This is a library of evolutionary algorithms with a focus on neuroevolution, implemented in pure python, depending on numpy. It contains a faithful implementation of Ken Stanley's NEAT (Neuroevolution of Augmenting Topologies) and HyperNEAT. The focus of this library is easy experimentation, it is pure python so it's easy to set up, and it has a simple and flexible API.

This code was written to do the experiments for:

• the paper Critical Factors in the Performance of HyperNEAT
• and the more extensive thesis An Empirical Analysis of HyperNEAT