Add mem0 Memory Implementation

[alpha-xone]

Why are these changes needed?

These changes are needed to expand AutoGen's memory capabilities with a robust, production-ready integration with Mem0.ai.

This PR adds a new memory component for AutoGen that integrates with Mem0.ai, providing a robust memory solution that supports both cloud and local backends. The Mem0Memory class enables agents to store and retrieve information persistently across conversation sessions.

Key Features

• Seamless integration with Mem0.ai memory system
• Support for both cloud-based and local storage backends
• Robust error handling with detailed logging
• Full implementation of AutoGen's Memory interface
• Context updating for enhanced agent conversations
• Configurable search parameters for memory retrieval

Related issue number

Checks

• I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[gitguardian]

️✅ There are no secrets present in this pull request anymore.

If these secrets were true positive and are still valid, we highly recommend you to revoke them.
While these secrets were previously flagged, we no longer have a reference to the
specific commits where they were detected. Once a secret has been leaked into a git
repository, you should consider it compromised, even if it was deleted immediately.
Find here more information about risks.

---

^{_{🦉 GitGuardian detects secrets in your source code to help developers and security teams secure the modern development process. You are seeing this because you or someone else with access to this repository has authorized GitGuardian to scan your pull request.}}

[alpha-xone]

@microsoft-github-policy-service agree

[ekzhu]

Thanks for the PR! Could you add unit tests so we can ensure the correctness of the features?

[codecov]

Codecov Report

Attention: Patch coverage is 0% with 133 lines in your changes missing coverage. Please review.

Project coverage is 78.63%. Comparing base (177211b) to head (b360f78).
Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
...ackages/autogen-ext/src/autogen_ext/memory/mem0.py	0.00%	133 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #6510      +/-   ##
==========================================
- Coverage   79.29%   78.63%   -0.67%     
==========================================
  Files         225      226       +1     
  Lines       16679    16812     +133     
==========================================
- Hits        13226    13220       -6     
- Misses       3453     3592     +139     

Flag	Coverage Δ
unittests	78.63% <0.00%> (-0.67%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[alpha-xone]

Thanks for replying 🚀

Unit test added: https://github.com/alpha-xone/autogen/actions/runs/14992498495
This is tested with my mem0 api key. If the test is from the main branch, it requires another key to test.

[ekzhu]

Thanks for adding the tests. Can we use the open source verison of mem0? I think it can run entirely locally.

[alpha-xone]

Yes we can. I'm running it locally with the combination of neo4j for graph storage + chromadb for vector db + SQLite for historical db. All we need to do is setup the local environment and pass a dict of configurations of these in. But for unit testing, I'm not sure how to make these environments ready to test.

[ekzhu]

For SQLite and Chroma DB, I think you can instantiate directly as test fixture, right? See example on ChromaDBVectorMemory tests: https://github.com/microsoft/autogen/blob/78ef148c88beb29a7e7602aa39a772b0ffbc50d5/python/packages/autogen-ext/tests/memory/test_chroma_memory.py

For Neo4j, there should be github actions that can set this up in CI. For local integration test, we can skip it if no neo4j server is running.

Besides all these above, I thought mem0's can run independently as in-memory python code? That's my impression reading their documentation. https://docs.mem0.ai/open-source/python-quickstart#basic

[alpha-xone]

The neo4j container cannot initiated on the server:
https://github.com/alpha-xone/autogen/actions/runs/15066738718

  Error: Failed to initialize container neo4j:5.19
Error: One or more containers failed to start.

I can only test locally with the same config in the test_mem0.py file - it's working on my side.