With advances in IT technologies even complex machines with several gears and bearings, running at varying rotational speed can be efficiently monitored with an algorithm consisting of a combination of signal envelope and synchronous resampling. For implementation, robust advanced software development technologies are applied, based on an object-oriented approach, supported by formal methodologies, like UML. Another concept important for distributed systems is middleware, like RPC or DCOM. The paper presents a proposal of the architecture of the distributed vibration monitoring and diagnostic system, based on the approaches mentioned above. Principal components are described and their functionality is discussed. Special interest was put on flexibility of architecture and optimization of remote access. XML was proposed as universal and efficient means of configuration storage. The structure of the monitored machine should also be stored in XML. A proposal of such a data structure is described for a gas compressor. Another key component is the database server. It needs to handle multiple databases and multiple users, delivering fast and reliable data. Vibration signal handling can be more efficient when signals are processed on the server side. Efficiency is essential when remote access to vibration data is required and data link is limited. Such a mechanism, based on plug-in approach, is proposed and described. Finally, the paper presents a case study which describes the installation of the system on a gas compressor. The measured data are presented after different processing algorithms. High resolution envelope order spectrum was able to detect the bearing failure.