We present a general method of handling constraints in genetic optimization, based on the Behavioural Memory paradigm. Instead of requiring the problem-dependent design of either repair operators (projection on the feasible region) or penalty function (weighted sum of the constraints violations and the objective function), we sample the feasible region by evolving from an initially random population, successively applying a series of different fitness functions which embody constraint satisfaction. The final step is the optimization of the objective function restricted to the feasible region. The success of the whole process is highly dependent on the genetic diversity maintained during the first steps, ensuring a uniform sampling of the feasible region. This method succeeded on some truss structure optimization problems, where the other genetic techniques for handling the constraints failed to give good results. Moreover in some domains, as in automatic generation of software test data, no other technique can be easily applied, as some constraints are not even computable until others are satisfied.