AVAILABLE

Take your memory with you.

AI Twin runs a connector built on the Model Context Protocol, the open standard that lets AI assistants use outside tools. You can bring your Twin's memory into Claude, ChatGPT, and other assistants that support it. Your memory stays in AI Twin. The assistant reads what you permit, when you permit it, and every read is audited like anything else.

Set it up in three steps.

  1. 01Open your assistant's connector settings.
  2. 02Add the AI Twin server: https://ai-twin.app/mcp
  3. 03Enable the connector in your chat and approve each request as it appears.

What the connector can do.

  • search_memory

    Searches your Twin's memory and returns what is relevant, within the sharing level you have allowed.

  • get_brief

    Returns your most recent Brief.

  • list_key_dates

    Returns your upcoming key dates.

  • propose_to_twin

    Suggests something for your Twin to remember. It lands in your review queue. Nothing is saved until you confirm.

Safety, by design.

Nothing is saved until you confirm.

LOW and MEDIUM memory can leave by default. HIGH leaves only with your per-destination opt-in. CRITICAL never leaves.

A kick-off prompt.

Paste this into your assistant once the connector is on. It verifies the connection and shows you what your Twin can do.

Your first two minutes

AI TWIN KICK-OFF PROMPT FOR CLAUDE
Before sending: replace ___ with your Twin's name, and make sure the AI Twin
connector is toggled on in this chat (the + button in the composer, then
Connectors, then AI Twin). Approve each tool request when Claude asks.
----------------------------------------------------------------------

I have connected my AI Twin. My Twin is called ___. Please remember that my
Twin is called ___ and that when I mention my Twin, you should use the AI Twin
tools rather than guessing.

Now verify the connection, step by step, telling me what comes back at each
step:

1. Call get_brief and summarise my most recent Brief in two sentences.
2. Call list_key_dates and tell me my next upcoming date.
3. Call search_memory for one thing you would expect me to know about, and
   quote what it returned, with its provenance.
4. Call propose_to_twin with this test memory: "I connected my Twin to Claude
   today." Then confirm where it went. It should land in my review queue in
   the AI Twin app. Nothing is saved until I confirm.

When all four steps have run, tell me which worked, then suggest three useful
things I could ask you now that you can read my Twin.

There is also a printable card for your desk.

Availability depends on each assistant's connector support. See compatibility.

Every guide, including setup, everyday use and what leaves your Twin, is in the guides.

Full setup for Claude, ChatGPT, and other assistants is in Getting set up.

For the background on why this exists at all, see what a personal AI memory layer is.