This chapter presents GPyConform, a Python package that extends the GPyTorch framework with Conformal Prediction (CP) for Gaussian Process Regression (GPR). CP is a Machine Learning framework for constructing prediction regions, or Prediction Intervals (PIs) in the case of regression, with distribution-free, finite-sample coverage guarantees under the sole assumption of data exchangeability. GPyConform implements both the Transductive and Inductive versions of CP with a GPR-specific normalized nonconformity measure that exploits the predictive variance of Gaussian Processes to produce adaptive uncertainty quantification for each instance. It also supports symmetric and asymmetric PIs in both framework versions through a unified and intuitive interface. We provide detailed examples showing how to set up models, construct Transductive and Inductive CP regressors, retrieve and evaluate PIs, and assess their empirical performance. An empirical study on the Abalone dataset investigates the coverage and widths of the provided PIs, as well as the practical computational efficiency of the package through GPU acceleration. Together, these features make GPyConform a practical tool for practitioners seeking reliable uncertainty quantification with GPR and a foundation for future research in CP.