Memory
memoryStore and retrieve documentation, decisions, tasks, and events to maintain persistent context across conversations. Use semantic search to find relevant information without filesystem tools.
Instructions
Persistent memory — docs, runbooks, specs, ADRs, decisions, lessons, tasks, and todos live HERE, never on disk: when the user mentions "the doc on X", "our runbook for Y", or "why we decided Z", use action="search" or list_docs/get_doc — NOT filesystem tools. Tasks here are lightweight project-tracking items; for tickets, bugs, incidents, releases, or handoffs use the entity tool instead. Event actions: create_event, get_event, update_event, delete_event (accepts event_id UUID or exact title; delete_all=true bulk-removes exact-title matches), list_events, distill_event, import_batch (bulk import array of events). Node actions: create_node, get_node, update_node, delete_node (accepts node_id UUID or exact title; delete_all=true bulk-removes exact-title matches), list_nodes, supersede_node. Query actions: search, decisions, timeline, summary. Task actions: create_task (create task, optionally linked to plan), get_task, update_task (can link/unlink task to plan via plan_id), delete_task, list_tasks, reorder_tasks. Todo actions: create_todo, list_todos, get_todo, update_todo, delete_todo, complete_todo. Diagram actions: create_diagram, list_diagrams, get_diagram, update_diagram, delete_diagram. Doc actions: create_doc, list_docs, get_doc, update_doc, delete_doc, create_roadmap. Transcript actions: list_transcripts (list saved conversations), get_transcript (get full transcript by ID), search_transcripts (semantic search across conversations), search_archive (hosted archive tier; local npm returns unavailable), delete_transcript. Team actions (team plans only): team_tasks, team_todos, team_diagrams, team_docs.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Mode metadata (capture/create filters) and query filter. Matches both structured `mode` and `mode:<value>` tag fallback. | |
| tags | No | Tags for event or task categorization | |
| agent | No | Agent identity metadata (capture/create filters) and query filter. Matches both structured `agent` and `agent:<name>` tag fallback. | |
| limit | No | Maximum number of results to return. | |
| order | No | Task order within plan | |
| query | No | Search query string. | |
| scope | No | Archive collection scope for search_archive: transcripts, decisions, lessons, docs | |
| title | No | Short descriptive title. | |
| action | Yes | Action to perform | |
| doc_id | No | Doc ID for get_doc/update_doc/delete_doc. For get_doc, accepts UUID or title/query text. | |
| due_at | No | Due date (ISO 8601) for todo | |
| events | No | Array of events for import_batch action | |
| reason | No | For supersede_node: reason for the supersede | |
| status | No | Backward-compatible alias for task_status in task actions | |
| content | No | Full content/body. | |
| node_id | No | Node ID (UUID). | |
| plan_id | No | Plan ID (full 36-char UUID): for create_task (link to plan), update_task (set UUID to link, null to unlink), list_tasks (filter by plan) | |
| task_id | No | Task ID for get_task/update_task/delete_task (full 36-char UUID) | |
| todo_id | No | Todo ID for get_todo/update_todo/delete_todo (full 36-char UUID) | |
| category | No | Input parameter: category. | |
| doc_type | No | Document type | |
| event_id | No | Event ID (UUID). | |
| metadata | No | Input parameter: metadata. | |
| priority | No | Task priority | |
| task_ids | No | Task IDs for reorder_tasks | |
| code_refs | No | Input parameter: code refs. | |
| completed | No | Todo completion flag for update_todo | |
| node_type | No | Input parameter: node type. | |
| relations | No | Input parameter: relations. | |
| delete_all | No | For delete_node/delete_event with a non-UUID lookup: delete ALL exact-title matches in one call instead of erroring on ambiguity | |
| diagram_id | No | Diagram ID for get_diagram/update_diagram/delete_diagram (full 36-char UUID) | |
| event_type | No | Input parameter: event type. | |
| milestones | No | Milestones for create_roadmap action | |
| project_id | No | Project ID (UUID). | |
| provenance | No | Input parameter: provenance. | |
| session_id | No | Session ID filter for list_transcripts | |
| client_name | No | Client name filter for list_transcripts (e.g., 'claude', 'cursor') | |
| description | No | Description for task | |
| is_personal | No | Mark as personal (only visible to creator). For create/list actions on todos, diagrams, docs. | |
| new_content | No | For supersede_node: the new content to replace the node with | |
| task_status | No | Task status | |
| todo_status | No | Todo status filter for list_todos, or status update value for update_todo | |
| diagram_type | No | Mermaid diagram type | |
| plan_step_id | No | Which plan step this task implements | |
| workspace_id | No | Workspace ID (UUID). | |
| started_after | No | ISO timestamp - filter transcripts started after this time | |
| todo_priority | No | Todo priority | |
| transcript_id | No | Transcript ID for get_transcript/delete_transcript (full 36-char UUID) | |
| blocked_reason | No | Reason when task is blocked | |
| started_before | No | ISO timestamp - filter transcripts started before this time |