A new 'memory' settings layer and MCP memory tool let Claude write, read, and edit notes across turns
Claude Code's settings system now includes a new layer called memory, added to the existing list of layers (managed, user, project, local). Alongside it, a new internal tool exposes memory operations: memory_write, memory_read, memory_str_replace, memory_append, and memory_delete. The whole feature is gated by the environment variable CLAUDE_CODE_POST_TURN_MEMORY; when it isn't set, the related post-turn memory writing logic stays inactive. Write operations support three modes: replace, append, and insert.
This lays groundwork for Claude to persist notes or state after a turn finishes and read them back later, using a dedicated settings layer and a small set of file-like operations, though it only activates when CLAUDE_CODE_POST_TURN_MEMORY is set.
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
A `user_actor` activity does not always mean the user took the action. Processes that Anthropic runs on a user's behalf can currently appear as `user_actor` for the affected user rather than as `system_actor`, and this attribution may chan…manage-claude/compliance-activity-feed see the edit
A small documentation edit on Fetch the first page (newest activities first) and capture its trailing cursor. touched a line naming…