OpenMetadata
Open-source context layer giving AI agents governed data memory.
About
OpenMetadata is an open-source metadata platform that has repositioned itself as the open context layer for AI. It unifies technical metadata, data quality signals, column-level lineage, ownership, usage, policies, glossaries, data contracts, and data products into a single metadata knowledge graph.
With 130+ connectors, semantic search, open APIs, SDKs, and an MCP server, it is designed so both humans and AI assistants can discover, understand, and trust data. The pitch is that AI does not need another raw database connector; it needs context and memory, and OpenMetadata aims to supply that as an open standard rather than a vendor silo.
What it can do
- Unified metadata knowledge graph
- 130+ source connectors for ingestion
- Semantic search over data assets
- MCP server for AI agent access
- Data quality tests and data contracts
Setup
Deploy via Docker Compose or Kubernetes Helm charts; add connectors from the UI to start ingesting metadata.
Prerequisites
Docker or Kubernetes; credentials for the data sources you want to catalog.
Use cases
Works with
Trust score — 8/10
Scored 8/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 90; Trending score 84/100 from researcher assessment.
Sources
Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.