Put the dltHub platform underneath the dlt you already run
Take the open-source project you already trust and put the platform underneath it.
Put this blueprint to work
Talk it through with the dltHub team and we will help you ship it to production.
Contact usBrowse all blueprintsYour coding agent
Claude Code, Cursor or Codex
the agentic layerdltHub AI harness
Agentic primitives to build, run and fix pipelines
dltHub context catalog
Lineage, schema, data quality, governance, run state
dltdltHubOpenAI
Anthropic
Pydantic Logfire
Arize
Langfuse
LangChain
OpenTelemetry
Datadog
Grafana
Honeycomb
Weights & Biases
Braintrust
+4 more pipelines, moved one at a time
the managed infrastructure layerDashboards
Your existing dashboards and warehouse, fed by pipelines you now own.
How it works
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.
Key features
- Keeps the open-source dlt you already run and puts the platform underneath it
- A persistent context layer that captures schemas, lineage, traces, and runtime state in one place
- The same Claude, Codex, and Cursor prompts produce better results against a complete context layer
- Ships with agent configs for Claude, Codex, and Cursor
How to get it
- Bring us the stack you want to move. We go on a scoping call, then send you a proposal.
- When we have capacity, we can move 30 pipelines in two weeks.
- Are you a consulting partner? We increasingly run Agentic Migrations together. Reach us through the same contact form.
Pricing
- dltHub from $1,190/month: the platform your migrated pipelines run on afterwards.
- Migration itself is scoped per project. Bring the number of pipelines and connectors, and we size it on the call.
- Priced against what you pay today, not per row.
Built by
- dltHub
Put this blueprint to work
Talk it through with the dltHub team and we will help you ship it to production.
Contact us