RLM removes the context ceiling. The unlock is at the intersection of RLM, retrieval that stuffs the REPL with existing art, and memory that distinguishes what is forever-true from what should be forgotten.

Context windows were never going to be the architecture. Once a model can operate over more than it can hold, the question becomes what you put in the environment and what you refuse to forget.

Retrieval without an RLM still truncates. An RLM without retrieval still starts empty. Memory without a theory of permanence becomes a junk drawer.

This is a forward call. It contains no benchmark I would have to look up. If it is wrong, it will be wrong in public, dated.