memorix_consolidate
Merge similar observations to reduce memory bloat by clustering related records using text similarity, then consolidating them into single records with all facts preserved.
Instructions
Find and merge similar observations to reduce memory bloat. Uses text similarity to cluster related observations by entity+type, then merges them into single consolidated records. Use action="preview" to see candidates without changing data, action="execute" to merge.
Example: 10 similar gotchas about Windows paths → 1 consolidated gotcha with all facts preserved.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | preview = dry run showing candidates, execute = actually merge | |
| threshold | No | Similarity threshold 0.0-1.0 (default: 0.45). Lower = more aggressive merging |