Letta OS-Style Tiered Memory Architecture: RAM/Disk Hierarchy with Function-Call Memory Management for Production Agents

The New Stack·medium signal

Letta's tiered memory architecture mimics OS memory hierarchy — main context as RAM, external storage as disk — with agents controlling their own memory through function calls for reading, writing, and archiving. Combined with importance scoring, temporal decay forgetting, and vector reranking (second-pass model that re-scores similarity candidates), this pattern addresses the core agent memory problem: even 1M token windows can't hold full user history. Simple composable patterns consistently outperform complex frameworks.