Documentation

Welcome to the Memory Service documentation. This guide will help you integrate persistent memory into your AI agents.

What is Memory Service?

Memory Service is a backend service designed to solve the persistent memory problems for AI agents systems. It stores all messages exchanged between agents, users, and LLMs in a structured, queryable format.

Key Capabilities

Persistent conversation storage - All messages are stored with full context and metadata
Resumable response streams - Long lived response streams can survive client reconnects or user device swtiching
Conversation replay/audit - Reconstruct converstation history and agent memory state as it was at any point in time
Conversation forking - Fork a conversation at any message to explore alternative paths
Access control - User-based ownership and sharing with fine-grained permissions
Multi-database support - Works with PostgreSQL and MongoDB
Semantic Search - Search across all conversations using vector similarity
Encrypted - All database data is encrypted for enhanced security

Architecture Overview

Memory Service is packaged as container image and provides both REST and gRPC APIs. It’s designed to be:

Backend Service - Designed to be used as an internal service used by your AI agent systems
Lightweight - Minimal overhead for your agent infrastructure
Flexible - Works with your existing database and vector stores
Secure - Provides access control and fine-grained permissions
Stateless - No state is stored in the service itself, making it easy to scale horizontally