Most "AI memory" demos are a bigger context window with better marketing.
What actually sticks is a tiny pipeline: decide what's worth keeping, park it, retrieve it later, and have a rule for when to stop keeping it. Skip that last part and you just accumulate sludge until the agent gets worse.
I tore "memory" into the five mechanisms people mash together, then wrote a ~90-line version that does the job.
Full piece (friend link, no paywall):
Top comments (0)