge graph, giving traders persistent memory across sessions. They can see how their margins have changed over time and track price trends across 10 commodities and 12 destination markets. Built on Bright Data, Cognee, AI/ML API, Vultr, Next.js, and FastAPI TradeBridge turns days of manual research into under 60 seconds of live intelligence.

VIGILO is a full-stack autonomous AI compliance enforcement engine built for the EU AI Act. Unlike chatbots that wait for user instructions, VIGILO operates as a true agent: upload one document or code file describing your AI system, and VIGILO takes over completely. Its multi-agent pipeline — powered by Google Gemini 2.0 Flash for analysis, Featherless Llama 3.1 70B for obligation scoring, and Speechmatics for voice input — autonomously reads the submission, classifies the EU AI Act risk tier (Unacceptable/High/Limited/Minimal), maps it to applicable Annex III categories, scores compliance across Articles 9-15, and generates a detailed remediation report. Every step streams live to the UI via WebSockets. VIGILO covers both document compliance (policy docs, system descriptions) and technical compliance (code scanning for prohibited patterns, missing human oversight, lack of audit trails). Deployed on Vultr, orchestrated visually via n8n, and open-source under MIT. Target users: legal teams, CTOs, and AI product managers at companies deploying AI systems in the EU who face real compliance obligations coming into force in 2025-2026.

LegacyLift is an AI-powered modernization intelligence platform built to help organizations understand and safely transform legacy enterprise software systems. Instead of relying on manual code reviews or costly architecture discovery exercises, LegacyLift automates modernization analysis using IBM BOB agents and a risk-engine pipeline to surface technical debt, architectural bottlenecks, and upgrade priorities. The project analyzes a legacy codebase (demonstrated using CargoTracker, a Java domain-driven design application) and produces actionable modernization insights. LegacyLift scans dependencies, evaluates bounded contexts, identifies high-risk modules, estimates upgrade effort, and visualizes architectural relationships in a live dashboard. The system transforms raw analysis into decision-ready insights for architects, engineering managers, and modernization teams. Using IBM BOB’s Architect Mode, Modernization capabilities, and BobShell audit outputs, LegacyLift generates structured intelligence that would normally require weeks of manual enterprise assessment. The platform highlights dependency hotspots, technical debt concentrations, risky modules, and recommended modernization paths while also producing a transparent audit trail of what the AI system discovered and why. The application includes a React dashboard for visualization, a Node.js risk-engine API for analytics, and JSON-based reporting pipelines that expose modernization summaries, recommendations, risk scores, dependency graphs, and quick-win opportunities. Teams can compare “before” and “after” modernization states to better understand transformation impact and planning effort. LegacyLift turns legacy modernization from a guessing game into a measurable, explainable process—helping enterprises reduce migration risk, prioritize engineering effort, and accelerate digital transformation with AI-assisted architectural intelligence.

📅 June 12–19, 2026 • June 12: Kick-off Stream • June 12–19: Online Build Phase • June 19: Project Submissions Ends 🌍 Fully online hackathon. Join and build from anywhere in the world. 🤝 Build practical enterprise workflows where AI agents communicate, coordinate, exchange context, and complete work together. 🧠 Powered by Band and Codeband, built for collaborative AI systems and agent orchestration. 🏆 Prize Pool: $10,000+ 🧑‍💻 Apply now to build the next generation of enterprise multi-agent systems.

Grab your ideas, spin up compute, and start building what’s next! Start with $100 in AMD Developer Cloud credits and begin building right away. Get access to hands-on tutorials, workshops, and curated learning resources to help you build faster and go further. To unlock credits and join the hackathon, sign up for the AMD AI Developer Program. 💰 $10,000 total prize pool Developers, builders, and innovators - bring your boldest ideas and let’s turn them into real AI systems on AMD.

🌍 Hybrid Hackathon | 💻 Online Build: May 25–30,2026 | 📍 SF Onsite Finale: May 30–31,2026 We’ve unlocked the web for your AI. Now build what wasn’t possible before. Build AI agents with live web data, then join the SF onsite finale at Bright Data’s new Web Data Loft. 🚀 The onsite experience will take place during the opening of Bright Data’s new SF space, The Web Data Loft. 📍 On-site Venue (May 30–31): The Web Data Loft 625 2nd St, San Francisco, CA 🏆 $18,300 cash prize + Bright Data AI Startup Program opportunities 🍕 Free food, drinks, networking, workshops, mentorship, and live demos 🎁 Onsite attendees are automatically entered into a live giveaway for 4 × $100 Amazon gift cards. 🧑‍💻 Apply now to build AI agents powered by real-time web access.

Build solutions that improve how software is built. Work with an AI that understands your codebase, helping you reduce repetitive work and build with real context. ⏳ Build your project in 48 hours. 🚀 Get hands-on with IBM Bob and explore how AI fits into real development workflows before it becomes standard. 💡 Build tools and workflows that developers would actually use. ⭐ Learn directly from experts throughout the event. 🤝 Join a team or build solo. 💰 Prize pool: $10,000 🧑🏻‍💻 Register before the Kick-Off Stream and start building with Bob.

⏱️ Build the next generation of Autonomous Agents in the heart of Europe’s AI Revolution. 📅 May 13 – 20, 2026 May 13 – 19: Online Build Phase. May 19: An exclusive on-site build day at Milan AI Week for selected participants. May 20: Awards Ceremony. 📍On-site Venue (May 19–20): Fiera Milano (Rho), Milan, Italy 🤝 Join solo or with a team. 🎟 FREE Milan AI Week conference ticket included for participants. 💰 $32,000+ prize pool 🧑‍💻 Apply now to turn your autonomous agent into a market-ready enterprise solution.