Machine-learned interatomic potentials have revolutionized molecular dynamics simulations by providing quantum-mechanical accuracy at empirical-potential speeds. The graphics processing unit molecular dynamics (GPUMD) package, featuring the highly efficient neuroevolution potential (NEP) framework, has emerged as a powerful tool in this domain. However, the complexity of force field development, active learning, and trajectory post-processing often requires extensive manual scripting, imposing a steep learning curve on new users. To address this, we present GPUMDkit, a comprehensive and user-friendly toolkit that streamlines the entire simulation workflow for GPUMD and NEP. GPUMDkit integrates a suite of essential functionalities, including format conversion, structure sampling, property calculation, and data visualization, accessible through both interactive and command-line interfaces. Its modular, extensible architecture ensures accessibility for users of all experience levels while allowing seamless integration of new features. By automating complex tasks and enhancing productivity, GPUMDkit substantially lowers the barrier to using GPUMD and NEP programs. This article describes the program architecture and demonstrates its capabilities through practical applications.
@article{arxiv.2603.17367,
title = {GPUMDkit: A User-Friendly Toolkit for GPUMD and NEP},
author = {Zihan Yan and Denan Li and Xin Wu and Zhoulin Liu and Chen Hua and Boyi Situ and Hao Yang and Shengjie Tang and Benrui Tang and Ziyang Wang and Shangzhao Yi and Huan Wang and Dian Huang and Ke Li and Qilin Guo and Zherui Chen and Ke Xu and Yanzhou Wang and Ziliang Wang and Gang Tang and Shi Liu and Zheyong Fan and Yizhou Zhu},
journal= {arXiv preprint arXiv:2603.17367},
year = {2026}
}