find_similar
Find memories semantically similar to an existing ref or free-form text to spot overlap and identify dedupe candidates during consolidation workflows.
Instructions
Surface memories semantically near an existing ref or free-form text. Use during consolidation/dream workflows to find overlap and dedupe candidates. Anchor with ref (an existing memory) or text (a fresh query). Self is always excluded when ref is given.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "find_similar"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ref | No | Anchor on an existing memory ref (excludes self from results) | |
| text | No | Or anchor on fresh text — embedded on the fly | |
| limit | No | Max neighbours to return (default 10) | |
| project | No | Restrict candidates to a project | |
| category | No | Restrict candidates to a category | |
| min_relevance | No | Drop matches below this cosine similarity (0..1) |