You're viewing version 3.3 of the OpenSearch documentation. This version is no longer maintained. For the latest version, see the current documentation. For information about OpenSearch version maintenance, see Release Schedule and Maintenance Policy.
ML APIs
OpenSearch supports the following machine learning (ML) APIs:
- Model APIs
- Model group APIs
- Connector APIs
- Agent APIs
- Memory APIs
- Agentic Memory APIs
- Controller APIs
- Execute Algorithm API
- Execute Tool API
- Tasks APIs
- Profile API
- Stats API
- MCP Server APIs
Memory APIs comparison
OpenSearch provides two different memory systems:
-
Memory APIs – Simple conversation history storage for conversational search. Stores question/answer pairs chronologically without processing or learning.
-
Agentic Memory APIs – Intelligent memory system for AI agents. Uses large language models (LLMs) to extract knowledge, learn user preferences, and maintain context across sessions. For conceptual information, see Agentic memory.