DataHub
The Context Platform for AI Agents

DataHub is an open-source data catalog and context management platform that helps teams discover, understand, and govern their data assets. It provides a unified context graph with lineage, data quality, and governance capabilities designed to serve both human data teams and AI agents. Available as a self-hosted open-source solution or a fully managed cloud offering, it is trusted by over 3,000 organizations.
DataHub ingests metadata from structured data, unstructured documents, business apps, and semantic models into a unified context graph, then exposes it via MCP, APIs, and SDKs so both humans and AI agents can query and act on it.
Data engineers, data teams, and AI agent developers at mid-to-large organizations
Background.
- Status
- launched
- Business model
- freemium
- Company
- DataHub Project
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.