Enqlave

Is it private?

Your documents are sealed on your device and stay sealed in the cloud. Here is the whole path — including the one step where a document is readable.

The journey of one document

Plaintext exists in two places only: on your own devices, and for the length of a single analysis call.

Your device Plaintext lives here The cloud Ciphertext only Your other devices Approved by you Model provider Reads one copy ENCRYPT · AES-256-GCM DECRYPT ON DEVICE ONE PLAINTEXT COPY ANALYSIS, ENCRYPTED FIRST

Who holds the keys

Library key AES-256-GCM seals every document WRAPPED WITH ML-KEM-768 Your Mac Your iPhone Your iPad private half in Keychain private half in Keychain private half in Keychain A new device gets nothing until you approve it by hand.

What the server can see

Encrypted

The document itself. Its filename, summary, labels, dates and embeddings — every one of them rides inside the ciphertext.

Visible

Routing metadata: which library a record belongs to, its id and version, which device wrote it and when, and how large the blob is.

  • Every record is sealed before it leaves the device, and the server has no key to open it.
  • We say “encrypted”, not “invisible” — a log of when and from where is still a log.

The one moment it’s readable

  • To describe a document, a model has to read it. That is unavoidable, and it is the single exception to everything above.
  • It runs under an enterprise agreement with zero data retention: the copy is not stored after the answer comes back, and it is never used to train models.
  • The copy goes straight from your device to the model provider — it never passes through Enqlave’s servers, and we keep no copy.
  • What comes back — summary, labels, embeddings — is encrypted on your device before it is stored.

Search never leaves home

  • Every client decrypts locally. The index lives on your device, not on a server.
  • Keyword and semantic search run entirely on the machine in your hands — nothing is sent anywhere.
  • Only when you ask a question does a short, summarized slice of the relevant documents go out, so the model can compose an answer.
Where this is going

As laptops and phones get faster, more of this work moves on-device — and the one readable moment shrinks toward zero. Today Enqlave uses frontier models because they give you materially better answers, and we would rather be honest about that trade than ship a worse product and call it privacy.

Enqlave — your documents, organized automatically.