Skip to main content
POST
/
memory-stores
/
{store_id}
/
memories
/
search
from hx import Client

client = Client()

memories = client.memory.search(
    store_id="ms-your-store-id",
    query="What is my name?",
    user_id="user_123",
    top_k=10
)

{
  "results": [
    {
      "id": "mem_abc123",
      "memory": "User's name is Alex",
      "score": 0.95,
      "user_id": "user_123",
      "metadata": {"type": "identity"},
      "created_at": "2025-01-04T00:00:00Z"
    }
  ],
  "count": 1,
  "query": "What is my name?"
}
Search memories using semantic similarity.
​
store_id
string
required
Memory Store ID
​
query
string
required
Search query text
​
user_id
string
Filter by user ID
​
agent_id
string
Filter by agent ID
​
run_id
string
Filter by run/session ID
​
filters
object
Additional metadata filters
​
top_k
integer
default:10
Number of results to return (1-100)
from hx import Client

client = Client()

memories = client.memory.search(
    store_id="ms-your-store-id",
    query="What is my name?",
    user_id="user_123",
    top_k=10
)

{
  "results": [
    {
      "id": "mem_abc123",
      "memory": "User's name is Alex",
      "score": 0.95,
      "user_id": "user_123",
      "metadata": {"type": "identity"},
      "created_at": "2025-01-04T00:00:00Z"
    }
  ],
  "count": 1,
  "query": "What is my name?"
}