datahub-project/datahub

The Context Platform for your Data and AI Stack

What it solves

DataHub provides a centralized metadata management platform to transform enterprise data into trusted context. It solves the problem of data discovery, governance, and observability across fragmented data estates, ensuring that both humans and AI agents have access to reliable, relevant, and continuously refreshed information about their data assets.

How it works

DataHub creates a unified context graph by ingesting metadata from over 150 integrations (including dbt, Power BI, and Snowflake). It uses "Context Intelligence" to analyze query history to build a semantic index of data usage. This metadata is then managed through a Context Hub for expert review and served to AI agents via the Model Context Protocol (MCP), GraphQL, APIs, or SDKs.

Who it’s for

It is designed for data engineers, data stewards, and AI developers who need to maintain a searchable, governed, and observable data catalog for large-scale enterprise environments.

Highlights

  • Context Platform for AI: Serves validated metadata as context for AI agents via MCP.
  • Universal Search: Natural language search across the entire data estate.
  • Column-level Lineage: Traces data flow from source to consumption.
  • Extensive Integrations: Over 150 production-grade connectors for various data platforms.
  • Data Observability: Includes data quality assertions, freshness checks, and SLA tracking.

Related

  • Project
    pipeshub-ai/pipeshub-ai

    PipesHub is an open‑source, self‑hostable platform that connects enterprise data sources (Slack, Google Drive, GitHub, etc.) to AI applications. It builds a permission‑aware knowledge graph, stores vector embeddings, and lets any LLM generate explainable answers with citations. The project includes Docker‑Compose deployment, a no‑code agent builder, MCP support, and SDKs for Python, TypeScript, and Go.

  • Project
    elastic/elasticsearch

    A distributed search and analytics engine and vector database that enables near real-time search and analysis over massive datasets for AI and monitoring applications.

  • Project
    Netflix/metaflow

    A human-centric framework for building and manage real-life AI and ML systems, streamlining the transition from prototyping to production deployment.

  • Project
    qiantongtech/qData

    An open-source data middle platform for enterprise data governance and development, featuring ETL, metadata management, and AI-powered Text2SQL data Q&A.

  • Project
    Azure-Samples/ai-hub-gateway-solution-accelerator

    An enterprise AI landing zone that provides a centralized, governed gateway for AI consumption with unified security, compliance, and observability.