AI builds. Humans govern. Schemas connect both.

One connected core model of what your data means.

Warehouses and pipelines, APIs and event streams, ontologies and content models, published standards and the schemas you wrote yourself. A library of connectors, and one governed model your team edits — that your agents build on, operate across, and answer from.

  1. 1Step 1

    Connect your models

    CoreModels reads the structure you already publish — a dbt manifest, a warehouse catalogue, a JSON Schema, a schema.org vocabulary, the taxonomy or ontology your team maintains. Nothing to migrate, nothing to rebuild. Connect one, or connect them all.

  2. 2Step 2

    Map it together, with AI

    The joins, the equivalences, the relationships — CoreModels helps your AI infer them across every source. Your human team talks them over and commits in a shared workspace, with AI as collaborator. Integrated, accountable, decision-traced.

  3. 3Step 3

    Point your agent at it

    Claude, Cursor, your own agents — they build on the model and operate across it. Import what dbt writes, audit drift in CI, answer what breaks, write the contract back. Assets, queries, reports, the daily work of the business. Coherent by construction.

What an agent did with dbt, end to end, in under five minutes

Imported a dbt manifest — 8 datasets, 39 columns, 3 vocabularies. Audited drift and caught an enum widened by one value. Answered which models break. Generated the enforced schema.yml contract back.

See the dbt connector

Watch CoreModels

One model. Every system. Every agent.

The meaning your business agreed on, written once and versioned. Every agent you run builds on it, operates across it and answers from it, in every system you own. When the model changes, their work changes with it.

Start your 14-day trial

Watch

CoreModels in 3m, 10m, or 60m

Same product, three lengths. Pick one and it opens here.

Who this is for

Data and pipeline teams

A dbt manifest, a warehouse catalogue, an Airflow DAG. You already publish the structure; nobody has written down what it means where it meets the rest of the business.

Find your connector →

Content, taxonomy and semantics teams

A schema.org vocabulary, a SKOS taxonomy, the ontology your team maintains. The definitions are yours. CoreModels makes them the ones every agent reads.

Find your connector →

API and integration teams

A JSON Schema, a Protocol Buffers file, an Avro contract. The shape systems promise each other, governed once and mapped to what the business calls it.

Find your connector →

Pricing

A library of connectors.
Simple pricing per builder, per team, or for the whole enterprise

Solo work. Team evaluation.

Builder

$49/ month

  • 1 builder seat · up to 3 projects
  • Up to 100,000 nodes per model
  • Unlimited view-only collaborators

Where teams build in production.

Team

$990/ month

  • 10 builder seats included · $99/month per additional seat · up to 10 projects
  • Up to 1,000,000 nodes per model
  • Unlimited view-only collaborators

Founding teams: $11,880 $5,880 for the first year, billed annually — the equivalent of $490 / month · renews at $11,880 / year · first 10 teams · while seats last. See the founding offer

No limits. Governed at scale.

Enterprise

from $4,000/ month

  • Unlimited projects, users & schema scale
  • SSO · SLA · private vaults
  • A named contact

Want the whole picture?

The CoreModels Solution Framework: what a core model is, where the methodology came from, why coherence is a capability, and how the platform is built.