Bayesian optimization for the bench
Reach the conditions you want in fewer experiments.
ALchemist suggests your next experiment from the ones you have already run, and shows how sure it is. It runs as a desktop app or in your browser without any code, and it also has a Python API and a REST API.
Design
Latin hypercube, Sobol, central composite and optimal designs, with linear constraints on your variables.
Model
Gaussian-process models, checked with parity, Q-Q and calibration plots from cross-validation.
Suggest
Expected improvement, upper confidence bound and batch acquisition. Stage the suggested points, then record the results once you have run them.