Stores new memory records from a list of messages, optionally inferring structured content; requires association via `agent_id`, `user_id`, `app_id`, or `run_id`.
inferbooleanIf true, infers structured memories from messages; otherwise, stores messages directly.
app_idstringUnique identifier for the application associated with this memory. At least one of agent_id, user_id, app_id, or run_id must be provided.
org_idstringOptional unique identifier for the organization associated with this memory.
run_idstringUnique identifier for the run associated with this memory. At least one of agent_id, user_id, app_id, or run_id must be provided.
user_idstringUnique identifier for the user associated with this memory. At least one of agent_id, user_id, app_id, or run_id must be provided.
agent_idstringUnique identifier for the agent associated with this memory. At least one of agent_id, user_id, app_id, or run_id must be provided.
excludesstringComma-separated keywords to exclude specific topics, aiding in filtering out irrelevant information.
includesstringComma-separated keywords to include specific topics, aiding filtering and prioritization.
messagesRequiredarrayList of message objects forming the memory's content. Each message should have 'role' (e.g., 'user' or 'assistant') and 'content' (text content). Alternative: You can also provide 'records' with 'text' field which will be automatically converted to messages format.
org_namestringThe name of the organization for this memory. Deprecated: use `org_id` instead.
async_modebooleanWhether to process memories asynchronously (default: true). When true, returns event_id/status/message for tracking background processing. When false, processes synchronously and returns id/event/memory fields. Most clients use the default async mode.
project_idstringOptional unique identifier for the project associated with this memory.
dataRequiredData from the action execution
errorstringError if any occurred during the execution of the action
successfulRequiredbooleanWhether or not the action execution was successful or not
API key connection. Risk level 2 of 5.
Free Action
No published Skills explicitly reference this Action yet.