Fredrick Andoh@Fred_Ricky

Memora Vision is an AI-powered visual memory assistant that transforms traditional CCTV and camera feeds into searchable, conversational intelligence. Instead of manually reviewing hours of footage, users can interact with the system using natural language queries such as “Where did I leave my backpack?”, “Who entered the room today?”, or “Summarize today’s activities.” Using multimodal AI models, computer vision, and event-based memory systems, Memora Vision understands scenes, tracks objects, detects events, and stores them as structured memories with timestamps. The system also supports real-time intelligent alerts, enabling users to create custom conditions like receiving notifications when someone arrives home or when unusual activity is detected. Built on AMD Instinct MI300X GPUs with ROCm acceleration, Memora Vision demonstrates how multimodal AI can turn passive surveillance systems into intelligent assistants capable of understanding, remembering, and responding to human environments in real time.

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.