Put the dltHub platform underneath the dlt you already run

dlt → dltHub takes the open-source project you already trust and puts the platform underneath it. Historically 70% of the people who became dlt users were writing Python first; with coding agents everywhere, that share is only growing.

dlt is the match between standardization and customization: the standardization of a managed tool with the customization of code you own. dltHub keeps that and adds one thing that is hard to reproduce on your own: a persistent context layer.

Most stacks discard context at each boundary, schema at ingest, joins in transform, lineage in the orchestrator. dltHub captures it continuously, across the whole pipeline, and keeps it in one place the agent can read from and write to, ingest to deploy.

Skills and MCP are common now, and their output is only as good as what they can read. With a complete, current context layer, the same Claude, Codex, and Cursor prompts you already use produce better results, because the agent reads the actual state of your pipeline instead of reconstructing it.