CellRank2 is a versatile and scalable framework designed to study cellular fate using multiview single-cell data, allowing for the integration of various data modalities such as RNA velocity, experimental time points, and metabolic labeling. The framework decomposes trajectory inference into two components: modality-specific modeling of cell transitions and modality-agnostic trajectory inference. It uses a modular design with kernels for computing cell transitions and estimators for analyzing these transitions to infer initial and terminal states, fate probabilities, and lineage-correlated genes. CellRank2 has been successfully applied to human hematopoiesis, endodermal development, and intestinal organoid systems, demonstrating its ability to recover terminal states, identify lineage drivers, and estimate cell-specific transcription and degradation rates. The framework's flexibility and scalability make it a powerful tool for analyzing complex cellular dynamics in large, multi-modal datasets.CellRank2 is a versatile and scalable framework designed to study cellular fate using multiview single-cell data, allowing for the integration of various data modalities such as RNA velocity, experimental time points, and metabolic labeling. The framework decomposes trajectory inference into two components: modality-specific modeling of cell transitions and modality-agnostic trajectory inference. It uses a modular design with kernels for computing cell transitions and estimators for analyzing these transitions to infer initial and terminal states, fate probabilities, and lineage-correlated genes. CellRank2 has been successfully applied to human hematopoiesis, endodermal development, and intestinal organoid systems, demonstrating its ability to recover terminal states, identify lineage drivers, and estimate cell-specific transcription and degradation rates. The framework's flexibility and scalability make it a powerful tool for analyzing complex cellular dynamics in large, multi-modal datasets.