AgentMemory is a persistent knowledge store and memory server designed to provide AI coding agents with long-term memory. It functions as a knowledge graph engine and vector database store that saves and recalls project context, architectural decisions, and patterns across different sessions.
The system distinguishes itself by using a tiered-memory consolidation pipeline that compresses raw observations into episodic, semantic, and procedural layers to optimize token usage. It employs a hybrid retrieval strategy combining keyword matching, vector embeddings, and graph traversal to surface relevant historical context.
The project covers a broad range of capabilities including automated project observation via lifecycle hooks, multi-agent coordination through shared synchronized memory pools, and local-first vector storage for data privacy. It also provides an interface for the Model Context Protocol to expose memory tools to compatible agents.
The system includes a command-line interface for server runtime management and environment bootstrapping.