The intelligent interaction model based on large models reduces the differences in user experience across various system platforms but faces challenges in multi-agent collaboration and resource sharing. To demonstrate a uniform user experience across different foundational software platforms and address resource coordination management challenges, this paper proposes KAOS, a multi-agent operating system based on the open-source Kylin. The research method involves empowering agents with large models to serve applications. Firstly, the process involves the incorporation of management role agents and the establishment of a vertical collaborative framework among multiple agents, which serves to either build new or substitute existing application software. Secondly, the approach includes an in-depth examination of system-level strategies for the scheduling of shared resources, with the aim of improving the overall user experience and achieving an optimized allocation of resources. Lastly, the methodology concludes with the validation of the efficiency and the demonstrated superiority of a large model multi-agent operating system, accomplished through the application of real-world scenarios and the assessment of its intelligence capabilities. The feasibility of this system is demonstrated, providing a new perspective for the development of multi-agent operating systems. Experimental results show significant advantages of multi-agent collaboration in various application scenarios.