Technical series
Memory in personal agents
How to think about memory, forgetting, provenance and trust in agents that work with personal context.
Reading order
01 The Problem of Memory in AI Making an AI remember looks like a storage problem. I learned, by getting it wrong, that it is three problems — and none of them is solved with more bytes. 02 Why Remembering Everything Is Bad Saving everything looks like prudence. But there is a kind of bug that never shows up in any log: the system does exactly what it was told and the results get worse. Too much memory is that bug. 03 The Difference Between Conversation, Memory and Knowledge For months, my system had two opposite defects I treated as one: it forgot too much and it remembered wrong. The fix was not code — it was realizing I was operating three layers with a single knob. 04 Memory as a Database Problem The question that broke Atlas's first memory was simple: why did I decide this? The system had the answer stored — and could not answer me. This essay is about what was missing. 05 Memory as a Ledger I destroyed a decision without ever pressing delete. Editable memory collapses three different truths into one mutable sentence — and a personal ledger is what pulls them back apart. 06 Provenance: Every Memory Needs a Source A memory can be correct and still not deserve trust. Without a traceable origin, it cannot be revised, challenged or used by agents with responsibility. 07 Governed forgetting Forgetting is not a memory failure. It's policy: the system decides what stops influencing the present, records the decision, and can reverse it. Without that, the ledger becomes an uncurated archive. 08 Compaction as memory design The ledger never erases, so it only grows. Compaction is the mechanism that keeps the weight of the past from freezing the present — rebuilding active state without losing the chain of provenance.