Distributed generators (DGs) play an important role to reduce the real power loss and to improve the voltage stability of the power system. However, proper placement and sizing of DGs in the distribution network is a vital issue, as any improper location and size of DGs may increase the overall system loss. In this study, a novel chaotic symbiotic organisms search (CSOS) algorithm is proposed to find out the optimal location and sizes of real power DGs in a radial distribution system (RDS) considering constant load models. This DG siting and sizing problem is associated with real power loss minimisation and voltage stability improvement objectives. The effectiveness of the proposed algorithm is tested on benchmark test functions as well as on 33-, 69- and 118-bus RDS. The simulation results obtained by the proposed CSOS algorithm are compared with the results offered by the basic SOS and other nature inspired algorithms to establish the superiority of the proposed CSOS algorithm over the others in terms of quality of solution and convergence mobility.