The specific design of this system uses the raw memories and allows rebuilding the operational memory from the raw memory (the LLL "Left Leg Layer").

To do this requires that there is an ordering of which memory came last.

    "always do X before committing Y"
    "always do X before committing Y except after Z"

Which of these is the current state? Without the date, it is not possible to rebuild the operational state of the rule from the raw records.

Oh cool. I'm working on exactly that here!

https://innerloop.works/breadcrumb

A timeline turns contradictory instructions into an orderly sequence of updates. Without it the model just gambles between the old guideline and the new one on every run

Thanks for the question. For a fixed rule like that, you're right, a date adds nothing. What the dates are really for is letting the AI live on the same clock as you. A model has no sense of time on its own, so it can't tell whether we last talked five minutes ago or two days ago. My setup injects the current time plus a timestamped index of past conversations into every turn. That way it notices on its own that it's been two days and asks how I've been, and it can answer "what were we working on yesterday?" The hook isn't in the repo yet, but I'm happy to add an example.

No? from a quick skim it doesnt look like it goes into the system prompt everytime, you just use search/grep over it. Pretty much most memory approaches relying on a big set of info where agent chooses what to 'recall'. Its like any other tool

Placing LLL inside the user message right ahead of the new query keeps the common conversation prefix fully intact