Anthropic details Claude agent memory architecture and offline dreaming

Anthropic published an Engineering Blog post on 6 November 2026 detailing how it designs and evaluates persistent memory for Claude agents. Drawing an analogy to hippocampal memory consolidation during sleep, Anthropic separates live session logging from offline consolidation, a background step the team calls “dreaming”.

During offline consolidation, Claude reviews raw session transcripts, filters out transient noise, resolves contradictions when earlier assumptions failed, and organises durable facts into structured wiki-style notes with an index layer injected into the start of future sessions. On the CL-Bench database evaluation across 30 sequential questions, adding the memory store lifted Claude Opus 5.5 from a 0.655 stateless baseline to 0.838 mean reward, and Claude Sonnet 5.5 from 0.644 to 0.833.