Dimension Starter

Create your world.

Describe a company context or a personal space. Vercy will package its identity, authority, registries and operating rules into portable files and give your AI agent a safe instruction for growing the world with meta-models.

What world are you creating?

A Dimension is a sovereign context with one namespace and an accountable owner. It can describe an organization, a product landscape or a personal knowledge space.

Stable lowercase identifier, e.g. acme.world

Who has authority?

The Owner Package makes responsibility explicit. It does not expose private data; it states who may govern the structure and grant access.

What must this world know?

Select the context your agent should discover first. The package contains recommendations, but the agent must interview you before creating or filling any meta-model.

Where will the world live?

The meta-model remains independent of its storage format and interface. These choices only generate an initial binding that can be replaced later.

The generated agent instruction defaults to private repositories and requires explicit approval before publishing data, changing access, deleting records or contacting external systems.

Your Owner Package is ready.

Review the essentials, then download a Git-ready ZIP. Nothing entered here is sent to Vercy; generation happens locally in your browser.

Package contents

  • AGENTS.md - immediate agent orientation
  • README.md - human starting point
  • dimension.yaml - identity and authority
  • registries/meta-models.yaml
  • registries/meta-objects.yaml
  • registries/events.yaml
  • policies/access.yaml
  • policies/lifecycle.md
  • vercy.lock
  • agent/BUILD-YOUR-WORLD.md
  • agent/COMPOSE.md
  • meta-models/README.md
The AI instruction is the working engine.
It explains how to interview the owner, query the Vercy catalogue, recommend suitable specifications, ask for approval, and create populated meta-models in private repositories.
Open model catalogueHow composing works
What happens next

The package is the beginning, not the deliverable.

You download thirteen small files. From then on your AI agent grows the world for you: it reads the instruction in AGENTS.md, notices what your world cannot yet describe, pulls the matching data structures from the Vercy catalogue and fills them as the work demands. You approve each step. What accumulates is your own universe of data.

01

Your agent reads the instruction

The root AGENTS.md tells it what this world is, who owns it, what it may do and what always needs your approval.

02

It notices what is missing

You mention an entity, a decision or a document that no installed model can hold, or an installed specification points at one you do not have yet. Both are demand signals.

03

It fetches the structure

It finds the matching meta-model in the catalogue, proposes it with its version, and installs it only once you agree. The version is pinned by digest.

04

It fills the structure with you

It interviews you, records where every fact came from, marks what is still unknown and turns that into the next question. Nothing is invented.

The result is yours and portable. Plain files in your own repository or database, in a form that stays readable when you change tools, and that any conformant agent can pick up without being told how your world works.