An industrial Multi-Agent System (MAS) platform Ariona Shashaj, Federico Mastrorilli, Michele Stingo and Massimiliano Polito Abstract When it comes to address challenges in the area of distributed and par- allel computing, Multi-Agent Systems (MAS) are emerging as a key architecture. Characterized as a collection of autonomous software (agents) which are able to cooperate in a distributed environment, MAS-based applications have proven ca- pabilities when using cognitive processes, reasoning and knowledge representation in order to develop functionality related to complex and dynamic scenarios where the contribution of a single agent is computationally limited. In this paper, we pro- pose an industrial platform which fully supports the development, deployment and maintenance cycle of MAS-based applications. 1 Introduction A Multi-Agent System (MAS) is a collection of autonomous software components (agents) which cooperate in a distributed and dynamic environment in order to achieve a common goal. A modern vision of Artificial Intelligence (AI) is the one of an intelligent agent capable of reasoning, planning, interacting and learning [17]. In this context, it is natural to focus the interest on MAS distributed architectures which enable the collaboration of intelligent agents in order to develop modular and computationally efficient applications related to Distributed AI, where the ca- pabilities of a single agent are limited due to a local perception of the environment and scarce computational resources. In order to completely support the develop- ment and maintenance cycle of multi-agent applications involved in the automation Ariona Shashaj, Federico Mastrorilli, Massimiliano Polito Network Contacts, Molfetta, Italy e-mail: {ariona.shashaj, federico.mastrorilli, massimiliano.polito}@network-contacts.it Michele Stingo DSPC - Universit` a degli studi di Salerno, Salerno, Italy e-mail: mstingo@unisa.it 1