Engineering notes
How agent memory actually works.
Technical essays on request-path security, memory writes, context budgets, and the evidence behind the claims. Every article points back to the status ledger.
Put the proxy before the memory
Most agent-memory systems are designed from the retrieval side inward. A query arrives, vectors are compared, the best results are packed into a prompt, and the model answers. That design works in a notebook. It becomes dangerous the moment two organizations share the same database.
The memory write path is a refinery, not an insert
A memory system that only inserts rows is a log with a search box. The hard part is deciding what should become memory, what should replace something older, what should be quarantined, and what should never be written twice.
How to spend a token budget without losing the plot
“Retrieve the top ten memories and concatenate them” is not context assembly. It is a way to discover your model’s context limit in production.
Reading the evidence
Essays explain the design. Capability status, known gaps, and verification evidence are maintained in one place.