For developers building AI agents that need persistent memory, Neo4j Agent Memory is a graph-native memory layer, built by Neo4j, that stores conversations, entities, and reasoning together in one graph.
Presence & Market Position
Tracked · below panel floor — earned mentions are accruing toward the next scored window.
Measures earned, engagement-weighted share of voice across the GTM voices panel. Methodology →
Neo4j Agent Memory is built as a graph-native memory layer for AI agents: conversations, extracted entities, and an agent's own reasoning persist together in one graph rather than split across separate memory and vector stores, with the aim of giving multi-agent systems a shared, queryable record instead of per-agent context that drifts apart. It ships as a Neo4j Labs project, distinct from the core database product, aimed at developers building agent frameworks directly. Public conversation specific to this project is still early, consistent with a labs-stage release aimed at a developer audience rather than a broad practitioner one.
Redis Agent Memory
Twilio Segment
Vercel
ElevenLabs
LangChainNo customer list on file yet. Claim this profile to add customers and case studies.
Business Profile
Neo4j Agent Memory is a product of Neo4j, the graph-database company founded in 2007, now at roughly 982 employees with $631.1M in total funding and reported ARR north of $200M. Rather than a separately funded spinout, it ships as an open-source Neo4j Labs project: Python and TypeScript SDKs, an MCP server, and a CLI, maintained alongside Neo4j's core commercial database rather than sold as its own product line. Its current state is early and community-supported, positioned as R&D on top of an established, well-capitalized parent rather than a standalone business with its own trajectory yet.
Employees & founded inherited from Neo4j (parent).
Agent Readiness
Measures how easily your agents can build on it — API, MCP, CLI, SDK, docs depth. Methodology →
Neo4j Agent Memory is itself the agent-readiness surface: an MCP server exposing a full tool set for AI assistants, matched by Python and TypeScript SDKs, a documented API, and a CLI for deployment. It integrates with common agent frameworks and offers both a self-hosted path and a hosted memory service, letting an agent's conversations, entities, and reasoning persist in one graph across sessions. The project carries an experimental, community-supported designation rather than a fully GA one.
IS THIS YOUR BRAND?
Claim this profile
Fact-check your data, add context, and earn the verified badge — free, takes minutes, work email required.
Claim Neo4j Agent Memory →