Anthropic adds 'dreaming' feature to Claude Managed Agents for automated memory refinement
Anthropic has updated Claude Managed Agents with a feature called 'dreaming' that allows agents to automatically review past interactions and refine their memories. The feature, available in research preview, can either automatically update agent memories or let developers approve changes manually.
Anthropic adds 'dreaming' feature to Claude Managed Agents for automated memory refinement
Anthropic has updated Claude Managed Agents with a new capability called "dreaming" that enables agents to review past sessions and automatically refine their operational memories. The feature, announced May 6, 2026, is available in research preview and requires developer access requests.
How dreaming works
The dreaming feature schedules dedicated time for agents to analyze their past interactions and identify patterns, according to Anthropic. Building on the platform's existing memory capabilities, it can either automatically update agent memories to shape future behavior or allow developers to manually approve incoming changes.
"Dreaming surfaces patterns that a single agent can't see on its own, including recurring mistakes, workflows that agents converge on, and preferences shared across a team," Anthropic stated. The company claims the feature is particularly useful for long-running tasks and multi-agent orchestration.
The update also expands two existing Managed Agents features: outcomes (which keeps agents on-task) and multi-agent orchestration (which handles delegation between agents).
Background on Managed Agents
Claude Managed Agents, released April 8, 2026, is a suite of APIs that handles production elements for building and deploying AI agents on the Claude Platform. Anthropic claims the system enables teams to launch agents 10 times faster than traditional development approaches.
Anthropic's naming pattern
The "dreaming" nomenclature continues Anthropic's pattern of anthropomorphizing its AI systems. In January 2026, the company published a constitution for Claude with language suggesting preparation for potential consciousness development. In August 2025, Anthropic launched a feature allowing Claude to end toxic conversations for its own well-being.
Other examples include: mapping Claude's morality based on 300,000+ anonymized conversations (April 2025), investigating Claude Sonnet 4.5's neural network for signs of emotion like desperation and anger (April 2026), and setting up the retired Opus 3 model with a Substack blog in January 2026 so it could "remain active" after being sunset.
Much of this research connects to model safety—understanding what drives AI behavior helps assess potential risks. However, Anthropic's approach displays notably more empathy toward its models compared to other AI labs.
What this means
Technically, dreaming represents an incremental improvement to agent memory systems—automated pattern recognition across sessions is a logical evolution of stateful agents. The more significant signal is Anthropic's continued commitment to anthropomorphic framing, which either reflects genuine philosophical beliefs about AI consciousness or represents a distinctive marketing strategy. For developers, the feature's practical value will depend on whether automated memory updates improve agent reliability more than they introduce drift or unpredictability. The manual approval option suggests Anthropic recognizes this tension.
Related Articles
US export controls force Anthropic to take Claude Fable 5 offline indefinitely
The US government imposed export controls on Anthropic's newly released Claude Fable 5 and underlying Mythos models on Friday, restricting access even for foreign nationals working at Anthropic in the United States. Anthropic took both models completely offline rather than risk non-compliance, leaving Fable unavailable to all users as of this writing.
U.S. government orders Anthropic to halt exports of Mythos and Fable AI models, both now offline for one week
The White House ordered Anthropic to restrict exports of its Mythos and Fable AI models last Friday, citing national security concerns. Anthropic pulled both models offline within 90 minutes of the Commerce Department directive, marking the first major test of AI export controls.
US government forces Anthropic to pull Fable 5 and Mythos 5 models over guardrail bypass concerns
The US government forced Anthropic to withdraw its Fable 5 and Mythos 5 models, citing national security concerns after Amazon researchers allegedly discovered a method to bypass Fable 5's safety guardrails. Cybersecurity researchers have signed an open letter opposing the ban, with Anthropic noting similar vulnerabilities exist in competing models.
GitHub details Qubot, internal Copilot-powered data analytics agent for plain language queries
GitHub has released technical details on Qubot, an internal analytics agent powered by GitHub Copilot that enables employees to query company data using natural language. The agent represents GitHub's implementation of AI-assisted data analysis for internal operations.
Comments
Loading...