Memori

Memori's BYODB edition is a memory library for developers who want agents to retain context in their own SQLite file or self-managed database. It generates embeddings locally, but its default Advanced Augmentation sends conversation messages and summaries to Memori's cloud API for memory extraction. The documented OpenAI connection also sends model requests to OpenAI.

Memory persists across sessions. The library wraps an application's LLM client, captures messages and responses, and stores conversation data in the selected database. Augmentation extracts facts, preferences and relationships between entities. Recall selects relevant context for later model requests instead of carrying the entire conversation history into every prompt.

Python and TypeScript SDKs support database-backed applications. Storage options include PostgreSQL, MySQL and MongoDB alongside SQLite. A local SQLite file provides storage without a separate database server.

Memori Cloud is the separate hosted storage and search service. BYODB keeps stored memories in the database you choose while using the default remote augmentation service; self-managed storage does not make all processing local.