Mobile health (mHealth) based on smartphone and smartwatch technology is changing the landscape for how patients and research participants communicate about their health in real time. Flexible control of the different interconnected and frequently communicating mobile devices can provide a rich set of health care applications that can adapt dynamically to their environment. In this paper, we propose a real-time online activity and mobility monitoring (ROAMM) framework consisting of a smart-watch application for data collection, a server for data storage and retrieval as well as online monitoring and administrative tasks. We evaluated this framework to collect actigraphy data on the wrist and used it for feature detection and classification of different tasks of daily living conducted by participants. The information retrieved from the smartwatches yielded high accuracy for sedentary behavior prediction (accuracy = 97.44%) and acceptable performance for activity intensity level estimation (rMSE = 0.67 and R2 = 0.52).