· Counterparts ·
A field guide to memory — human & artificial
Its context window is working memory — a fixed buffer where thinking happens. When the conversation ends, it’s gone. In human terms that’s severe anterograde amnesia: intact intelligence, no ability to form a lasting memory. Solving it means borrowing from the one system that already did — the brain. This is a guide to how memory actually works, how AI is trying to copy it, and where the ground is still open.
The word for a memory
An engram is the physical trace a memory leaves in the brain — a term coined by Richard Semon in 1904Semon 1904, when it was pure theory. A century later, Susumu Tonegawa’s lab found the cells: they tagged the neurons active during an experience, then reactivated them with light and watched the memory returnTonegawa 2012–2015. Engrams are real, locatable, and switchable. This guide is organized around the mechanisms those traces are built from — one specimen at a time. For a plain explanation of a term, with the experiments behind it, see How memory works.
The spine
Each specimen reads the same four ways: how the brain does it, the model that formalizes it, how AI implements or fails it, and the map of who has claimed it. Where the map runs thin, there’s open ground.
Showing 11 of 11 mechanisms
EncodingAI: occupied
Not everything that happens is worth keeping. Something has to decide.
a new day starts — moments incoming…
Most of a day is never stored. Novelty, goals and emotional stakes decide what the brain encodes, and nearly every AI memory system tries to make the same call with an importance score.
The full entry: in the brain, the model, in AI, the mapEncodingAI: partial
The moments that mattered are the ones you keep. Feeling is the encoder's thumb on the scale.
small talk
▸ starts weak, fades fast · six months later:
barely a trace
Arousing moments start stronger and fade more slowly. AI memory systems usually keep only the first half of that.
The full entry: in the brain, the model, in AI, the mapStorageAI: occupied
Forgetting is not the failure of memory. It is one of its functions.
Contested — Whether forgetting is true decay or retrieval interference is a century-old, still-unsettled question.
day 0 · curve at
100
%
· everything is still fresh
Memories weaken with time unless they're renewed: steeply at first, then slowly. It is the most-copied idea in AI memory, and most copies decay in a straight line the brain doesn't follow.
The full entry: in the brain, the model, in AI, the mapStorageAI: partial
New memories crowd out old ones. Old ones distort new ones. They compete.
monparked: level 3, by the north stairs0.92
tuedentist, 2:00 pm0.94
two unrelated memories · both recall cleanly
Old memories get in the way of new ones, and new ones degrade the old. For AI agents it is the outdated fact that keeps coming back: well measured, barely solved.
The full entry: in the brain, the model, in AI, the mapRetrievalAI: occupied
Every time you remember something, you change it — and usually make it stronger.
every recall strengthens · every neglect fades — click a memory to keep it alive
Recalling a memory is not a passive read: it makes the memory stronger and easier to find next time. Every AI memory retrieves; few let retrieval change anything.
The full entry: in the brain, the model, in AI, the mapRetrievalAI: occupied
Recalling one thing pulls its neighbors with it — everything you learned in the same hour.
recalled that song on the radio ▸ surfaced with it:
12:30p (0.74) · 1:05p (0.67) — the
morning and evening
stayed dark
Memories formed close together get linked, so recalling one brings back the rest of the afternoon. AI systems copy it with session tags and memory graphs.
The full entry: in the brain, the model, in AI, the mapRetrievalAI: partial
Remembering to do something later — the memory that fires itself at the right moment.
○ armedpick up milk on the way home
an intention is armed — no timer, no alarm; it’s waiting for a moment that matches
A memory for the future: an intention that has to surface on its own when the time or the cue arrives. For AI agents it is mostly open ground.
The full entry: in the brain, the model, in AI, the mapTransformationAI: occupied
Memories aren't saved when they're made. They're rebuilt, offline, while you sleep.
Contested — How consolidation works long-term is actively debated — standard systems consolidation vs. multiple-trace theory.
5 traces in today’s buffer · 3 are about the same thing
A memory isn't finished when it forms. The brain replays it, especially during sleep, and slowly folds it into long-term knowledge; AI memory systems copy it with an offline merge pass.
The full entry: in the brain, the model, in AI, the mapTransformationAI: occupied
Recall makes a memory briefly editable. Then it's re-stored, sometimes rewritten.
Contested — The boundary conditions for reconsolidation — when a recalled trace becomes labile — are still debated.
● storedv1
We caught a twelve-inch trout at the lake, and a few people clapped.
one story, stored · each recall opens the copy, and the re-save keeps whatever changed
Recalling a settled memory can make it editable again before it is re-stored. AI systems do the tame version: update a fact in place and keep the old wording.
The full entry: in the brain, the model, in AI, the mapTransformationAI: occupied
"I met her on Tuesday" slowly becomes "I know her" — the event fades, the meaning stays.
Contested — Whether gist is compressed episodic detail or an independent multi-trace abstraction is unresolved.
1 day after the episode ·
0
of
5
details gone · the gist
is forming
Events lose their detail and leave their meaning. AI systems copy the split; distilling gist across many episodes, rather than one, is far less common.
The full entry: in the brain, the model, in AI, the mapTransformationAI: open ground
New facts don't land on blank ground. They're folded into what you already believe.
a standing picture of Sam — every new fact about them lands on this ground first
New facts are folded into what you already believe, which speeds learning and bends recall. On the AI side it is close to untouched.
The full entry: in the brain, the model, in AI, the mapThe map
Every patent, paper, and open-source system found across five rounds of adversarial prior-art search. Sorted by priority date, the shape is the finding: the field is occupied, not crowded — a convergence in 2023–2026, with Microsoft, the ex-Cerego team behind Alai Vault, DeWix, Snap, Meta, Samsung, and a fast-moving research frontier all arriving at once.
47 of 47 references
The uncharted region
If the obvious mechanisms are occupied, where is the real work? Read as a map, the search points fairly clearly.
Almost everyone is building memory systems; almost no one agrees how to measure them. Most results lean on synthetic benchmarks that don’t capture real interaction — the gap behind the RECALL conversation-grounded benchmark.
LLMs demonstrably can’t suppress outdated information. FadeMem and Counterparts both attempt mechanisms — but “the model retrieves a value it should have forgotten” is far better characterized than it is solved.
Nearly every system operates on days or weeks. What a memory should do over months and years — what genuinely consolidates, what becomes irrecoverable versus merely hard to find — is close to unexplored.
Human memory distinguishes “the trace is gone” from “the trace exists but the path is lost.” Most AI systems only delete. Graded, partially reversible forgetting has very little prior art and real conceptual room.
How this was built
The landscape was compiled from five escalating rounds of adversarial prior-art search conducted during the engram project (May 2026), Counterparts’ predecessor — broad academic and OSS sweeps, then patents across the US, Europe, Korea, and China, then focused deep dives on the closest references. The goal was deliberately hostile: not to confirm an idea was new, but to find everything that would prove it wasn’t.
References
42 prior-art references · 11 mechanisms · a defensive publication, not a patent. Take the map and go further.