OS-style tiered memory: treat the context window as RAM and page to external 'disk'

Letta·medium signal

Letta/MemGPT gives the agent tool calls to page memory in and out of a fixed context window — main context acts as RAM, external storage as disk — so it maintains effectively unlimited memory under a hard token cap. The agent decides what to keep resident versus evict, rather than relying on naive truncation that destroys coherence on multi-step tasks. Adopt the RAM/disk mental model when a long-running agent keeps blowing its window.