The paper introduces CALYPSO (Crystal structure AnaLYsis by Particle Swarm Optimization), a software package designed to predict the energetically stable or metastable crystal structures of materials at given chemical compositions and external conditions. The method combines several key techniques, including particle-swarm optimization (PSO), symmetry constraints, bond characterization matrices, partial random structures, and penalty functions, to achieve global structural minimization. These techniques are crucial for avoiding premature convergence and enhancing structural diversity, thereby improving the efficiency and success rate of crystal structure prediction. The authors demonstrate the effectiveness of CALYPSO through various tests, including benchmarking on TiO₂ and other systems, and discuss the implementation details, parameter optimization, and applications of the method. The paper concludes by highlighting the reliability and promise of CALYPSO as a powerful tool for crystal structure determination.The paper introduces CALYPSO (Crystal structure AnaLYsis by Particle Swarm Optimization), a software package designed to predict the energetically stable or metastable crystal structures of materials at given chemical compositions and external conditions. The method combines several key techniques, including particle-swarm optimization (PSO), symmetry constraints, bond characterization matrices, partial random structures, and penalty functions, to achieve global structural minimization. These techniques are crucial for avoiding premature convergence and enhancing structural diversity, thereby improving the efficiency and success rate of crystal structure prediction. The authors demonstrate the effectiveness of CALYPSO through various tests, including benchmarking on TiO₂ and other systems, and discuss the implementation details, parameter optimization, and applications of the method. The paper concludes by highlighting the reliability and promise of CALYPSO as a powerful tool for crystal structure determination.