This paper presents a new distributed approach applying to the numerical optimization problem. The algorithm is based on ant-stigmergy metaheuristics where indirect coordination between ants drives the search procedure towards the optimal solution. Indirect coordination offers a high degree of parallelism and therefore a straightforward distributed implementation. For communication between processes a MPICH2 for Windows library is used. The cost function evaluation is an important part of numerical optimization and is usually realized as black-box simulator. Therefore, an algorithm analysis according to simulator’s time complexity is discussed.