User facts, task history, graph entities, and workflow state should be evaluated differently.
Open memory systems by recall model
Browse memory systems by what they store, how recall works, who controls the memory, and where the data can run.
Good memory retrieves the right context, explains why, and corrects stale information.
Memory needs scoping, deletion, export, and deployment choices because it stores sensitive context.
User and product memory
Memory layers for personalization, preferences, assistant continuity, and product-level recall.
ragflow
Open-source Retrieval-Augmented Generation engine that combines deep document understanding with agent capabilities.
CowAgent
Open-source AI assistant with multi-model support, task planning, tool execution, and persistent memory.
haystack
Open-source AI orchestration framework for building production-ready LLM applications with modular pipelines and RAG.
AgentMemory
Persistent memory for AI coding agents, with benchmarks and local-first workflows.
OpenLore
Persistent architectural memory for AI coding agents using queryable codebase knowledge graphs and MCP tools.
Mnemo Cortex
Open-source memory coprocessor for AI agents with persistent recall, semantic search, and crash-safe capture.
Cognee
Open-source memory and data infrastructure for AI applications that need reliable context.
Graphiti
Temporal knowledge graph memory system for agents that need facts, entities, and time-aware context.
Letta
Platform for stateful agents with advanced memory, personalization, and learning over time.
Mem0
Open-source memory layer for AI agents and assistants that need personalized recall.
Memori
Open-source memory engine for LLM apps and agents that need persistent context injection.
Graph and knowledge memory
Systems that use graphs, RAG, retrieval, or knowledge structures to recall durable context.
ragflow
Open-source Retrieval-Augmented Generation engine that combines deep document understanding with agent capabilities.
haystack
Open-source AI orchestration framework for building production-ready LLM applications with modular pipelines and RAG.
OpenLore
Persistent architectural memory for AI coding agents using queryable codebase knowledge graphs and MCP tools.
Mnemo Cortex
Open-source memory coprocessor for AI agents with persistent recall, semantic search, and crash-safe capture.
Cognee
Open-source memory and data infrastructure for AI applications that need reliable context.
Graphiti
Temporal knowledge graph memory system for agents that need facts, entities, and time-aware context.
Mem0
Open-source memory layer for AI agents and assistants that need personalized recall.
Memori
Open-source memory engine for LLM apps and agents that need persistent context injection.
Agent state and workflow memory
Memory used to preserve agent state, decisions, tool history, and long-running workflow context.
OpenLore
Persistent architectural memory for AI coding agents using queryable codebase knowledge graphs and MCP tools.
Mnemo Cortex
Open-source memory coprocessor for AI agents with persistent recall, semantic search, and crash-safe capture.
Cognee
Open-source memory and data infrastructure for AI applications that need reliable context.
Graphiti
Temporal knowledge graph memory system for agents that need facts, entities, and time-aware context.
Letta
Platform for stateful agents with advanced memory, personalization, and learning over time.
Mem0
Open-source memory layer for AI agents and assistants that need personalized recall.
Memori
Open-source memory engine for LLM apps and agents that need persistent context injection.
Self-hosted memory infrastructure
Memory systems that can run closer to your data with APIs, local control, or self-hosted deployment.
Cognee
Open-source memory and data infrastructure for AI applications that need reliable context.
Graphiti
Temporal knowledge graph memory system for agents that need facts, entities, and time-aware context.
Letta
Platform for stateful agents with advanced memory, personalization, and learning over time.
Mem0
Open-source memory layer for AI agents and assistants that need personalized recall.
Memori
Open-source memory engine for LLM apps and agents that need persistent context injection.