AI agents benefit from persistent memory, enabling them to recall past interactions and maintain context, which enhances customer experience in scenarios like customer service. The Letta Developer Platform allows developers to create stateful agents with advanced context management features. It supports self-hosting within a virtual private cloud and uses Amazon Aurora PostgreSQL for long-term memory storage. Aurora PostgreSQL offers capabilities such as efficient similarity searches with the pgvector extension, sub-second query latency, and dynamic storage scaling. Letta operates as a persistent service, allowing agents to function independently and scale horizontally using Kubernetes. The platform supports multi-tenancy and includes enterprise features for security and monitoring.
To set up an Aurora Serverless cluster for Letta, users must create a database on Amazon RDS, configure security group access, and install the pgvector extension. Letta connects to Aurora using a PostgreSQL connection string. After establishing the connection, users can create agents, send messages, and view agent states and conversation histories stored in Aurora. Letta organizes data in 42 tables, including those for agents, messages, and memory blocks. Users can explore the database schema and examine the structure of stored messages and embeddings. Finally, it is recommended to delete the Aurora cluster and associated resources after completing the integration to avoid charges.