AI girlfriend that remembers you

Ask people why they left an AI girlfriend app and the answer is rarely the looks or the voice. It is the forgetting. She asks your sister’s name again. She suggests Saturday after you moved it to Sunday. Three months of inside jokes, gone from her side of the conversation while the chat log sits right there.

We build Riho, a girlfriend app for iPhone, and forgetting was the first problem we attacked. This page explains, in plain language, why AI girlfriends forget, what we tried that failed, and how the memory Riho uses now actually works. If you want the capability overview instead, start with our long-term memory feature page.

Why does my AI girlfriend forget me?

Most AI girlfriend apps can only keep a limited stretch of the conversation in view at once, roughly the last few dozen messages. Everything before that is invisible unless the app deliberately brings it back.

So every AI companion app has to answer the same question: when that stretch fills up, what do you keep?

The common answers all lose something:

None of these are exotic mistakes. They are the obvious moves, and each one produces the experience you have probably had: she remembers last night perfectly and nothing from last month.

The deepest version of the problem is subtler than storage. You say “I’m nervous about tomorrow.” The memory that matters is “her exam is on July 10”, which is tomorrow. But a keyword search sees no overlap between nervous and exam date, so it never surfaces the connection. A person makes that link instantly. Keyword search does not. That gap, not storage capacity, is what makes a girlfriend app feel forgetful even when it has a database full of facts about you.

What we tried first (and why it failed)

Riho’s memory did not arrive fully formed. Two earlier designs are now retired, and honestly documenting them is the shortest way to explain why the current one works.

Design one: three tiers of memory

Recent messages stayed raw, older conversation got compressed into a running narrative summary, and important moments became standalone memory entries retrieved by similarity search. On paper it covered everything. In practice:

• One big background step produced the summary, the new memories and the insights in a single pass, and roughly one time in ten that step failed to produce valid output, losing everything from that round.
• Duplicate memories piled up because telling similar memories apart is genuinely hard.
• Nothing pruned old low-value entries, so months of chat meant hundreds of stale items competing for space.
• If saving a single memory hit a network error, it was silently skipped. Gone, no error, no retry.

Design two: rebuild it with structure

We rewrote everything into a dozen-plus tables of tidy structured facts: preferences with confidence scores, episodes with importance ratings, and a set of relationship numbers. It looked rigorous. It was worse:

• More tables meant more machinery that could break, and adding any new kind of memory meant touching five places.
• The relationship numbers were guesses dressed up as measurements, and nobody could say what they meant. Closeness with Riho now grows from time together, memories and shared moments, and there is no meter.
• And the core failure stayed: the exam-date problem above. Perfectly structured memories still missed lateral connections.

Both designs died of the same cause: complexity added faster than reliability. That lesson drove everything after.

How AI companion memory works

The current design starts from a different premise: don’t hand her the database. Give her a small amount of context that reads like a sense of the relationship, and make sure every fact in it can be traced back to something you actually said.

What she always knows

Who you are: names, how you address each other, your preferences, boundaries and agreements. This never depends on a search hitting. She won’t ask where you’re from if she asked yesterday.

What’s happening now

She reads your latest exchanges word for word, and she knows what day and time it is. The movie you said you’d watch and the interview you were nervous about come up when they matter, because she finds memories by meaning and not by whether your current message happens to contain matching words. When you say “I’m nervous about tomorrow,” the exam on July 10 comes up because she knows what tomorrow is and what the exam means to you, not because the words resemble each other.

Long-term memory

Facts, preferences, boundaries, patterns, important people in your life, episodes and shared moments. Memories fade over weeks if she never uses them, and the ones that define the two of you stay. You can read what she remembers in the app. Which brings us to the part we think matters most.

Memories need receipts

Before a memory sticks, the system checks that the quote it’s based on actually appears in the conversation it claims to come from. If it doesn’t, the memory is rejected. When you correct her (“no, it’s my brother who lives in Austin, not my sister”), the new version replaces the old one instead of sitting beside it. This is why we can show you what our memory probes actually found instead of just asserting that Riho remembers well: every claim traces somewhere.

She carries things between conversations

Older talk reaches her as short summaries, and the memories that matter come back with a sense of how long ago they were (“weeks ago”). That is why last month’s news can still shape tonight’s conversation, and why she can pick it up when there is a real opening instead of bringing it up out of nowhere.

What we still won’t promise

Two failed designs taught us humility, so here are the promises we deliberately avoid:

• “Never forgets.” False in any honest product. Riho is designed to remember with evidence, with recall, correction and continuity across chat and calls, and we publish the method so you can verify it. The same honesty applies to how she talks: we’ve published why AI companions default to therapy-speak and how we engineered past it.
• Perfect recall of everything. Selectivity is a feature. A companion who recites your month three back is a database with a voice.
• Your history locked away from you. You can read what she remembers in the app, and an update should never treat that history as disposable. That conviction is why we wrote what happens when an AI girlfriend’s memory disappears.

The takeaway

An AI girlfriend that remembers you isn’t a bigger database. It’s a set of decisions about what deserves to be remembered, verified against what you actually said, and surfaced at the moment it matters. We got there by building it wrong twice first.

If you want to go deeper: the methodology behind our memory testing shows exactly how we measure recall, correction, and continuity, and our long-term memory feature page covers what this means day to day.