HDBSCAN is a hierarchical density-based clustering algorithm that extends DBSCAN by performing clustering over varying epsilon values and integrating the results to find the most stable clustering. This allows HDBSCAN to identify clusters of varying densities and be more robust to parameter selection. The algorithm was introduced by Campello, Moulavi, and Sander (2013) and further developed by Campello et al. (2015). The HDBSCAN library also includes support for Robust Single Linkage clustering, GLOSH outlier detection, and tools for visualizing and exploring cluster structures. Additionally, it provides support for prediction and soft clustering. HDBSCAN is particularly useful for datasets with clusters of varying densities, making it more flexible than DBSCAN. The algorithm is implemented in Python and is available under a Creative Commons Attribution 4.0 International License. The software is maintained by the Tutte Institute for Mathematics and Computing and Shopify. The library is designed to be robust and efficient, with a focus on accuracy and performance in clustering tasks. It is suitable for a wide range of applications, including data mining, machine learning, and data analysis. The HDBSCAN algorithm is widely used in research and industry for its ability to handle complex data structures and provide meaningful insights. The algorithm has been validated through extensive testing and is supported by a number of academic papers and technical reports.HDBSCAN is a hierarchical density-based clustering algorithm that extends DBSCAN by performing clustering over varying epsilon values and integrating the results to find the most stable clustering. This allows HDBSCAN to identify clusters of varying densities and be more robust to parameter selection. The algorithm was introduced by Campello, Moulavi, and Sander (2013) and further developed by Campello et al. (2015). The HDBSCAN library also includes support for Robust Single Linkage clustering, GLOSH outlier detection, and tools for visualizing and exploring cluster structures. Additionally, it provides support for prediction and soft clustering. HDBSCAN is particularly useful for datasets with clusters of varying densities, making it more flexible than DBSCAN. The algorithm is implemented in Python and is available under a Creative Commons Attribution 4.0 International License. The software is maintained by the Tutte Institute for Mathematics and Computing and Shopify. The library is designed to be robust and efficient, with a focus on accuracy and performance in clustering tasks. It is suitable for a wide range of applications, including data mining, machine learning, and data analysis. The HDBSCAN algorithm is widely used in research and industry for its ability to handle complex data structures and provide meaningful insights. The algorithm has been validated through extensive testing and is supported by a number of academic papers and technical reports.