CatNodesTool

boolean

string

string

(optional): Query in JSON format to filter documents

Removes outdated or incorrect memories by document ID.

(optional): The format of SearchIndexTool response. options are csv and json

(required): The document ID to explain

(optional): The name of the index to get detailed information for. If provided, returns detailed information about this specific index instead of listing all indices.

(optional): Limit the information returned to the specified metrics. Options include: \all, blocks, metadata, nodes, routingtable, routingnodes, masternode, version

Compares percentile distributions (P50, P90) of all numeric fields between a baseline and a selection time range, then returns the top fields ranked by change score. Useful for identifying which numeric metrics shifted most during an anomaly window.

(optional): A comma-separated list of metrics to display. Available metrics include: id, name, ip, port, role, master, heap.percent, ram.percent, cpu, load1m, load5m, load15m, disk.total, disk.used, disk.avail, disk.usedpercent

(optional): A comma-separated list of node IDs or names to limit the returned information. Supports node filters like \local, \master, master:true, data:false, etc. Defaults to \all.

boolean

string

boolean

integer

string

string

(required): The search query in OpenSearch Query DSL format

Saves facts, decisions, and preferences to persistent storage with automatic semantic enrichment.

Searches memories using natural language with recency-aware ranking.

(optional): The size of SearchIndexTool response. Default is 10, maximum is 100 (configurable). To change the maximum limit, set maxsizelimit via CLI arguments or config file. See Tool Customization for details.