Skip to main content
EverMemOS offers a unique feature for handling multi-user team collaboration scenarios, such as Discord groups, Slack channels, or any collaborative platform where multiple participants interact simultaneously.

​
Overview

The Team Collaboration scenario is optimized for environments with two or more participants. In these scenarios, the system doesn’t just treat the conversation as a single stream of text. Instead, it performs Subject-Event Attribution to ensure that every piece of information is mapped to the correct individual.

​
Key Features

  • Multi-User Extraction: As the conversation flows, EverMemOS identifies each speaker and extracts relevant memories for all of them in parallel.
  • Separated Storage: Memories are stored in individual “Episodic Memories” associated with each user’s unique user_id. This prevents “profile contamination” where one user’s preferences might be mistakenly attributed to another.
This scenario is ideal for Discord moderators, team assistants, or any agent operating in a social or professional group setting.

​
Configuration

To enable this scenario, you must set the scene field to group_chat via the Set Conversation Metadata API.
  • Endpoint: POST /api/v1/memories/conversation-meta
  • Key Field: "scene": "group_chat"
For detailed parameter descriptions, please refer to the API Reference.