Anthropic gives Claude agents a ‘dreaming’ mode to tidy up their memories

The new feature lets Claude Managed Agents review past sessions, merge duplicate notes, and flag recurring mistakes without touching model weights Anthropic has taught its AI agents to sleep on it, sort of. The company unveiled a capability called “dreaming” on May 6, 2026, at its Code with Claude developers’ conference in San Francisco. The feature lets Claude Managed Agents step back from active work, review what happened in past sessions, and reorganize what they remember. Anthropic says the process sorts memories, fixes errors, and makes it easier for Claude to find the right information in later sessions. In early testing with legal AI company Harvey, task completion rates on realistic legal benchmarks reportedly jumped sixfold after dreaming was applied. How dreaming actually works An agent writes down notes while it works, in real time, without knowing which details will matter later. Over many sessions, those notes pile up like a junk drawer: duplicates, contradictions, half-useful observations, and the occasional genuinely valuable lesson buried at the bottom. Dreaming is the cleanup crew. It runs asynchronously, meaning it works in the background rather than interrupting ...