Where this sits
Plenty of people are building AI memory. Most are answering a different question than it first appears.
The map
Only one of them is competing with us.
| Kind | Who | What you get |
|---|---|---|
| Memory librariesfor developers | Mem0, Zep / Graphiti, Letta, Cognee, LangMem | Infrastructure for building agents. An API and a store — you bring the product. |
| Local-first assistantsself-hostable | Khoj, OpenClaw, note-app copilots | Answers retrieved from what you already wrote or sent. Very good at finding things. The memory is your existing material. |
| Hosted assistantscloud, funded | Town, and a wave of “personal AI twin” startups | Something that genuinely learns you — on their servers, under their terms. |
| Kainerosthis project | — | An assistant that writes its own memory of you, as plain files on your machine, and decides which version of a fact to believe. |
A snapshot, and it will date. Corrections welcome at contact@kaineros.com.
Credit where it’s due
Serious systems by serious people, several further along than this one. If what you want is on this list, go and use them.
The difference
Most systems settle a contradiction by recency, or ask a model to merge the two into something agreeable. Kaineros holds the rival versions side by side and ranks them pair by pair, with the deep model as judge. A passing remark has to win to overturn something settled; a deliberate correction takes hold at once.
Elsewhere it lives in a vector store or a graph you can’t read. Here it’s one Markdown page per fact, with its provenance, in a folder you own. Nothing to export, because nothing was ever encoded.
Plenty of systems extract memories asynchronously. Here the split is the design: a slow model compiling between conversations, a fast one that only ever reads finished pages — so the half you talk to never pays for the half that thinks.
The other side of it
A comparison that only flatters its author is worth nothing.
A note on numbers
The rankings you’ll find online trace back to blog posts and to each project’s own marketing, measured on different benchmarks and corpora. Reprinting them would imply a like-for-like comparison nobody has run. So this page compares approaches, which can be described honestly — and the only numbers on this site are ones we measured ourselves, with their method attached.
Same principle as the assistant: say what’s grounded, abstain from the rest.
Get involved
If you’re building in this space — or you think this map is wrong — I’d like to hear from you. contact@kaineros.com