One memory. Every AI.
Every AI you talk to has amnesia, and a wall around it. You re-explain the same context to each one, every session, and none of them share what they learn.
Kemory is a permissioned memory that lives across every AI you use. Tell one thing to one assistant and they all understand, with you holding the keys. Connect it to ChatGPT and your preferences, project facts and decisions are there from the first message — including the ones you explained last week, in a different client, on a different machine.
This is not another memory inside one assistant. ChatGPT remembers what you tell ChatGPT. Kemory is the layer underneath that travels with you: the same memory answers in ChatGPT, in Codex, in Claude, in Cursor, and in any other MCP client — with organisation-level scoping and an audit trail that a single assistant's memory does not provide.
What you can do with it:
How it is governed: every memory is scoped to a user and an organisation, and that scoping is enforced in the database rather than in a prompt. Colleagues cannot read each other's memories by default.
Memories are shared only when you deliberately promote them to a shared namespace, and every event lands in a hash-chained, tamper-evident audit log. We do not train on your data.
Kemory reads only what you deliberately capture into your own account. It never reads ChatGPT's own memory, chat history, conversation summaries or your files.
Kemory reads and writes. Every memory tool is titled and annotated, so ChatGPT knows reading from writing from deleting before it runs anything.
Requires a SeKondBrain account. Sign in over OAuth; there is nothing to install and no keys to paste.
Kemory by SeKondBrain — the memory layer of the SeKondBrain Cognitive OS. Beta version.
При подключении к Kemory ChatGPT может передавать этому приложению релевантные чаты и данные Памяти, чтобы учитывать контекст ваших запросов. Использование этих данных в Kemory регулируется его условиями и политикой конфиденциальности. Если у вас включена Память, данные из приложения могут использоваться, чтобы проактивно предоставлять полезную информацию или рекомендации. ChatGPT всегда соблюдает ваши настройки использования данных для обучения, в том числе данных из подключенных приложений. Использование приложений может быть связано с повышенным риском. Вы можете в любой момент управлять своими предпочтениями или отключиться от приложений в настройках. Узнать больше