Build XMemo context
recall_contextRead-onlyIdempotent
Build a context pack from saved memories to inform answers and plans. Retrieve preferences, prior conversations, projects, decisions, and TODOs using semantic search.
Instructions
Build a context pack from XMemo memories. Call this before answering or planning when the task could benefit from multiple saved memories — preferences, prior conversations, projects, decisions, TODOs, or long-running work.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. | |
| query | Yes | Natural-language question or search text. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | % |
| team_id | No | Optional team/workspace identifier for team-scoped memory access. | |
| agent_id | No | Optional client-supplied agent label for memory attribution. | |
| max_items | No | Maximum number of memory items to include. | |
| max_tokens | No | Approximate maximum response size. | |
| memory_type | No | Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %. | auto |
| output_json | No | Return a machine-readable JSON response instead of a human-readable summary. | |
| path_filter | No | Memory path filter; % matches all paths. | % |
| prefer_working | No | Whether to prioritize working/session-state memories in retrieval. | |
| agent_instance_id | No | Optional stable, non-secret agent instance ID for per-client attribution. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |