Devs, Would You Mind Answering One Question?

It's been about two months since I started actually running this, not just building it, and I keep coming back to the same question instead of moving past it.

What I'm building

I work at Wontopos, a memory API in the same space as Mem0 and Zep. Store what a user says once, retrieve only what's relevant on each query, hand that to an LLM prompt. The long term goal, and I'll admit this out loud, is to become something close to standard infrastructure for AI memory at the B2B level. Not a feature bolted onto someone else's product, but the layer everyone building on AI just reaches for.

That's a long way off, and I'm aware of how that sounds coming from two months in. Right now what actually matters is much smaller. Get real developers to use it, and find out where we're wrong before we've committed to being wrong at scale.

Where the confidence went

This is the part I didn't expect. Watching actual usage come in has made me less confident, not more. I thought two months of real traffic would sharpen my sense of what people want from something like this. Instead it mostly sharpened my sense of what I don't know. People reach for memory for reasons I didn't anticipate, and skip it for reasons I also didn't anticipate. Neither of those is something I can fix by thinking about it harder alone.

What I'm actually asking

So here's the honest question, and I mean it plainly rather than as a lead-in to a pitch.

Where would you actually reach for a memory API. And what would you need it to do that you're not getting from whatever you use now, whether that's another memory product, rolling your own with a vector store, or just stuffing more into the context window and hoping.

Even a short answer helps. I'd rather hear "I wouldn't use this and here's why" than nothing at all, because silence doesn't tell me whether we're solving a real problem or a problem we invented.

Comments

[woochan]

Wrote a full rundown of what this actually does a couple weeks ago, linking it here instead of the post so this doesn't turn into a pitch: An Introduction to Wontopos.Knowing what I'm talking about will probably get you to a more useful answer than guessing at it.

[Mythex]

A real answer from someone who rolled their own: I'm building Mythex (an AI app builder), and we built memory in-house rather than using a memory API. Storage and retrieval weren't the slow part. These were:

1. Deciding what counts as a memory. We only learn from the user's own words, never from files, web pages, tool results or the agent's replies, and task requests ("add a login page") aren't remembered. Without that rule the store fills with junk, and with things planted by content the agent happened to read.
2. Provenance the user can see: each memory says whether it was added by the user, saved because they asked, or learned from a chat in a named project, with edit and delete next to it. People trust memory once they can see and fix it.
3. Limits and eviction: one short fact per memory, a cap, and when it's full the oldest learned memory goes, never one the user typed.
4. Keeping facts about the person (background the agent may use) separate from project rules (instructions it must follow).

So what would make me reach for an API: that write policy and provenance built in, a list I can render for users with edit and delete, and per-user delete and export in one call. At our size those mattered more than retrieval quality.