Long-term memory
for AI agents,
in every language.
Ask it again. When one pass doesn't carry the answer, Tablet 2 returns memories it hasn't already given you. It stores images now too, and finds them from a sentence in any language.
Finer recall, higher accuracy. Scroll 1.2 finds memory by the sentence, so a fact said once, in passing, still surfaces. It scores 92.3% on LongMemEval-S, up from Scroll 1's 90.7%, in about 2,800 tokens of context per query.
Learns from its mistakes. A fundamentally different design, not the context-for-accuracy trade. Built for one goal: never repeat the same mistake. When it gets something wrong, it learns so it won't miss that way again.
Book — model pagecurl -X POST api.wontopos.com/api/v1/memory/recall
Don't take our word for it.
Ask the engine yourself.
This guide runs on your own LLM key, not ours. WOS loads the persona and everything it knows about the product and this page as memory, and the model simply speaks from it. We are showing you the engine by using it.
Connect your LLM key to start
The demo runs on your own key. It stays in your browser and is never sent to our servers.
Connect your LLM key
No login needed. Your key stays in your own browser - never sent to our servers.
Security: your key is never sent to our servers - it is saved only in your own browser's memory (sessionStorage) and wiped when you close the tab. We recommend using a temporary, scoped key and deleting it right after testing.
Type any model your key supports - we keep the latest as a default.
Three distinct
models.
Tablet, Scroll, and Book are separate models, not versions of one another; each is built for a different need, so you pick the one that fits.
Now it remembers images too. Tablet 2 scores 95.7% on LongMemEval-S and 67.5% on BEAM 1M, and can be asked again when one pass isn't enough. An image saved with no caption is found from a sentence in any language. Coming next.
Tablet 2 — full reportFiner recall, more context. Scroll 1.2 finds memory by the sentence, so a fact said once still surfaces. It scores 92.3% on LongMemEval-S, up from Scroll 1's 90.7%, and hands the reader about 2,800 tokens per query. Pick it when you would rather the reader saw more.
Scroll 1.2 — full reportLearns from its mistakes. Book is built on a fundamentally different design from Tablet and Scroll, not the same context-for-accuracy trade. It's made for one goal: never to repeat the same mistake. When it gets something wrong, it learns so it won't miss that way again.
Actual usage may differ from these numbers.
Your memory is yours. We hold it, and we don't look inside without your permission.
Our people and our models don't read your memories unless you ask us to, nothing ever trains on your data (no LLM runs in the retrieval path), one call erases a single memory or an entire user without a trace (GDPR-ready), and your LLM keys are sent per request and never stored while every memory stays isolated per account and user.
One file your AI
can read instantly.
Download a compact, LLM-friendly spec of the whole API. Drop it into your IDE or any coding agent and start building - no docs spelunking.
# Wontopos (WOS) - Long-term memory for AI agents > The same recall in every language. No LLM in the path. ## Start here - API key + a storage id (user_id) ## Won - free calls the MODEL makes for itself ## SDKs - in YOUR app · Python · TS · Rust ## MCP (beta) - in AI tools · Claude Code, Cursor ## Models & pricing Tablet $2/$3 · Scroll $4/$8 per 1M + endpoints, engrams, images, speakers, caching, trust ...