🤫husshhussh
🤫husshhusshOnePuppy
Implemented · Cryptography · retrieval · personal computing

How do we retrieve private memory without handing over a life?

A useful private agent needs durable context, but sending an entire personal model to a backend defeats the premise. The problem is selective recall: enough relevant memory to help, no ambient plaintext collection, and an honest erase path.

Read the companion essayAll open problems
Problem statement

The hard question.

Select a minimal, query-relevant memory card locally; decrypt it only for the owner’s current session; and attach enough provenance for an answer to explain its grounding without exporting a private corpus.

Retrieval quality improves when a system has more context. Privacy usually improves when it has less. Treating that as a budgeted systems problem makes the trade-off explicit.

Status

What is true today.

The web vault holds its AES-256-GCM key and owner token in memory only and clears them on identity change, expiry, or lock. Portable, query-selective memory retrieval is active work, not a complete product claim.

Primary source: Personal World Model research

Constraints

The work is only useful if these survive.

  • A refresh re-locks the vault; keys and owner tokens are not browser-persisted.
  • Decrypted context must clear on account change, expiry, lock, or sign-out.
  • A whole-life memory dump is neither better retrieval nor a privacy win.
  • The backend cannot become the canonical plaintext personal-memory store.
Evaluation

How we would know.

Encrypted round-trip and cross-account isolation tests.
Recall quality at fixed, explicit context budgets.
Adversarial tests for stale, over-broad, and wrong-owner cards.
A first contribution

Start with something that can fail.

Prototype a local relevance gate with a fixed context budget, then measure answer quality, leakage surface, and failure behavior against a deliberately over-broad baseline.

Read it plainly, then make it better.

The companion essay is written for a broader technical audience. The repository and developer community are the places to turn a claim into a contribution.

Companion essayJoin Discord

One is a product of Hushh Technologies Corporation (brand: 🤫 “hussh”), an independent company. One runs on third-party silicon, systems, and cloud; platform names are used solely to describe where One software runs and imply no affiliation, endorsement, or sponsorship by those platforms. Our own go-to-market and bill-of-materials partner programs are real and actively in pursuit; we name a partner only once an agreement is executed.