Every language, the same accuracy.

Recall quality is the same whether your users write in 日本語, 中文, Español, or English. We measure it as a grid of 70 store-language by query-language pairs and publish the number: 95.2% recall@5.

A store holding many languages is where retrieval usually degrades without anyone noticing: the same question scores differently depending on which language the memory was written in. We treat that as a defect rather than a limitation, and measure it as a full grid of language pairs.

One store, three languages at once

You don't pick a language per store - mix them freely. Below, one user's memory holds Japanese, English, and Spanish at the same time, and every question finds the right memory regardless of language. This is a real exchange against the live API:

# one user, three languages stored together
mem.add("彼女はコーヒーより紅茶が好き", user_id="alice")                      # Japanese
mem.add("she works at a design studio in Brooklyn", user_id="alice")       # English
mem.add("A ella le encanta hacer senderismo los sábados", user_id="alice")  # Spanish

"¿Qué bebe ella?"               -> 彼女はコーヒーより紅茶が好き
"what does she do on weekends?" -> A ella le encanta hacer senderismo los sábados
"彼女の仕事は?"                  -> she works at a design studio in Brooklyn

No translation step, no language detection, no per-language config. Memories and questions are placed by meaning, not by language - if the meaning matches, the language doesn't matter.

Why one language must not beat another

One rule sits above every other tuning decision here: recall quality must not depend on which language a memory was written in. It is measured across 70 language pairs and enforced in code review, and anything that would lift one language at another language’s expense does not ship.