AzureAIMemoryMiddleware

Middleware that periodically extracts memories from turns into Azure AI Memory.

This middleware collects messages from the agent's state after each turn and sends them to Azure AI Memory in batches. It supports both user and assistant messages, configurable by the roles parameter. Use the memory store configuration to control which memories are stored and how. To retrieve those memories back into your agent, use the :class:AzureAIMemoryRetrieverTool in your agent.

Example usage:

from langchain.agents import create_agent
from langchain.chat_models import init_chat_model
from langchain_azure_ai.agents.middleware import AzureAIMemoryMiddleware

memory_middleware = AzureAIMemoryMiddleware(
    store_name="my-memory-store",
    scope="my-scope",
    update_every_n_turns=1,
    roles=["user", "assistant"],
    project_endpoint="https://resource.services.ai.azure.com/api/projects/my-project",
    credential=DefaultAzureCredential(),
)
tools = [memory_middleware.get_retriever_tool()]

agent = create_agent(
    model=init_chat_model("azure_ai:gpt-5"),
    tools=tools,
    middleware=[memory_middleware],
)

This class doesn't create the memory store itself, so make sure to create the specified memory store before using the middleware.