When a large amount of data is generated from multiple, heterogeneous and continuous data streams, the need for continuous processing and on-the-fly consumption of the overwhelming flow of data is crucial. In this context, the W3C RDF Stream Processing (RSP) Community Group has defined a common model for continuous querying RDF Streams, giving rise to a plethora of RSP engines. However, their main limitation is that, depending on the application queries, one RSP engine may be more appropriate than another, or multiple engines are required to address complex queries. In this paper, we propose a multi-agent based framework for distributed continuous processing that gives the opportunity to use several RSP engines in the same framework in order to benefit from their advantages and to offer the possibility to use them at the same time or in a sequence to answer complex queries. A preliminary experimental evaluation with a real-world benchmark shows promising results when compared to an existing work.