Multi-objective optimization in Python. The leading open-source framework for multi-objective optimization — featuring NSGA-II, NSGA-III, MOEAD, and dozens of other algorithms, with millions of downloads.

Surrogate-assisted multi-objective optimization in Python. Extends pymoo with surrogate models to solve expensive black-box problems where each evaluation is costly.

Sampling methods for real-valued variables — Latin Hypercube Sampling (LHS), Sobol sequences, and other space-filling designs for design-of-experiments and optimization.

A Python reimplementation of the DACEFIT toolbox — Gaussian process regression (kriging) originally implemented in Matlab, now available as a clean Python package.

A common interface for surrogate models and model selection. Wraps multiple model types behind a unified API, making it easy to swap and compare models in optimization pipelines.

A lightweight tool for recording videos from Python — useful for creating algorithm visualizations, animated Matplotlib figures, and scientific illustrations.