mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00

Files

T

Dmytro Struk 57d09afe04 Python: Context providers abstraction and Mem0 implementation (#631 )

* Added context provider abstractions

* Added mem0 implementation

* Example and small fixes

* Added unit tests for agent

* Added unit tests for mem0 provider

* Updated README

* Small doc updates

* Update python/packages/mem0/agent_framework_mem0/_provider.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Small fixes in tests

* Renaming based on PR feedback

* Small fixes

* Added tests for AggregateContextProvider

* Small improvements

* More improvements based on PR feedback

* Small constant update

* Added more examples

* Added README for Mem0 examples

* Small updates to API

* Updated initialization logic

* Updates for context manager

* Updated Context class

* Dependency update

* Revert changes

* Fixed tests

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>

57d09afe04 · 2025-09-10 21:11:42 +00:00

History

mem0_basic.py

Python: Context providers abstraction and Mem0 implementation (#631 )

2025-09-10 21:11:42 +00:00

mem0_threads.py

Python: Context providers abstraction and Mem0 implementation (#631 )

2025-09-10 21:11:42 +00:00

README.md

Python: Context providers abstraction and Mem0 implementation (#631 )

2025-09-10 21:11:42 +00:00

README.md

Mem0 Context Provider Examples

Mem0 is a self-improving memory layer for Large Language Models that enables applications to have long-term memory capabilities. The Agent Framework's Mem0 context provider integrates with Mem0's API to provide persistent memory across conversation sessions.

This folder contains examples demonstrating how to use the Mem0 context provider with the Agent Framework for persistent memory and context management across conversations.

Examples

File	Description
`mem0_basic.py`	Basic example of using Mem0 context provider to store and retrieve user preferences across different conversation threads.
`mem0_threads.py`	Advanced example demonstrating different thread scoping strategies with Mem0. Covers global thread scope (memories shared across all operations), per-operation thread scope (memories isolated per thread), and multiple agents with different memory configurations for personal vs. work contexts.

Prerequisites

Required Resources

Mem0 API Key - Sign up for a Mem0 account and get your API key
Azure AI Foundry project endpoint (used in these examples)
Azure CLI authentication (run az login)

Configuration

Environment Variables

Set the following environment variables:

For Mem0:

MEM0_API_KEY: Your Mem0 API key (alternatively, pass it as api_key parameter to Mem0Provider)

For Azure AI Foundry:

FOUNDRY_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
FOUNDRY_MODEL_DEPLOYMENT_NAME: The name of your model deployment

Key Concepts

Memory Scoping

The Mem0 context provider supports different scoping strategies:

Global Scope (scope_to_per_operation_thread_id=False): Memories are shared across all conversation threads
Thread Scope (scope_to_per_operation_thread_id=True): Memories are isolated per conversation thread

Memory Association

Mem0 records can be associated with different identifiers:

user_id: Associate memories with a specific user
agent_id: Associate memories with a specific agent
thread_id: Associate memories with a specific conversation thread
application_id: Associate memories with an application context