An observation-first kernel that preserves evidence and derives current beliefs — without overwriting history. Immutable observations, a confidence resolver, and a repository graph you can interrogate.
Most memory systems mutate: new information replaces old, and the trail is gone. Anamnesis keeps the two layers apart — the observation is immutable and permanent; the belief is derived, current, and always revisable as evidence accumulates.
Immutable, timestamped, never edited. The record of what actually happened stays intact no matter what is later believed about it.
Derived by a confidence resolver from all evidence to date. Revised, not overwritten — and always traceable back to the observations that support it.
Validated desktop agent profiles, each with a distinct lens on the same evidence. They request no microphone, speaker, display, network, or model access unless a profile grants it.
Notices what changed — surfaces new observations against the standing record.
Compares claims against evidence, holding beliefs accountable to their support.
Proposes testable hypotheses — inference reaching past the current evidence.
Governs archive metadata through a domain-agnostic boundary; retrieves on request.
A public, model-free measurement track (built on LongMemEval) asked a sharp question about delegation — whether one agent handing retrieval to another's lens actually helps. The honest answer wasn't the expected one.
The point isn't a smarter answer. It's that every belief can be walked back to the evidence it stands on — and the evidence is still there.