Lab

The laboratory of memory and context.

We study how humans and AI lose, find again and use context.

Our goal:

keep less, keep better, and bring back the right information at the right time.

  • Capture better
  • Retrieve better
  • Give less, but better
  • Know when to say nothing
  • Stand the test of time

Nawame is not a frozen memory.

It is a system we keep improving so that AI understands your context better.

  • We observe.
  • We test.
  • We measure.
  • We correct.
  • And we keep going.

Durability

465 confirmed writes.0 violations observed.

How do we check that a confirmed piece of information does not silently disappear?

False precedents

When an AI thinks it finds something that does not exist.

We study how to tell apart:

  • a precedent found;
  • a possible match;
  • no convincing precedent.

Non-writing

Not everything deserves to become a memory.

Our first synthetic non-writing protocol correctly classified 26 events out of 26.

Reality will be more complicated.

That is precisely what we want to observe next.

Import

How do we import a memory without importing a false truth?

Imported information stays identified as such and never automatically becomes authoritative.

Nawame extends your cognitive surface.

It does not try to remember everything.

It tries to make your experience available again when it matters.