The fastest way for agentic teams to build and run trusted data pipelines, from any source.
dlt is the open-source Python library 50,000+ developers use to build data pipelines. When AI makes it easy to build, dltHub becomes the fastest way to put trusted dlt data pipelines into production.
dltHub
Agents build your dlt pipelines from a prompt. Paste this prompt into Claude/Codex/Cursor:
Run uvx dlthub-start@latest to build my first example pipeline and run it on dlthub
"What I didn't expect is how much it unblocks the team. A mid-level engineer can spin up a prototype, browse the raw data in dltHub's local DuckDB workspace, validate the SQL schema - all without pulling in a senior. That loop of prototype, inspect, fix, re-run - that's the real unlock."
Marcello Victorino
Staff Data Engineer, Tasman Analytics
Marcello Victorino
Staff Data Engineer, Tasman Analytics
THE AGENTIC DATA ENGINEERING LIFECYCLE ON DLTHUB
From the outcome you define to the answer you ship, end to end.
Same code from local prototype to production. Same governance from raw data to dashboard. Same agents writing every stage.
1 · DEFINE
Turn the business outcome into an agent-ready build plan
The bootstrap toolkit gives agents shared rules, secrets handling, and MCP routing while its skills call dlthub ai init --agent claude and dlthub ai mcp install.
Get a governed pipeline brief, local workspace, and live agent context before code is written.
uv run dlthub ai toolkit install bootstrap
Opus 5.0 · dltHub · ~/agent-observability
2 · INGEST
Load source data with a reusable dlt pipeline
The rest-api-pipeline toolkit guides agents through source discovery, endpoint setup, and schema-safe loading while its skills call dlthub init rest_api duckdb and dlthub pipeline run. So source data lands locally with repeatable pipeline code.
uv run dlthub ai toolkit install rest-api-pipelineOpus 5.0 · dltHub · ~/agent-observability
3 · VALIDATE
Catch drift and data issues before they reach consumers
The data-quality toolkit adds checks and verification steps while its skills call dlthub ai install data-quality and dlthub transform verify --inputs/--outputs.
Schema drift and quality failures become visible before dashboards depend on them.
uv run dlthub ai toolkit install data-qualityOpus 5.0 · dltHub · ~/agent-observability
4 · DEPLOY
Run the pipeline in dltHub platform
The dlthub-platform toolkit prepares production profiles, jobs, schedules, and logs while its skills call dlthub deploy <pipeline>, dlthub runtime schedule, and dlthub runtime logs. Outcome: the same pipeline runs in managed production with observable jobs.
uv run dlthub ai toolkit install dlthub-platformOpus 5.0 · dltHub · ~/agent-observability
5 · TRANSFORM
Promote raw loads into governed models
The transformations toolkit turns loaded resources into reusable models with @dlt.hub.transformation while its skills call dlthub transform run and dlthub dbt generate. Outcome: raw tables become governed analytical datasets without leaving the workflow.
uv run dlthub ai toolkit install transformationsOpus 5.0 · dltHub · ~/agent-observability
6 · VISUALIZE
Explore fresh data in notebooks and dashboards
The data-exploration toolkit helps agents inspect datasets and build Marimo views while its skills call dlthub runtime serve --app-type marimo and dlthub dataset head. Outcome: users see fresh, validated data as interactive analysis.
uv run dlthub ai toolkit install data-explorationOpus 5.0 · dltHub · ~/agent-observability
7 · SHARE
Hand off a live answer your team can use
The dlthub-platform toolkit publishes the notebook or data app from the same workspace while its skills call dlthub runtime publish and return a share URL. Outcome: teammates get a live, governed answer instead of a static screenshot.
Opus 5.0 · dltHub · ~/agent-observability
9 of 9
Ship the answer with pipeline-level confidence
The lifecycle closes where operations begin: every pipeline, transformation, validation, notebook, and shared answer remains traceable from the dltHub workspace to Runtime.
| Run | Started | Duration | Rows | Status |
|---|---|---|---|---|
| #4128 | 13:42 · today | 4.21s | 2,214 | Running |
| #4127 | 13:12 · today | 4.04s | 2,189 | Success |
| #4126 | 12:42 · today | 4.17s | 2,202 | Success |
| #4125 | 12:12 · today | 4.31s | 2,176 | Success |
| #4124 | 11:42 · today | 42.5s | 0 | Failed |
| #4123 | 11:12 · today | 4.08s | 2,164 | Success |
Complete agentic workflows for every phase of data engineering
Not autocomplete, not a chatbot on a dashboard. A guided sequence of skills, commands, rules, and MCP - with guardrails agents can't skip. Maintained by dltHub, controlling the infrastructure agents and pipelines operate on.
Discover individual skills per agentic workflow
See how each workflow guides your agent - step by step, from first prompt to production deployment.
The guided entry point. Names a use case, checks the workspace, and hands off to the right toolkit in a few prompts.
Opus 5.0 · Quick Start · ~/pipelines
Take me through the full workflow with the GitHub API
The guided entry point. Names a use case, checks the workspace, and hands off to the right toolkit in a few prompts.
Opus 5.0 · Quick Start · ~/pipelines
Take me through the full workflow with the GitHub API
Blueprints for data workflows
dltHub is a composable data platform. Blueprints are its ready-made builds: each one dltHub assembled for a specific use case, end to end, from the sources you already use to a production dashboard or API.
Your 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
Pydantic Logfire
Arize
Langfuse
LangChain
the managed infrastructure layerIngest and standardize traces into the OpenAI messages format as a training-ready dataset.
OpenAI
distil labs
Fine-tune a specialist model, served as a drop-in replacement via API to distil labs customers.
Frequently Asked Questions
What is dlt?
dlt (data load tool) is an open-source Python library for building data pipelines. It handles schema inference, incremental loading, nested data normalization, and works with 10,100+ sources. Apache 2.0 licensed and always free to use.
What is dltHub?
dltHub is the managed agentic platform for running dlt pipelines in production. It bundles a managed runtime (deploy with one command, no infra to patch), Python and SQL transformations orchestrated inside your pipeline, data quality checks that fail fast with actionable errors, a managed Iceberg lakehouse with the option to bring your own storage, and an MCP server so agents can analyze pipelines and datasets directly. The outcome: teams ship trustworthy data faster, without owning the infrastructure. See the full feature list in the dltHub docs.
How is dltHub different from a Claude skill or tools like Replit?
Tools like Claude skills or Replit are great for writing and running code. But they are not built for data engineering workflows end to end. dltHub gives your team complete agentic workflows that cover every phase: coding, running, deploying, and debugging pipelines, on infrastructure you control.
How is dlt different from Fivetran or a Python script that uses the request library?
dlt is the perfect match between standardization and customization. You get the automation that matters: schema inference, incremental state, normalization, and loading, while keeping the full flexibility and portability of plain Python. And with agentic dltHub workflows, your team can code, run, deploy, and debug pipelines faster.
How do I get access to dltHub?
dltHub is available now. Book a demo with our team to get set up, or see our pricing page for plans and what's included.