The AlphaFold Protein Structure Database (AFDB) contains full-length predictions of three-dimensional structures for almost every protein in UniProt. The Encyclopedia of Domains (TED) is a comprehensive resource that combines advanced deep learning-based domain parsing and structure comparison algorithms to segment and classify domains across the AFDB. TED describes over 370 million domains, significantly more than sequence-based methods can detect. Nearly 80% of TED domains share similarities with known superfamilies in CATH, expanding the set of known protein structural domains. TED uncovers over 10,000 previously unseen structural interactions between superfamilies, expands domain coverage to over 1 million taxa, and reveals thousands of new architectures and folds. This resource provides a functional interface to the AFDB, enabling a wide range of downstream analyses and advancing our understanding of biology, evolution, and drug discovery.The AlphaFold Protein Structure Database (AFDB) contains full-length predictions of three-dimensional structures for almost every protein in UniProt. The Encyclopedia of Domains (TED) is a comprehensive resource that combines advanced deep learning-based domain parsing and structure comparison algorithms to segment and classify domains across the AFDB. TED describes over 370 million domains, significantly more than sequence-based methods can detect. Nearly 80% of TED domains share similarities with known superfamilies in CATH, expanding the set of known protein structural domains. TED uncovers over 10,000 previously unseen structural interactions between superfamilies, expands domain coverage to over 1 million taxa, and reveals thousands of new architectures and folds. This resource provides a functional interface to the AFDB, enabling a wide range of downstream analyses and advancing our understanding of biology, evolution, and drug discovery.