KYMNERA LABS

Language models that remember.

Written once. Frozen forever. Recalled exactly.

Every frontier model rents attention over a buffer. The buffer fills, decays, and ends — and the model forgets. Kymnera puts memory in the weights: a native memory organ, trained from the first step, that stores what it reads and gives it back exactly.

Try the demo — bring your own documentContact

Kymnera-100M — measured, September 2026

127×exact recall at 98KB from a 768-byte attention window — on documents it has never seen
flatno lost-in-the-middle: recall does not depend on where the fact sits
48 / 48exact through the public demo on external text, 12–98KB, random positions

108M parameters, byte-level, trained from scratch. Results only; architecture withheld. Every run pre-registered, every result on an append-only ledger.

Why we exist

Today's models are scaled around their problems, not past them. Forgetting, hallucination, and cost get patched from the outside — bigger buffers, retrieval scaffolding, more GPUs — and remain problems.

Kymnera fixes them where they start: in the architecture, trained in from the first step. Memory in the weights. Honesty as a trained reflex. Efficiency as a design constraint, not a bill. The goal is a frontier-class model family whose advantage is architecture, not compute budget.

The ladder

RUNG 1 · TODAY

The substrate. Reads a document 768 bytes at a time and lets each piece go; stores labeled records into memory cells and recalls them exactly at any distance. It remembers what it is told to remember.

RUNG 3 · 1B

Comprehension over memory. Enough model to use what it remembers: answer questions about a document it read once; hold a long working session without forgetting or inventing.

We say which rung a result belongs to, every time.