Anthropic launches Memory in Claude Agents for enterprise

Anthropic has launched Memory for Claude Managed Agents in public beta, giving agents persistent memory across sessions.

The feature uses a filesystem-based system with API access, permissions, export tools, and audit logs for enterprise control.

It is available now in the Claude Console and programmatic interfaces, with early adopters already using it in workflows.

The goal is to help enterprise agents improve over time without repeated prompts while meeting governance and audit requirements.