memory_query
Read-only
Retrieve a focused subgraph from memory to answer questions without flooding context. Uses hybrid search and graph traversal, with configurable depth and token budget.
Instructions
Answer a question with a TIGHT, relevant subgraph instead of flooding context. Seeds from hybrid search, walks the memory graph (hub-avoiding) up to max_hops, and returns a token-budgeted "context" string plus structured nodes — with an actionable hint when truncated.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The question to answer. Seeds from hybrid search, then walks the memory graph to return a tight, relevant subgraph instead of flooding context. | |
| max_tokens | No | Approximate token budget for the rendered context (~4 chars per token). Nodes are rendered until the budget is hit, then truncated with a hint. | |
| max_hops | No | How many hops to walk out from the seed memories (1-4). | |
| seed_limit | No | Maximum seed memories from the initial search. A gap cutoff drops seeds scoring below 20% of the top seed to keep the traversal focused. | |
| scope | No | Memory scope for isolation | |
| namespace | No | Namespace within scope (e.g., project name, team name) |