Skip to content
Best Data Catalogs mark: an unfinished lineage pathBest Data Catalogs

Platform review

Context platform

DataHub review: an open-source context platform for AI agents

Short answer

DataHub pairs an open-source core with DataHub Cloud, a managed context platform that reaches agents through MCP, an Agent Context Kit, Skills, APIs and SDKs. It scores 8.02 and ranks 1 of 9. Column-level lineage depth and persona-scoped agent context are not stated on the pages we read.

By The Lineage Desk · Best Data Catalogs · Published

Desk research from public vendor pages. Editorial assessment.

8.02 / 10

Rank 1 of 9 on default weights. Change the weights

What does DataHub do for AI agents?

DataHub, formerly Acryl Data, offers DataHub Core as open source and DataHub Cloud as a managed context platform that unifies technical metadata, business knowledge and documentation for people and agents.

Agent interface
MCP, Agent Context Kit, Skills, APIs and SDKs, Ask DataHub
Lineage
Lineage and impact analysis built from query logs, dbt projects and BI dashboards
Deployment
Open source from a single node to cloud-hosted, hybrid and decentralized setups, or DataHub Cloud as managed SaaS.
Best for
Teams that want an open-source core or self-hosting, many agent interfaces and a large connector base

Which hops from warehouse to agent does DataHub document?

DataHub context path: documents 5 of 5 stages.1Warehouse and lakehouse2Transformation (dbt, ETL)3BI and semantic logic4Governance and access rules5Delivery to agents (MCP or API)
  • Solid dotDocumented on the vendor's pages
  • Dashed hollow dotNot documented on the pages we read

  1. 1Warehouse and lakehouse: Documented

    Snowflake and 100+ connectors.

    Source: DataHub Cloud context platform

  2. 2Transformation (dbt, ETL): Documented

    dbt projects feed Context Intelligence.

    Source: DataHub Cloud context platform

  3. 3BI and semantic logic: Documented

    Looker and BI dashboards.

    Source: DataHub Cloud context platform

  4. 4Governance and access rules: Documented

    Access and policy, data contracts, RBAC.

    Source: DataHub Cloud context platform

  5. 5Delivery to agents (MCP or API): Documented

    MCP, Agent Context Kit, Skills and APIs.

    Source: DataHub Cloud context platform

A filled node means the vendor's own pages describe that hop. It does not measure how well it works.

What are DataHub's key features?

What does DataHub claim?

What does DataHub cost?

DataHub Core is open source. DataHub Cloud has no list price on datahub.com; an AWS Marketplace listing (Discover & Govern) shows $75,000 for a 12-month contract with up to 20 monthly active users.

Entry price: $75,000 for 12 months (AWS Marketplace, up to 20 monthly active users)

Source: AWS Marketplace: DataHub Cloud listing

How does DataHub score on each criterion?

CriterionWeightScoreWhy
Agent access to contextHighest in set15%10 / 10MCP, Agent Context Kit, Skills, APIs and SDKs, with Claude, Cursor, Cortex, Genie, CrewAI, LangChain and Agent Development Kit named.

Source: DataHub Cloud context platform

Cross-stack lineage13%7 / 10Lineage and impact analysis built from query logs, dbt projects and BI dashboards; column-level depth is not stated on the pages read.

Source: DataHub Cloud context platform

Automated context build13%8 / 10Context Intelligence extracts metric definitions and join patterns "in days, not months" and flags context drift.

Source: DataHub Cloud context platform

Governance agents can use13%7 / 10Access and policy, data contracts and data quality, with RBAC, SSO and SOC 2 Type II; persona-scoped agent context is not described.

Source: DataHub Cloud context platform

Business definitions and metrics12%7 / 10Holds metrics and extracts metric definitions automatically; not a dedicated semantic layer.

Source: DataHub Cloud context platform

Answer quality checks8%7 / 10Detects context drift and routes it to experts; DataHub cites nearly 2X agent accuracy at Miro.

Source: DataHub Cloud context platform

Integration breadthTied highest10%9 / 10100+ pre-built connectors, plus an open-source project used by more than 3,000 organizations.

Source: DataHub Cloud context platform

Pricing transparency8%7 / 10Open-source core is free; an AWS Marketplace listing shows $75,000 for 12 months and up to 20 monthly active users; no list price on datahub.com.

Source: AWS Marketplace: DataHub Cloud listing

Deployment optionsHighest in set8%10 / 10Open source from a single node to hybrid and decentralized setups, or managed SaaS.

Source: DataHub Series B announcement

Where does it score well, and where does it fall short?

Scores well

Highest in set on: Agent access, Integrations and Deployment.

  • Many ways for agents to reach context: MCP, an Agent Context Kit, Skills, APIs and SDKs, with Claude, Cursor, Snowflake Cortex, Databricks Genie, CrewAI and LangChain named.
  • An open-source core that runs from a single node to hybrid setups.
  • A marketplace list price exists, which is rare in this category.

Falls short

  • Column-level lineage depth and persona-scoped context for agents are not stated on the pages we read.
  • Direct pricing is not published; the only figure is a marketplace listing.
  • Answer checking is described as drift detection and expert routing rather than testing agent answers.

Key facts

Company
A $35M Series B led by Bessemer Venture Partners was announced on 21 May 2025, for $65M in total. Palo Alto, California; CEO Swaroop Jagadish, CTO Shirshanka Das.

Source: DataHub Series B announcement

Customers named
Named on DataHub's pages: Pinterest, Miro and Netflix.

Source: DataHub Cloud context platform

How does DataHub compare head to head?

DataHub alternativesBuild a shortlist with DataHub

Frequently asked questions

What does DataHub cost?

DataHub Core is open source. DataHub Cloud has no list price on datahub.com; an AWS Marketplace listing (Discover & Govern) shows $75,000 for a 12-month contract with up to 20 monthly active users.

Does DataHub have an MCP server?

Yes. DataHub lists MCP alongside an Agent Context Kit, Skills, APIs and SDKs.

Can DataHub be self-hosted?

Open source from a single node to cloud-hosted, hybrid and decentralized setups, or DataHub Cloud as managed SaaS.