Devoured - April 27, 2026
Anthropic launches Memory in Claude Agents for enterprise (1 minute read)

Anthropic launches Memory in Claude Agents for enterprise (1 minute read)

AI agentsenterprise Read original

Anthropic's Claude agents can now remember information across sessions with a new Memory feature that stores knowledge as manageable files.

What: Memory is a new feature for Claude Managed Agents that lets AI agents retain and build on information from previous sessions using a filesystem-based storage layer, with all changes logged via audit trails for enterprise compliance.
Why it matters: The filesystem approach with granular auditability gives organizations programmatic control to export, redact, or roll back agent knowledge, addressing enterprise concerns about AI memory transparency and governance.
Takeaway: If you're using Claude Managed Agents, the Memory feature is available now in public beta through the Claude Console and APIs.
Decoder
  • Managed Agents: Anthropic's enterprise offering that lets organizations deploy autonomous Claude AI agents to handle tasks and workflows
  • Filesystem-based memory: Memory stored as discrete files rather than opaque internal state, making it exportable and manageable
  • Audit trails: Logs tracking every memory change an agent makes, allowing organizations to review and control what agents learn
Original article

Anthropic has released the Memory feature for Claude Managed Agents, now accessible in public beta. This allows developers and enterprise teams to have agents remember and use information from prior sessions, making it possible for agents to accumulate knowledge over time without requiring manual prompt updates. Memory is designed as a filesystem-based layer, meaning data is stored as files that can be exported, managed through APIs, and scoped with permissions for various organizational needs.

The release is aimed at developers, enterprise customers, and technical teams using Claude Managed Agents. The feature is available immediately in public beta to all users of Managed Agents, with access through the Claude Console and programmatic interfaces. It supports a range of platforms by integrating with the existing Claude agent infrastructure.

Anthropic's approach with this release centers on transparency and control. All memory changes are logged, with audit trails for each session and agent, giving organizations granular control to roll back, redact, or manage data. This sets it apart from earlier versions and competitive offerings that may not provide the same level of programmatic control and auditability. Early adopters such as Netflix, Rakuten, Wisedocs, and Ando are already leveraging memory to streamline workflows, reduce errors, and accelerate processes. Industry observers note that the ability for agents to build memory over time could shift how companies automate complex workflows and manage organizational knowledge.

Anthropic, the developer of Claude, is recognized for focusing on enterprise-grade AI tools that prioritize safety, transparency, and developer control. This release aligns with their strategy of offering advanced agent capabilities for businesses seeking robust, auditable AI solutions.