ModelBrain Download (beta)

Docs / Connect / ChatGPT

ModelBrain and ChatGPT

Copy a pairing code from the ModelBrain menu, add ModelBrain as a plugin in ChatGPT, and your memories work in ChatGPT the same as in Claude Desktop, Claude Code, or Cursor. This is the one connection that goes through a hosted relay, and this page explains exactly how it works.

Before you start
Step 1: get a pairing code from ModelBrain
  1. Open the ModelBrain menu and choose Connect to ChatGPT → Connect…
  2. ModelBrain reaches its relay and shows a short pairing code in the same submenu. Choose Copy Pairing Code.

A pairing code works once and lasts 10 minutes, so do this step right before step 2. Every state this submenu can show is listed in The ModelBrain menu.

Step 2: add ModelBrain as a plugin in ChatGPT
  1. Go to chatgpt.com, sign in, and open Settings from your profile menu. You can also choose Open ChatGPT Connector Setup in the ModelBrain submenu to land on chatgpt.com.
  2. Turn on Developer mode. Look for it under Security and login, or under Advanced settings on the Plugins page, depending on your ChatGPT version. Without it, the plus button in the next step does not appear.
  3. Open Settings → Plugins (or go straight to chatgpt.com/plugins) and click the plus (+) button to create a new one.
  4. Fill in the form:
    • Name: ModelBrain
    • MCP server URL: https://relay.modelbrain.net/mcp
    • Authentication: OAuth. There is no token or key to paste.
  5. Save it. The plugin first appears under Drafts, and ChatGPT starts the authorization step.
  6. ChatGPT opens a login page hosted by ModelBrain's relay. Paste the pairing code from step 1 and choose Allow.

ChatGPT renames and moves these menus from time to time. If a label here differs from what you see, the pieces to look for are the same: Developer mode, Plugins, a plus button, a URL field, and OAuth.

Step 3: confirm it works
  1. Open the ModelBrain menu. The submenu now reads Connected; ChatGPT can reach ModelBrain.
  2. In ChatGPT, start a new chat and choose ModelBrain from the Developer Mode tool in the message box. You pick which plugins each conversation can use, so do this in every chat where you want ModelBrain.
  3. Try it: ask ChatGPT to remember that my test word is pelican, then open a fresh chat, enable ModelBrain again, and ask it to recall your test word.
If something does not work

There is no plus button on the Plugins page

Developer mode is off, or your plan does not include custom plugins. Turn Developer mode on (step 2) and reload the page. On a Business, Enterprise or Edu workspace, an admin controls this setting.

The authorization page rejects my code

The code was already used or is older than 10 minutes. In the ModelBrain menu, open Connect to ChatGPT, choose Get a New Code…, and paste the new one.

The ModelBrain menu says "Connecting to ModelBrain's relay…" and stays there

Choose Cancel & Retry… in the same submenu. If it keeps failing, check that your computer is online, then see Troubleshooting.

Why this one connection is different

Claude Desktop, Claude Code and Cursor all run as local MCP clients: they talk to your ModelBrain daemon directly, on your own computer, with no network hop in between. ChatGPT cannot do that: it only reaches outside tools through a remote, internet-reachable connector. So this one connection is routed through a small hosted relay ModelBrain runs (relay.modelbrain.net), which pairs your ChatGPT session to your specific computer over an authenticated connection and forwards each request to it, and the answer back, over TLS.

The relay does not write what you ask ChatGPT to remember or recall to disk; it holds only the connection state needed to keep a device paired and a login session alive (device and session identifiers, access tokens), not message content. This is the one path where your requests pass through a server ModelBrain operates while in transit, rather than going directly between your assistant and your own machine.

Also works with

Claude Desktop, Claude Code and Cursor connect directly to your local ModelBrain, no relay involved: Claude Desktop · Claude Code · Cursor. Memory is shared across whichever of these and ChatGPT you use: the same notes, the same recall.

Questions

How do I connect ChatGPT to ModelBrain?

Open the ModelBrain menu, choose Connect to ChatGPT, then Connect, and copy the pairing code. In ChatGPT on the web, turn on Developer mode, open Settings → Plugins, click the plus button, and create a plugin named ModelBrain with the URL https://relay.modelbrain.net/mcp and OAuth authentication. When ChatGPT asks you to authorize, paste the pairing code and choose Allow. The ModelBrain menu then shows Connected.

Does connecting ChatGPT send my notes to ModelBrain's own servers?

ChatGPT can only reach outside tools through an internet-reachable connector, so this one connection is routed through a small hosted relay ModelBrain runs, which pairs your ChatGPT session to your specific computer and forwards each request to it and the answer back over an encrypted connection. The relay does not write request or answer content to disk; it holds only the connection state needed to keep the pairing alive. Claude Desktop, Claude Code and Cursor don't use this relay at all, since they talk to your local ModelBrain directly.

My pairing code stopped working. What do I do?

Pairing codes are single-use and expire after 10 minutes. Open Connect to ChatGPT in the ModelBrain menu and choose Get a New Code.

How do I disconnect ChatGPT?

Remove the ModelBrain plugin from ChatGPT's own Plugins settings.

No relay needed

These connect straight to your local ModelBrain, with no pairing code and no relay.

Claude Desktop → · Claude Code → · Cursor →
Stuck connecting?

Common setup problems and fixes for every client.

Troubleshooting →
Every item in the menu

A full reference for the ModelBrain menu bar and system tray menu.

The ModelBrain menu →