We present PyXtal FF-a package based on Python programming language-for developing machine learning potentials (MLPs). The aim of PyXtal FF is to promote the application of atomistic simulations by providing several choices of structural descriptors and machine learning regressions in one platform. Based on the given choice of structural descriptors (including the atomcentered symmetry functions, embedded atom density, SO4 bispectrum, and smooth SO3 power spectrum), PyXtal FF can train the MLPs with either the generalized linear regression or neural networks model, by simultaneously minimizing the errors of energy/forces/stress tensors in comparison with the data from the ab-initio simulation. The trained MLP model from PyXtal FF is interfaced with the Atomic Simulation Environment (ASE) package, which allows different types of light-weight simulations such as geometry optimization, molecular dynamics simulation, and physical properties prediction. Finally, we will illustrate the performance of PyXtal FF by applying it to investigate several material systems, including the bulk SiO 2 , high entropy alloy NbMoTaW, and elemental Pt for general purposes. Full documentation of PyXtal FF is available at https://pyxtal-ff.readthedocs.io.