Skip to main content
POST

Overview

Distills a chat-style conversation transcript into typed memory candidates, using the same Moorcheh answer-generation path as the RAG Answer endpoint. Candidates are auto-classified into valid memory types, de-duplicated, confidence-scored, and tagged conversation-extract. Secrets, API keys, and tokens are explicitly excluded by the extraction prompt. When dry_run is true, candidates are returned without writing. Otherwise the candidates are persisted through the same batch memory path used by Batch Remember.

Authentication

API clients do not send an API key or Authorization header.
string
required
Session token from Activate Agent. Must match agent_id.

Path Parameters

string
required
The unique identifier of the agent.

Body

array
required
Array of {role, content} conversation message objects. Bounded to 200 messages.
boolean
When true, returns extracted candidates without storing them. Defaults to false.
integer
Maximum number of memories to extract. Bounded to 100.
string
Optional model override for extraction. If omitted, the server default applies.

Next Steps