The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure
DataChain is a Python library and data-processing system that turns files from cloud storage or local filesystems into typed, versioned datasets that can be queried and processed. Teams use it to build repeatable pipelines for unstructured data, with optional knowledge-base and agent features that help coding agents understand and work with those datasets. The catalogue entries connect agents to DataChain's data workflows.
Latest release 0.59.7 · 24 Aug 2026
These files are datachain-ai/datachain's own configuration. They tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.
CLAUDE.md A 87 tok