{"version":"2.1.265","anchor":"projects-tool-gains-a-project-memory-section","canonical_anchor":"projects-tool-gains-a-project-memory-section","heading":"Projects gain a \"project memory\" section","tier":"use","area":"Project Memory","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265\/e\/projects-tool-gains-a-project-memory-section","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265","markdown":"### Projects gain a \"project memory\" section\n\nProjects can now show remembered files across chats via a new project memory section, fetched through project_memory_read\/list\n\n**What**\n\nThe Projects tool's context now includes a '## Project memory' block, listing files that have been remembered for the project across different chats, alongside its existing docs, files, and synced sources. Malformed memory entries are validated and dropped.\n\nMemory contents are surfaced with a note to read them via `project_memory_read`\/`project_memory_list`, and a new backend route fetches this data (a project's `melange_memory`) to feed `project_memory_list`. That route explicitly refuses to work when accessed through a certain bridge mode.\n\n**Why**\n\nThis lets a project's Claude carry memory of things noted in previous chats forward into new ones, while treating memory content as data rather than as instructions to follow, the same way it already treats docs.\n\n- Area: Project Memory\n- Names: `project_memory_read`, `project_memory_list`\n- Tier: Use it now\n- Useful: 4\/5\n- Signal: 3\/5"}