EVevermind-ai
memory

Add Memory

Changed on

Add messages into the user-memory + agent-memory pipelines.

post/api/v1/memory/add

Request

  • The document declares no server URL.
  • Auth
    none declared

Request body

session_idstring required
app_idstring
project_idstring
defer_extractionboolean

Persist messages in the durable unprocessed buffer without running boundary detection or extraction. A later /flush commits the batch.

async_modeboolean

Persist the batch to the memorize queue and return 202 at once instead of running boundary detection and extraction inline. Poll GET /tasks/{request_id}. A session that already has queued batches is queued even when this is false, so batches never run out of order.

Response

Successful Response

OR

Changes

  • 6beb324a48ddRevision changes
    • breaking

      the response's body type changed from object to no type for status

    • breaking

      removed the required property from the response with the status

    • breaking

      removed the required property from the response with the status

    • info

      added the new optional request property

    • info

      added to the response body anyOf list for the response status

    • info

      added the non-success response with the status

    • info

      added the non-success response with the status

    • info

      added the success response with the status

  • 9a2e78d664d6Revision changes
    • info

      added the new optional request property