Abstract In this paper, the semantic complex event processing based on the metagraph approach and its usage in metagraph multiagent system are discussed. The metagraph model is a kind of complex graph model with emergence. The key element of the metagraph model is the metavertex, which makes the definition of metagraph holonic – a metavertex may include a number of lower-level elements and in turn, may be included in a number of higher-level elements. For metagraph transformation, the metagraph agents are proposed. The distinguishing feature of the metagraph agent is its homoiconicity, which means that it can be a data structure for itself. This is due to the fact that the metagraph agent may be represented as a set of metagraph fragments. Thus, the metagraph agent can change the structure of itself or the structure of the other metagraph agents. Changing the structure of a metagraph agent is a form of agent learning. The metagraph multiagent system based on semantic complex event processing using metagraph description of semantic complex event.