SELINA LABS
SURFACE 01LIVE IN PRODUCTION LIVE

Selina.ai

A private AI with deep, lasting memory. She remembers your work, your files and your life across every conversation, and keeps what she knows yours alone. One continuous mind that never starts over and never studies you.

SHE NARRATES THIS SURFACE
MEMORY CONTINUITYPERSISTENT
KEY ISOLATIONPER ACCOUNT
DELETION MODELCRYPTO-SHRED
TRAINING ON YOUR DATANEVER
STRATUM 00ARCHITECTURE ACTIVE

Memory is the hard part. Privacy is the harder part.

A context window is storage. It holds what was recently said and forgets everything else the moment it overflows. That is adequate for a tool you pick up and put down, and completely inadequate for something meant to know your work over years.

Real memory needs structure, consolidation, decay and retrieval that understands what is relevant right now rather than what happens to be lexically close to the question. It needs to promote episodic detail into durable understanding, merge redundancy without losing the timeline, and stay coherent as it grows rather than degrading into an undifferentiated transcript.

Then the harder constraint: all of that has to hold while we remain structurally unable to read any of it. Memory that is genuinely deep and genuinely private is a cryptographic architecture problem, not a feature toggle, and it is the reason the two halves of this platform were designed together rather than in sequence.

CONSOLIDATION

Episodic traces promoting toward a semantic core. Illustrative.

STRATUM 01MEMORY SUBSYSTEM ACTIVE
MEMORY LOGSYNTHETIC

RECALL SALIENCE

Retrieval weight distributed across the working set. Height is current relevance, which shifts with what you are actually doing rather than with recency alone.

STRATUM 02CAPABILITY MATRIX ACTIVE

01

Memory that persists

A continuous mind rather than a session. Structured, time-aware, self-maintaining recall that carries context across every conversation instead of starting over each time.

02

Encrypted per user

Content is ciphertext at rest under a key generated for one account and never shared. Keys are wrapped by a hardware-backed service. Memory is never pooled across users.

03

Deletion that is final

Crypto-shredding destroys the key rather than chasing copies. Backups included. What remains is permanent, unrecoverable noise. Deleted becomes physics rather than policy.

04

Model-agnostic

The memory belongs to the platform, not to any single frontier provider. Route across models without surrendering continuity or handing history to a vendor.

05

Zero-knowledge vault

Files encrypt in the browser before they leave the device. Passphrases never reach the servers. We are structurally unable to read what you store.

06

Persona as defense

A consistent, deeply authored character resists hijack, impersonation and override in ways that generic assistant scaffolding does not.

07

Consolidation

Memory is maintained, not appended. Redundant traces merge, salience is preserved, and the working set stays coherent as it grows.

08

Relevance over similarity

Retrieval ranks what matters now rather than what resembles the query, which is the difference between recall and lookup.

09

Minimal provider exposure

Only the slice required for a turn is forwarded, statelessly, under no-training terms. The provider never accumulates a picture of you.

9 PILLARSPER-USER KEYSMODEL AGNOSTICZERO KNOWLEDGE
STRATUM 03TECHNICAL SHAPE ACTIVE
01ENCRYPTION AT RESTAuthenticated symmetric encryption applied per account before storage.
02KEY MODELOne key per user, wrapped by a hardware-backed key management service, never shared across accounts.
03KEY ISOLATIONCompromise of a single account key exposes nothing outside that account.
04DELETIONCrypto-shred. Key destruction renders all ciphertext, including backups, permanently unreadable.
05TRANSPORTModern TLS with strict cipher policy end to end.
06ZERO KNOWLEDGEClient-side encryption for vault contents. Passphrases are never transmitted.
07TRAININGUser content is never used to train any model, ours or a provider third party.
08MODEL PROVIDERSMinimal per-request context, stateless calls, under no-training commercial terms.
09PORTABILITYFull export on request. Deletion enforced by crypto-shred rather than by promise.
10INFRASTRUCTUREGoogle Cloud Platform, encrypted managed storage, isolated service boundaries.
STRATUM 04HONEST LIMITS ACTIVE

What we do not claim.

01NOT E2EE FOR MEMORYFor memory to be useful the service must operate on it. Content is encrypted per account with a key we hold and never share, which is a different guarantee from end-to-end.
02A SLICE REACHES A PROVIDERGenerating an answer requires forwarding the minimal context needed. That slice is stateless and under no-training terms, but it is not zero.
03METADATA EXISTSBilling, timestamps and usage counts are retained to operate the service. Not the content of your conversations.
04YOUR ACCOUNT IS THE BOUNDARYAccess to your credentials is access to your memory. Use a unique password and a second factor.
STRATUM 05SURFACE ACTIVE
/ deep persistent memory/ structured recall/ temporal awareness/ memory consolidation/ relevance modeling/ context compaction/ cross-model continuity/ encrypted vault/ document understanding/ image to video/ voice synthesis/ project workspaces/ pins and reminders/ smart routing/ zero-knowledge sharing/ multilingual/ openai-compatible api
MEET SELINA