Skip to main content
gbrain
Menu
Get Started

Codex

Codex, connected to the accounts around the code.

The same endpoint hands it your mail, calendar and web search.

Codex can work in a repo for hours, but it cannot see the accounts around the work: the mail that explains a change, the calendar that says when it ships, the docs on the live web.

gbrain connects on two sides. Point Codex at the endpoint and it can use those accounts mid-run, with every call logged and a permission deciding what it may touch. And your gbrain workspaces run OpenAI models, the same company behind Codex.

One endpoint connects Codex

Not one per service. What this client can call is decided by its permission, not by the address, and the token comes from the client's own page in the workspace, minted once and shown once.

Endpoint
https://gbrain.io/mcp
Header
Authorization: Bearer <token>

Every application Codex gets

Connect one in the browser and it answers here, under the same permission and the same record as everywhere else.

Your workspaces run OpenAI models too

The company behind Codex also makes models your workspaces can think with. Each one has its own page, and Models lists the full set.

The other places a connection answers are on Works with, and Tools explains the permission, the ceiling and the record they share.