Ubiquitous computing technology plays a key role for providing context information and makes context-aware services can be delivered in a smart space. As the contexts changing rapidly, context resources can be gathered from sensors, mobile devices, and personal information softwares. Consequently, a contextaware system must be aware of such environment changes so that it can provide adaptive and proactive services to the users. In addition, all the inner computing operations have to be hidden behind the users. We propose a Context-aware Service Platform, which is implemented in JADE agent platform and utilizes Semantic Web technologies, to analyze the ambient contexts and contrive service plans. We integrated ontology and rule-based reasoning to automatically infer high-level contexts and deduce a goal of context-aware services. An AI planner decomposes complex services and establishes the execution plan. Agents perform the specified task to accomplish the service. A scalable/distributed hardware architecture implements the Context-aware Service Platform, and supports applications with distributed multi-agents embodied in objects throughout the smart space environment. A Smart Alarm Clock scenario demonstrates the detail functions of each agent and shows how these agents incorporate with each others.