AVAILABLE

Take your memory with you.

AI Twin runs a connector using the Model Context Protocol, the open standard that lets AI assistants use outside tools. Add it to 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 any other.

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. 03Sign in and choose what the assistant may read.

What the connector can do.

  • search_memory

    Search your Twin's memory and return what is relevant.

  • get_brief

    Return your most recent Brief.

  • list_key_dates

    Return your upcoming key dates.

  • propose_to_twin

    Suggest something for your Twin to remember. It lands in Pending Review and is never 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.

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