Agent Memory
Memory layers and knowledge-graph stores that let agents remember users, projects and past runs across sessions instead of starting from a blank context every time.
-
Letta
Framework for building stateful agents with long-term memory that learn and self-improve over time.
-
Mem0
Memory layer for AI agents and apps that stores and retrieves user context across sessions.
-
Zep
Context engineering platform that builds a temporal knowledge graph from conversations and business data for agent memory.
-
Cognee
Open-source knowledge-graph memory engine that turns your data into persistent, queryable agent memory.
-
Supermemory
Memory and context API for AI apps and coding agents, with a personal knowledge base on top.