The explosive growth in the volume of information available on the Internet computing environments requires new architectures for information retrieval systems. Typically, in these environments, the information resources are dynamic, heterogeneous and distributed. In addition, these computing environments are open, where information resources may be connected or disconnected at any time. This dissertation presents the design and implementation details of Multi Agent-System for Web Information Retrieval (MACIRS). The system includes six types of agents: Interface, Broker, Domain, Result Analysis, web crawler and Information agents. It will also explained that how these agents communicate with each other in order to accomplish information retrieval