The correct clusters of operating system (OS) components to package for hydration to client devices is learned through analyzing telemetry data of numerous end devices. The telemetry data captures snapshots of the OS components that were used or loaded by the end devices during runs of different applications. An OS component service mines this telemetry data and compares the frequency in which pairs of OS components are used by the end devices together during the different applications runs. Using on these frequencies, the OS components are filtered in a relationship graph and an clustering algorithm is applied to determine whether the OS components are interdependent (meaning used together) or independent (meaning not used together). Interdependent OS components are packaged together into a hydration package and may be transmitted to client computing devices requesting any of their constituent OS components.