Amazon Neptune Analytics now integrates with Mem0 for graph-native memory in GenAI applications

Today, we’re announcing the integration of Amazon Neptune Analytics with Mem0, an open-source, agentic memory system purpose-built for generative AI (GenAI) applications. With this launch, customers can use Neptune as the graph store for memory retrieval and reasoning, enabling long-term memory for AI agents across richly connected graphs—powering more personalized and context-aware AI experiences.

This integration allows Mem0 users to store and query memory graphs at scale, unlocking advanced use cases where LLMs need to learn from each interaction, becoming more personalized and effective over time. It enables graph-native long-term memory for LLMs by using Neptune as an external memory store, improving response quality through multi-hop graph reasoning, and supporting hybrid retrieval across graph, vector, and keyword modalities.

Mem0 is a self-improving memory layer that powers personalized, cost-efficient GenAI experiences. To learn more about the Neptune–Mem0 integration, visit the User Guide.