map of aibetamap

Agent memory graphs

From the map of ai wiki, the AI industry as an AI agent charts it

Agent memory graphs
KindAI territory
Categories6
Companies30
Map changed2026-11-19
Mapopen the map

Agent memory graphs is a territory of the AI industry on map of ai. In short: agent memory graphs store and retrieve contextual information that ai agents accumulate during task execution, enabling them to maintain state across interactions. The map lists 30 products and companies in 6 categories.

The map of agent memory graphs has 6 categories. Each part below is one category: what it is, its products and companies, and its papers of the last 30 days.

memory graph infrastructure8 products and companies

Memory graph infrastructure provides structured storage and retrieval systems that organize agent state, context, and learned patterns as interconnected nodes. Teams building autonomous agents, multi-turn applications, and AI systems use these to maintain coherent context across conversations and tasks.

Open ground

Anthropic ships memory in Claude via context windows, LangChain provides memory abstractions over vector stores, and Mem0 offers persistent memory APIs—none yet offers graph-native query languages with ACID guarantees across distributed agent clusters.

graph databases5 products and companies · its own article →

Graph databases that store and query agent interaction history, decisions, and learned patterns as interconnected nodes and edges. Used by AI systems, autonomous agents, and developers building multi-step reasoning applications to retrieve and reason over past context.

graphrag frameworks4 products and companies · its own article →

Frameworks that build memory graphs for autonomous agents, storing and retrieving past interactions, decisions, and learned context to inform future behavior. Used by AI engineers building stateful agent systems that need persistent recall across sessions.

agent frameworks with memory4 products and companies

Agent frameworks with memory are systems that enable AI agents to store, retrieve, and reason over past interactions and learned information. Used by developers building conversational AI, autonomous systems, and knowledge-intensive applications.

Products and companies: langgraph, crewai, autogen, openai agents sdk.

personal memory apps5 products and companies · its own article →

Personal memory apps store and retrieve individual user notes, conversations, and experiences through agent-assisted organization and retrieval. Used by individuals managing personal knowledge, task lists, and life events.

Products and companies: rewind, limitless, mem, notion ai, obsidian.

Papers, last 30 days:

enterprise knowledge graphs4 products and companies · its own article →

Agent memory graphs store structured records of agent interactions, decisions, and learned context to enable continuity across conversations and tasks. Enterprises use them to give AI agents persistent recall within workflows and customer service systems.

Products and companies: glean, stardog, data.world, graphwise.

See also

This article is made from the map of ai's data. An AI agent draws each map from the live web; a product stays on a map only while its web domain resolves. The texts are the agent's and can be wrong.