{"version":"2.1.275","anchor":"post-turn-memory-new-memory-settings-layer-and-mcp-memory","canonical_anchor":"post-turn-memory-new-memory-settings-layer-and-mcp-memory","heading":"Post-turn memory: new 'memory' settings layer and MCP memory tool with read\/write\/append\/delete, gated by CLAUDE_CODE_POST_TURN_MEMORY","tier":"soon","area":"Memory","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.275\/e\/post-turn-memory-new-memory-settings-layer-and-mcp-memory","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.275","markdown":"### Post-turn memory: new 'memory' settings layer and MCP memory tool with read\/write\/append\/delete, gated by CLAUDE_CODE_POST_TURN_MEMORY\n\nA new 'memory' settings layer and MCP memory tool let Claude write, read, and edit notes across turns\n\n**What**\n\nClaude 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`.\n\n**Why**\n\nThis 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.\n\n- Area: Memory\n- Names: `CLAUDE_CODE_POST_TURN_MEMORY`, `memory_write`, `memory_read`, `memory_append`, `memory_delete`\n- Tier: Nothing to try yet\n- Useful: 5\/5\n- Signal: 5\/5\n- Present in the build but not switched on"}