Overview

GUMem (General User Memory) is a user memory engine for Agents. It accepts conversation messages and behavior records, extracts reusable Memory, and recalls relevant context in later Agent turns.

The four-layer Memory model

GUMem's public model is easiest to understand by recall depth:

Layer	Role	Example
Topic	A high-level area used to find related memory.	team scheduling
Summary	A long-term compressed memory supported by Facts.	The user prefers Berlin as the default city for Europe team scheduling.
Facts	Traceable facts, preferences, plans, or constraints extracted from Message input.	The user said Europe maps to Berlin and Americas maps to Toronto.
Message	Raw conversation or behavior input.	User messages, searches, filters, saves, or tool results.

Writes usually start from Message, then produce Facts, Summary, and Topic. Recall usually starts from Topic, retrieves the related Summary, and adds supporting Facts when needed.

Core capabilities

Capability	Description
Conversation Message writes	Add user, assistant, or system messages to a Session and send them into the Memory processing pipeline.
Behavior Message writes	Record searches, filters, clicks, saves, tool calls, and business events to capture intent the user did not explicitly type.
Facts and Summary generation	Extract traceable Facts from raw input, then compress them into Summary for long-term recall.
Topic-layered recall	Find relevant Topic first, then recall Summary and supporting Facts in a later Agent turn.
Governance and explainability	Keep source, processing stage, status, and webhook extension points for audit, filtering, and business rules.

Smallest integration path

1. Create a Session and bind it to your business user identifier.
2. Write Message input after conversation or behavior events happen.
3. Call Query Memory before the next Agent response.
4. Put formatted_context or structured Memory into the model context.
5. After the response is generated, write the new user message and assistant reply back to GUMem.

The order matters: recall, generate, then write back. This lets the Agent use Memory settled before the current turn instead of treating its current reply as historical fact.

Documentation entry points

• Quick Start completes the first integration with the Node SDK, Python SDK, or cURL.
• How GUMem Works explains Message, Facts, Summary, and Topic.
• Multimodal Content explains how text, image, and video content enters GUMem.
• Add Memory writes new Message input.
• Query Memory explains how to recall Topic, Summary, Facts, and recent Message context.
• User Case shows how GUMem fits into a typical Agent turn.