Search Archival Memory

Deprecated

get/v1/agents/{agent_id}/archival-memory/search

Search archival memory using semantic (embedding-based) search with optional temporal filtering.

This endpoint allows manual triggering of archival memory searches, enabling users to query an agent's archival memory store directly via the API. The search uses the same functionality as the agent's archival_memory_search tool but is accessible for external API usage.

Path ParametersExpand Collapse

agent_id: string

The ID of the agent in the format 'agent-'

minLength42

maxLength42

Query ParametersExpand Collapse

query: string

String to search for using semantic similarity

end_datetime: optional string

Filter results to passages created before this datetime

formatdate-time

start_datetime: optional string

Filter results to passages created after this datetime

formatdate-time

tag_match_mode: optional "any" or "all"

How to match tags - 'any' to match passages with any of the tags, 'all' to match only passages with all tags

Accepts one of the following:

"any"

"all"

tags: optional array of string

Optional list of tags to filter search results

top_k: optional number

Maximum number of results to return. Uses system default if not specified

ReturnsExpand Collapse

count: number

Total number of results returned

results: array of object { content, timestamp, tags }

List of search results matching the query

content: string

Text content of the archival memory passage

timestamp: string

Timestamp of when the memory was created, formatted in agent's timezone

tags: optional array of string

List of tags associated with this memory

Search Archival Memory

curl https://api.letta.com/v1/agents/$AGENT_ID/archival-memory/search \
    -H "Authorization: Bearer $LETTA_API_KEY" \
    -d '{}'

{
  "count": 0,
  "results": [
    {
      "content": "content",
      "timestamp": "timestamp",
      "tags": [
        "string"
      ]
    }
  ]
}

Returns Examples

{
  "count": 0,
  "results": [
    {
      "content": "content",
      "timestamp": "timestamp",
      "tags": [
        "string"
      ]
    }
  ]
}