Marwane Oraiche@skouza

AI-powered web/desktop platform for real-time weapon detection in images and live video, with secure authentication, alerts, and detection history tracking.

An interactive platform for mastering C pointers through real-time memory visualization and a Gemini-powered AI tutor. Simplifies memory management concepts with visual analogies.

Fortress AI is an intelligent legal automation platform built for judicial professionals, law firms, and legal departments. It combines a modern Next.js frontend with a FastAPI backend to process legal documents—PDFs, Word files—through automated parsing, vector embedding, and retrieval-augmented generation. At its core, a multi-agent pipeline orchestrates specialized AI workers powered by open-source LLMs (Qwen3-36B and Gemma-4-27B via vLLM on AMD ROCm). These agents handle distinct legal tasks: contract clause extraction, risk assessment, compliance checking, and case law research. Real-time audit feeds via Server-Sent Events ensure every AI decision is transparent and traceable. Built during the AMD Developer Hackathon hosted by lablab.ai, Fortress AI demonstrates how open-weight models and GPU-accelerated inference can deliver enterprise-grade legal tech without proprietary API dependencies.

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. 🤝 Go solo or team up — ship something real. 💰 $21,500+ total prize pool & 1 × AMD Radeon™ AI PRO R9700 GPU up for grabs. 📍 On-site Venue (May 9-10): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 📍On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑‍💻 Developers, builders, and innovators - bring your boldest ideas and let’s turn them into real AI systems on AMD.