Query Persistent Agent Memory Triplet Store
query_memory_storeQuery local agent memory to retrieve semantic triples, causal reasoning chains, and MinHash entity clusters, helping you recall past decisions and trace dependencies without modifying stored records.
Instructions
Queries semantic triples, causal reasoning graphs, and MinHash entity clusters from the local agent memory store, distinguishing from 'manage_memory_store' and 'search_codebase' by retrieving episodic reasoning relations rather than modifying memory records or searching repository code.
Parameters:
query: Entity identifier, concept keyword, or natural language query to look up in the persistent semantic memory graph.query_mode: Query strategy: 'semantic' for knowledge triple and relation lookup; 'causal_chain' for temporal cause-and-effect traces; 'minhash' for sub-microsecond entity similarity clustering.project_root: Workspace root directory where the local memory store JSON file is located (defaults to current directory).
Behavior:
Mutability: Strictly read-only; queries persistent memory store without altering stored knowledge, weights, or timestamps.
Idempotency: Deterministic; returns consistent knowledge relations for identical queries on the same memory state.
Privacy & Network: 100% offline local graph and MinHash index lookup; zero cloud synchronization or network traffic.
Performance & Resources: Query latency <10ms for 10,000 triples using <25MB RAM; thread-safe.
Auth: Zero authentication, API keys, or cloud credentials required.
Return Structure: Emits Markdown report with extracted semantic triples, knowledge relationships, or causal inference chains.
Error Handling: Returns clean empty graph notice if the queried entity does not exist in the codebook without raising exceptions.
Usage Guidelines:
When to use: Recall past agent decisions, query knowledge graph entity relations, or trace causal dependency chains across reasoning sessions.
When NOT to use: Do not use for storing, consolidating, or deleting memory stores (use 'manage_memory_store' instead); do not use for searching source code in the repository (use 'search_codebase' instead).
Returns: Markdown report with extracted semantic triples, graph relationships, or causal inference chains.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"query": "<query>"
},
"name": "query_memory_store"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Entity name, concept, or search query to look up in the memory store. | |
| query_mode | No | Query strategy: 'semantic' for triple & relation lookup, 'causal_chain' for temporal cause-and-effect traces, 'minhash' for sub-microsecond entity similarity clusters. | semantic |
| project_root | No | Workspace root where memory store is located (default: current directory). | . |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |