on top of any data warehouse.
dltHub is an AI-native data engineering platform for teams of humans and agents. Your team and their agents generate and manage high-quality data at scale, on infrastructure we run for you.
Any engineer on your team can ship production data, with agents doing the work on infra we run. Every run is logged and auditable.
Paste this prompt into Claude, Codex, or Cursor. The agent does the rest.
Run uvx dlthub-start@latest to build my first pipeline and run it on dltHub
Your coding agent
Claude Code, Cursor or Codex
dlt Sources
Salesforce
Postgres
HubSpot
the managed infra layerdltHub 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 infra layerIngest and standardize traces into the OpenAI messages format as a training-ready dataset.
distil labs
Fine-tune a specialist model, served as a drop-in replacement via API to distil labs customers.
"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
Build a pipeline that loads CRM contacts and deals into my warehouse using dlt
Not autocomplete, not a chatbot on a dashboard. The harness is the skills, commands, rules, and MCP tools that walk Claude Code, Codex, or Cursor through building a pipeline and then keeping it running in production: scheduled runs, schema changes, failures. Maintained by dltHub and wired to the infrastructure your pipelines run on, so your data team ships without a platform team.
What your agent reaches for, step by step, from first prompt through the pipelines it keeps running.
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
For regulated life sciences · GxP
dlt is code-native, test-first ingestion; dltHub runs it. Together they satisfy CSA and GAMP 5 without freezing versions or exposing you to platform churn.
Pin the validated baseline
OpenAIgit tag validated/veeva-vault@1.4.0tag created · this exact code is what you validate
Prove it behaves the same every run
pytest tests/behavioural/214 passed · same input, same output
Open the evidence trail
dlthub showrun history, schema contracts, lineage · the ALCOA+ record
Snowflake Industry Competency
Recognised for healthcare and life sciences data workloads on Snowflake.
As a simple-to-use Python library, dlt is the first tool that this new wave of people can use. By leveraging this library, we can extend the machine learning revolution into enterprise data.
Julien Chaumond
CTO/Co-Founder at Hugging Face
Python and machine learning under security constraints are key to our success. dlt is a lightweight yet powerful open source tool we can run together with Snowflake. Now anyone who knows Python can self-serve to fulfil their data needs.
Maximilian Eber
CPTO & Co-Founder at Taktile
I am building our internal skills usage leaderboard so we can see how people are using AI and spread what's working. dltHub turns this into a cohesive process without messy scripts to dedupe queries or wrangle intermediate tables. And the best part is anyone on the team can use agents to easily contribute.
Nate Sesti
Co-Founder & CTO at Continue
It's easy to write AI-assisted code and get a prototype. dltHub instead is built for the inspect-validate-debug loop, which is where AI-assisted data engineering actually lives or dies. The first platform I've seen that treats that loop as a design assumption, not a feature.
Savin Goyal
CTO & Co-Founder at Outerbounds (acquired by Anaconda)
The modeling layer is where the real cost lives, and it's where consulting companies like ours have been doing the most repetitive, high-cost manual work. We are excited about the dltHub product vision for the modeling layer because the main challenge in all data projects is how the data is being interpreted.
Thomas in't Veld
CEO at Tasman Analytics
In dltHub, agents propose transformations in Python, dlt.hub.transformation compiles them to SQL through Ibis, and execution stays inside DuckDB. The data doesn't move into Python memory at any step — the same composition pattern Ibis and Arrow are designed around.
Wes McKinney
Builder of Apache Arrow, pandas, Ibis at Posit
Every Ops leader is trying to answer the same question: is my team getting better or worse? I always had good intuition about what data I needed, but never the resources to get it and measure it reliably. dltHub changes the equation: it's the first product I've seen built for operators and their agents, not just fully-staffed enterprise data teams.
Jacob Matson
Developer Advocate at MotherDuck
dltHub and Snowflake deliver a simple, end-to-end pathway for financial institutions to transform raw data into governed analytics and AI-ready datasets without needing a full engineering team. You can pull data from core banking systems, market feeds, and APIs directly into Snowflake.
Suraj Rajan
Field CTO, Financial Services at Snowflake
dltHub lets my agents develop data pipelines locally, test changes quickly and cheaply in CI, and then runs them in the cloud against my largest workloads. It gives them the tools to take care of the knucklehead stuff so that I can get a good night's sleep.
Josh Wills
Member of Technical Staff at DatologyAI
We weren't looking for a custom rebuild, and we didn't want to staff up a data team to run something we couldn't sustain at our size. The toolkit by dltHub took what we already had, structured the parts that needed cleaning up, and gave us back a stack we can confidently run, with Chat-BI on top that actually understands our business.
Martin Miodownik
CTO & Co-Founder at NAVIT
We needed analytics on our GitHub Actions CI. With dltHub we wired the end-to-end pipeline up in hours, not days. Now we see where builds drag, fix the slow spots, and ship faster.
Simon Rosenberger
Head of Data Platform at Tower.dev
The quality of AI output depends on the frameworks and context used. This is where the dltHub AI Workbench shines. Ingestion used to sit with me and one other person. Now our analytics engineers self-serve.
Bijan Soltani
Founder & Managing Director at Gemma Analytics
Ingestion moved from being owned by a small group with deep tool knowledge to something any Python developer on the team could author, review, and ship. The question changed from "who knows the tool?" to "what data do we need next?"
Euan Johnston
Senior Analytics Engineer at dentolo
For financial services
dlt pipelines are code-native and version-controlled, and the dltHub context catalog carries the lineage. Mapped to SR 11-7, SOX ITGC, and BCBS 239.
Pin the validated baseline
git tag validated/market-feed@2.1.0tag created · this exact code is what auditors review
Prove it behaves the same every run
pytest tests/behavioural/187 passed · reproducible, deterministic output
Open the evidence trail
dlthub showrun history, schema contracts, lineage · your audit record
Snowflake Industry Competency
Recognised for financial services data workloads on Snowflake.
Agent-led migration off your legacy vendor, 90% faster.
A months-long migration is what keeps teams tied to legacy tools they have outgrown, and what vendors count on to keep you locked in. We make it the easy part. Our engineers, armed with internal AI tooling, rebuild your Fivetran, Airbyte, and custom Python pipelines as clean dltHub code. We hand over pipelines running in production and coach your team on AI-forward data engineering.
Use dlt as your open-source ingestion foundation and move to dltHub when you need managed runtime, observability, and governed collaboration at scale.
Apache 2.0
pip install dltFree, self-paced course. From first prompt to production deployment.
dltHub's agentic workflows come with a REST API toolkit that taps directly into dltHub Context - a hub of deeply researched, enriched context on REST APIs across SaaS sources, databases, and destinations. Your agent pulls exactly what it needs to code any dlt pipeline, in minutes.
We already cover more than 10,100 sources, with a clear path to hundreds of thousands. From prompt to pipeline to live reports in a notebook - all in one agentic flow, with outputs tailored to data users.
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. Not just a skill, not just an editor, but a guided workflow from first line to production.
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, with the reliability you can trust at every step.
dltHub is the managed platform for deploying and operating data pipelines built with dlt. It provides a runtime, observability, data quality checks, and collaboration features so teams can go from development to production with one command.
dlt (data load tool) is an open-source Python library for building data pipelines. It lets you write any connector, run anywhere, and requires no backend. dlt is Apache 2.0 licensed and always free to use.
