See how agentic AI workflows can use both local AMD hardware and cloud resources to improve privacy, performance, and cost efficiency. This demo showcases AI agents running with the AMD ROCm™ software platform. Private and data-sensitive tasks can remain on the local system, while more demanding workloads can be sent to cloud-based models when needed. The demo also demonstrates local SDXL style transfer running on an AMD GPU, helping keep data on-device while reducing cloud token usage. The open-source application provides tools for interacting with agents, assigning tasks, and monitoring workflows across local and cloud environments.
