Résumé : The SAMBA (Systems for AMBient intelligence enabled by Agents) architecture reported here is a conceptual service-oriented architecture supporting the interaction and interoperability of systems, applications and actors by the notion of an "Ambient Intelligence Element Society". The architecture supports the interaction and interoperability of various elements by encapsulating and representing them through agents acting as members of an Ambient Intelligence Elements Society, and by using executable models at run-time in support of interoperability. 1 Introduction The vision for Ambient intelligence (AmI) envisages that devices (e.g. nodes, routers, PDAs) and software agents running on those devices, organise themselves for the benefit of their respective users. Ambient Intelligence builds on three recent key technologies: Ubiquitous Computing, Ubiquitous Communication and Intelligent User Interfaces. Ubiquitous Computing refers to integration of microprocessors into everyday objects like furniture, clothing, white goods, toys, even paint. Ubiquitous Communication enables these objects to communicate with each other and with the user by means of ad-hoc and wireless networking. An Intelligent User Interface enables the inhabitants of the Ambient Intelligence environment to control and interact with the environment in a natural (voice, gestures) and personalised way (preferences, context). In this paper, we will refer to those inhabitants (i.e. devices and software agents) as AmI elements (AmIE). Such AmI elements interoperate and share knowledge or ex