Our Projects

These are our open-source AI projects. They are developed under our organization, follow clear governance principles, and are maintained over the long term.

sktime is a Python library that makes it easy to analyze and forecast time series data using a scikit-learn-like interface.

GitHub Docs Website

Feature-engine is an open-source Python library for feature engineering that works natively with pandas DataFrames and integrates seamlessly with scikit-learn pipelines.

GitHub Docs

Hyperactive is an open-source library for optimization and hyperparameter tuning with a unified API.

GitHub Docs Website

pgmpy is an open-source Python library for causal and probabilistic inference using Bayesian Networks and DAGs.

GitHub Docs Website

Prophetverse is an open-source library for Bayesian time series forecasting and Marketing Mix Modeling.

GitHub Docs Website

PyTorch Forecasting is a high-level library for neural network–based time series forecasting.

GitHub Docs Website

pyGAM is an open-source Python library for building Generalized Additive Models.

GitHub Docs Website

pykalman is an open-source Python library for Kalman filtering, smoothing, and state-space models.

GitHub Docs

skbase is an open-source framework for building scikit-learn– and sktime-style parametric objects.

GitHub Website

skforecast is an open-source Python library for machine learning–based time series forecasting.

GitHub Website

skpro is an open-source Python library for supervised probabilistic prediction.

GitHub Website

PyPortfolioOpt is an open-source Python library for portfolio optimization, combining classical approaches such as the efficient frontier and Black–Litterman with modern risk models and optimization techniques.