Live

Marmot Data — Open-Source Data Catalog & Lineage

A self-hostable data catalog that indexes an organization's data infrastructure and serves that context to both people and AI agents via MCP.

Delivered and in production use.

What We're Building

The full scope of this engagement

A custom source connector extending Marmot's integration library
An internal AI assistant that queries Marmot's MCP server so employees can self-serve lineage and ownership answers
An automated lineage-generation agent that inspects pipelines and writes discovered lineage back via Marmot's API
An eval harness measuring whether AI agents given MCP access retrieve accurate, non-hallucinated data context

This is real, active work — talk to us about what you're trying to build and we'll tell you honestly what it would take.