Table of Contents

Namespace LMKit.Agents

Classes

AgentMemory

Provides persistent memory storage and retrieval capabilities for conversational agents.

The AgentMemory class uses a retrieval-augmented generation (RAG) engine to store text-based information in partitions and later recall the most relevant ones based on incoming messages. This mechanism enhances multi-turn conversations by integrating additional context or previously stored information.

Enums

MemoryType

Enumerates the different types of memory within the AgentMemory system.