Skip to main content

Overview

Summary Memory generates and maintains an evolving summary of key conversation points. It works both alongside conversation memory and independently.

Save vs Load

FlagPurpose
summary_memorySave: Generate and persist session summaries
load_summary_memoryLoad: Inject summary into subsequent runs (defaults to summary_memory)

Standalone Usage

Summary memory works without full session memory. The agent recalls context through generated summaries instead of raw message history:

Combined with Conversation Memory

Use both for detailed context + cost-efficient summaries:

Save History, Load Summary Only

Save full history for auditing but only inject the summary to reduce token usage:

How It Works

  1. After each completed run, the session summary is updated by a sub-agent
  2. Summary includes key points, user preferences, and topics discussed
  3. Summary is injected as context for subsequent interactions (when load_summary_memory is enabled)
  4. Works independently of full_session_memory — can be the sole source of recall

Parameters

ParameterTypeDefaultDescription
summary_memoryboolFalseSave and generate summaries
load_summary_memorybool | NoneNoneInject summary into runs (defaults to summary_memory)
session_idstrauto-generatedSession identifier
modelstr | Model(required)Model for generating summaries