In the recent years, multi-agent systems (MAS) have become a very active research area that apply to many other areas, both inside and outside of computer science.This research presents a multi-agent based urban demand responsive transport (DRT) system intelligent control model, which adopts a practical multi-agents planning approach for urban DRT services control that satisfies the main constraints: minimize total slack time, travel time,waiting time, client’s special requests, and using minimum number of vehicle. In this paper, we propose an agent based multi-layer distributed hybrid planning model for the real-time problem. By computational experiments, we examine an effectiveness of the proposed method for the large real-time urban transport system.