Description

This PR adds a working example demonstrating persistent memory for AI agents using Mem0 with AWS ElastiCache for Valkey and Amazon Neptune Analytics. This is the actual code featured in our joint AWS-Mem0 blog post, providing a complete implementation of dual memory storage (vector + graph) with significant performance improvements.

The example shows how to build a GitHub repository research agent that stores information in both ElastiCache (vector similarity search) and Neptune Analytics (graph relationships), demonstrating 97%+ token reduction with memory retrieval.

Blog Post References:

• AWS: https://aws.amazon.com/blogs/database/build-persistent-memory-for-agentic-ai-applications-with-mem0-open-source-amazon-elasticache-for-valkey-and-amazon-neptune-analytics/
• Mem0: https://mem0.ai/blog/build-persistent-memory-for-agentic-ai-applications-with-mem0-open-source-amazon-elasticache-for-valkey-and-amazon-neptune-analytics

Type of change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Refactor (does not change functionality, e.g. code style improvements, linting)
• Documentation update

How Has This Been Tested?

• Test Script (Streamlit application with interactive testing)
• Validated all blog post example queries
• Confirmed memory performance improvements (330K→7K tokens, 8.9s→3.8s)
• Tested dual memory storage and retrieval functionality

Checklist:

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works (Not applicable since this is example)
• New and existing unit tests pass locally with my changes
• Any dependent changes have been merged and published in downstream modules
• I have checked my code and corrected any misspellings