Give your agents a memory that actually remembers.
The Neo4j Agent Memory Service is a hosted, graph-native memory layer for LLM agents - short-term conversations, long-term knowledge, and full reasoning traces - backed by Neo4j Aura with native vector search.
4 memory types
12 MCP tools
1 managed service
0 infrastructure to run
Everything your agent needs to remember
A complete memory layer - structured, searchable, and production-ready out of the box.
Four Memory Types
Short-term conversations, long-term knowledge graph, reasoning traces, and synthesized observations - all in one place.
Graph-Native by Design
Typed entities, typed relationships, entity merging, and cross-conversation history. Traversable, queryable, explainable.
Semantic Search Built In
HNSW vector indexes on messages, entities, observations and reflections. Hybrid vector + text with automatic fallback.
MCP-Ready
12 memory tools exposed over an SSE-based MCP server - plug straight into Claude, Cursor, or any MCP-compatible agent.
Fully Multi-Tenant
Per-workspace isolated databases on Neo4j Aura, provisioned on demand. Bring-your-own Neo4j also supported.
Production Auth & Metering
API keys, Auth0 SSO, scoped JWTs, rate limiting, real-time usage counters - ready for real workloads.
How it works
Three steps from zero memory to a fully-remembering agent.
STEP 01
Connect
Point your agent at the NAMS MCP endpoint or REST API using your workspace API key.
STEP 02
Remember
Messages, entities, and tool calls are captured, extracted, and embedded automatically.
STEP 03
Recall
Query the graph, search semantically, or ask for the three-tier context for any conversation.
Stop rebuilding memory from scratch.
NAMS handles extraction, embedding, compression, and retrieval - you keep building the agent.
Sign In to your Workspace