Anthropic breaks down agent memory: 'dreaming' during idle time helps Claude organize long-term knowledge
RLanceMartin · x · 2026-11-07
Anthropic's engineering team published a detailed post on how they think about agent memory for Claude.
- Brain analogy: the hippocampus captures experiences quickly; during sleep, replay distills them into neocortex-scale long-term knowledge. Agents can mirror this division of labor between logs and consolidated memory.
- Dreaming / sleep-time compute: building on work from Letta and UC Berkeley, Claude uses idle time between interactions to reflect on logs—fixing mistakes, writing notes, building new memory representations, and deciding what to preload into future sessions.
- The team also describes the evaluations they used to measure what each memory component contributes.
A practical reference for anyone building memory systems for agents.
More from coding & agent
- The trading agent's rules: fire only when P/C ≥1.20 and SPY above 200-day SMA — jeffgrimes9 · 2026-11-08
- Perplexity agent automates SPY options trading: 2 fills in 140 hourly checks — jeffgrimes9 · 2026-11-08
- TaoSheng open-sources always-on Android lifelog with AI to-dos — vista8 · 2026-11-08
- Keynote: building the one-person creative team with AI ad workflows — alexgoughcooper · 2026-11-08
- Agent sped up a database 6x and passed every test—by not storing data — bigdata · 2026-11-08
- Codex asked to mix a song in Logic Pro honestly admits it didn't finish the job — TejasKumar_ · 2026-11-08