Assembly sequence planning (ASP) problem is one of the NP-hard combinatorial problems in manufacturing, where generating a feasible sequence from the set of finite possible solutions is a difficult process. As the ASP problem is the discrete optimization problem, it takes a major part of the time in the assembly process. Many researchers have implemented different algorithms to get optimal assembly sequences for the given assembly. Initially, mathematical models have been developed to solve ASP problems, which are very poor in performance. Later on, soft computing techniques have been developed to solve ASP problems, which are very effective in achieving the optimal assembly sequences. But these soft computing techniques consume more time during execution to get optimal assembly sequence. Sometimes these algorithms fall in local optima during execution. Keeping the above things in mind in this paper, a new algorithm namely hybrid cuckoo–bat algorithm (HCBA) is implemented to obtain the optimal assembly sequences. The proposed algorithm is compared with two different assemblies (gear assembly and wall rack assembly) with the algorithms like genetic algorithm (GA), ant colony optimization (ACO), grey wolf optimization (GWO), advanced immune system (AIS) and hybrid ant–wolf algorithm (HAWA). The results of the different algorithms are compared in terms of CPU time and fitness values with the proposed algorithm. The results show that the proposed algorithm performs better than the compared algorithms. © Springer Nature Singapore Pte Ltd. 2019.