Abstract. Currently, many kinds of information agents for di erent purposes exist. However, agents from di erent systems are still unable to cooperate, even if they accurately follow a common standard like FIPA, KIF or KQML. Being able to plug agents together with little e ort and exchange information easily, would be of a great use for several reasons. Among others, the agents could pro t from each others' services. In addition, certain aspects of multi-agent systems could be evaluated without needing to build a complete system. Testing agent systems with standard components would allow simpler comparison. Furthermore, building di erent agent-based applications would be simpli ed by combining new software with o the shelf"components. In this paper, we explore the feasibility of practical software development and integration of existing systems, without developing yet abstract agent architecture". 1 Motivation The demand for multi-agentsystems has initiated an increasing...