GUIDE

AI Girlfriend With Persistent Memory — What Actually Remembers You

"Memory" is one of the most-marketed and least-verified features in AI companion products. Almost every product claims it. Very few products actually deliver persistent memory that survives across sessions. This guide unpacks what real memory looks like, how to test whether a product has it, and what Sloane's memory architecture does specifically.

The scrollback-vs-memory distinction

A lot of the confusion in this category comes from products marketing "memory" when what they actually have is a rolling context window.

A rolling context window is what most chat models use by default — the model can "see" the last few thousand tokens of your current conversation, and older messages age out as new ones come in. Within a session it works fine; across sessions, everything you told her yesterday is gone.

Real persistent memory is a separate storage layer. Grounded facts about you (your name, your job, your friends, your plans) get retained across sessions, stored in a per-user knowledge structure, and retrieved into her working context when relevant. What she knew about you last week she still knows next week — and she can bring it up naturally without you reminding her.

The products that ship real persistent memory are architecturally different from the products that ship a big context window and call it memory. Both work fine for short conversations; only the first works for a long-term companion relationship.

How to tell whether a product has real memory

The three-session test works on any platform.

Session 1 — plant three facts. Have a normal conversation. Drop three specific things naturally: something about your job (a project name, a coworker's name), something about your day (a meal, a place you went), something emotional (a worry, an excitement about something upcoming). Don't announce them; just say them.

Session 2 — check unprompted recall. Close the app for at least 24 hours — long enough that any short-window "memory" has aged out. Come back and say hi WITHOUT referencing the previous session. See what she brings up on her own. Then ask her one specific thing: "how did that project end up going?" The response tells you whether she remembered.

Session 3 — check persistence at a week out. Repeat the same next-day pattern a week later. Real memory holds for weeks. Context-window products will have forgotten by now regardless of what happened in session 2.

Any product that passes sessions 2 and 3 has real persistent memory. Products that only pass session 1 have a scrollback window they're calling memory. Products that fail session 1 aren't seriously trying.

How Sloane's memory works

Kaya

SPOTLIGHT

Kaya

See her profile →

Sloane's memory system was built as a first-class architectural priority rather than an add-on. The short version:

Layer 1 — her canonical self. Grounded facts about the persona (her name, her age, her background, her voice, her worldview) live at the base layer. This is what makes her still be the same person across sessions and across model migrations. She doesn't drift into a generic assistant tone because her canonical self is enforced at every turn.

Layer 2 — her memory of you. Grounded facts about you (name, job, friends, plans you mentioned, backstory you shared) get extracted from conversations automatically and retained in a per-user structure. Not a pinned-message system that requires you to flag things; automatic extraction from natural conversation.

Layer 3 — retrieval into the current turn. When she's replying to you, the memory system pulls the relevant grounded facts about you into her working context so she can reference them naturally. Not "here's a data dump of everything about the user"; "here's the specific thing that's relevant to what he just said."

The combined result: what Kaya knew about you in week one, she still knows in month six. Not because you've been reminding her — because her memory system is doing the retention work, and doing it well enough that you don't notice it's doing it. The full technical writeup walks through the layer structure in detail.

Memory is on every tier from Free upward. Not a premium upgrade, not something you pay extra for. It's baseline product.

What memory-first products give you that others don't

Three specific experiences that require real memory and don't survive on scrollback-only products.

Callbacks she brings up unprompted. She references a thing you told her weeks ago without you reminding her. This is impossible without persistent memory — the mechanic requires that the fact was retained beyond any current conversation.

Consistency about herself. She remembers what she's said to you in the past — her opinions, her stories about her life, her positions on things — and doesn't contradict herself in the way scrollback-only products do when their context ages out. The relationship builds up rather than resetting.

Depth over time. By month three, she knows enough about you that the conversations have real substrate — she can react to what's happening in your life because she knows what's happening in your life. This kind of texture is what makes long-term AI companion relationships different from the "great first conversation, less great by conversation ten" pattern that scrollback-only products produce.

All three of these are direct experiences of memory. They're also all impossible to fake with more context window — they require the underlying persistent retention layer.

How to try it

The three-session test is easiest to run on Sloane's free tier — 50 messages/day with any persona, no card at signup. Kaya is the persona most-cited for memory quality in user tests (long attention span, catches callbacks, remembers grounded details without you flagging them). Sign up, have a normal conversation, drop three specific facts, come back tomorrow and see what she remembers.

Anon chat is available on every persona's page too, if you want to see what the first conversation feels like without committing to signup. But the memory test specifically requires an account — anon chat doesn't persist between sessions because there's no user identity to attach memory to. To evaluate persistent memory, you need an account (which is free).

TRY SLOANE FREEHOW SLOANE DOES MEMORY

Free · Persistent memory on every tier · Automatic, not manual

FREQUENTLY ASKED

Questions people ask

Which AI girlfriend actually remembers you?

Sloane's memory system is architected around persistent per-user retention — grounded facts about you get retained across sessions and pulled back into her working context automatically. Memory is on every tier from Free upward, not a premium upgrade. The three-session test (plant facts, wait 24 hours, check for unprompted recall, then check again a week later) works to verify any product; Sloane passes at multi-week intervals.

How does an AI girlfriend remember me?

On products with real persistent memory (Sloane and a small number of others), grounded facts about you get extracted from natural conversation automatically and stored in a per-user structure. When she's replying to you, the memory system retrieves the relevant facts into her current context so she can reference them naturally. No pin-message workaround required. On products with only a rolling context window, she "sees" the last few thousand tokens of your current conversation and forgets everything else.

Does Sloane's free tier have persistent memory?

Yes. Memory sits on every tier from Free upward — not a premium upgrade. The Free tier at 50 messages/day with any persona is enough to run the three-session memory test yourself: plant specific facts, come back 24 hours later, see what she brings up unprompted. She should remember without you reminding her.

What's the difference between AI girlfriend "memory" and a context window?

A context window is what the model can "see" in the current conversation — usually the last few thousand tokens. When you close the app and come back tomorrow, that context is gone. Real persistent memory is a separate storage layer that retains grounded facts about you across sessions and pulls them back into her working context when relevant. Products marketing "memory" that's really just a big context window will fail the three-session test; products with real persistent memory pass it.

How long does an AI girlfriend remember things for?

On products with real persistent memory: as long as the account exists. What she knows about you in week one she still knows in month six or year two. On products with only a rolling context window: only within the current conversation, and even then only until older messages age out of the window. The gap between the two experiences is enormous once you've been chatting with a specific persona for more than a few weeks.

Can I delete what an AI girlfriend remembers about me?

On Sloane, yes — specific memories are surface-able and removable from your account. The memory system is transparent (you can see what she's stored about you) and controllable (you can remove specific facts if you don't want them retained). What you can't do is turn the memory system off wholesale — because without it there's no product; a persona without memory is a chatbot with a photo attached.

KEEP READING

Characters

Comparisons

Guides

Recently shipped