one place for your personal context.
across your agents.

Connect your AI app

one task shouldn’t need
your whole inbox.

they’re your memories.
you decide who knows what.

Muse can see Travel, Lisbon trip and Food.

see what you’ve shared.
stay in control.

a full audit log.
every agent, every use.

what your agent
can do.

your memories, accounts and personal info are end-to-end encrypted. not even Decoy can read them, except through a connection added inside an AI app.

Your vault keeps your personal context together across the agents you choose: memories, accounts, personal info and Decoy addresses. You decide what each agent can read or change. Memories, accounts and personal info are end-to-end encrypted: Decoy’s servers can’t read them, except through a connection added inside an AI app (see decoys.me/privacy). Decoy also reads an email address you verify for forwarding, to deliver your mail. Mail is encrypted as it arrives; ordinary email delivery still requires readable processing.

  • remember you

    save what it learns, and read the memories you allow.

  • sign into a website

    use the saved login for an account you choose.

  • use a passkey

    allow each sign-in on your phone. the private key stays there.

  • complete 2FA

    read an emailed code or generate a live TOTP.

  • finish checkout

    use an approved name, address and card.

  • read and reply to email

    use a Decoy address for one service, without connecting Gmail.

stored in Decoy
what you add or import, end-to-end encrypted
allowed for the agent
the access you approve
received by the agent
only what it requests within that access
shared with your agent
your AI provider can read the details you share

before you
connect.

explore the agent guides

You approve which accounts and information a connection can use, and for how long. Stored vault values are encrypted; approved values are decrypted in the agent’s runtime. Decoy cannot read those values, except through a connection added inside an AI app (see decoys.me/privacy); your agent and its provider can. You can review activity and revoke future access.

how to secure AI agent credentials