Anthropic's engineering team detailed a four-layer memory architecture for Claude spanning raw session logs, self-written notes, structured wikis, and auto-injected context, plus a post-session 'dreaming' step that revisits transcripts to fix and reorganize notes. Pokemon and database-QA tests show memory quality, not volume, drives performance, with Opus 5 the first model to form a complete learning loop.
Context Priming
上下文注入
Loading the full context of a target task into the model before querying, so responses draw on that context rather than parametr
Curated Intelligence
Anthropic published research titled 'The components of agent memory,' splitting Claude agent memory into four layers: session logs, memory notes, knowledge representations and context injection, plus a 'dreaming' mechanism that lets the model review logs, correct errors and distill rules during idle time. On the CL-Bench database QA task, memory-enabled Claude Opus 5.5 and Sonnet 5.5 scored 0.838 and 0.833 on average, well above their no-memory baselines.
The author describes a general technique for reverse-engineering agent products: instead of directly asking for system prompts or skill definitions, first have the agent load and execute the target skill, then ask it to reproduce the same inputs and outputs or draft a technical plan from that primed context. The approach works across products like Claude Design and Claude Duet, though complex skills may be reproduced incompletely and require follow-up questions.