Neo4j introduces in-memory database to support agentic AI systems

Graph database company Neo4j has introduced Relate, an open-source, in-memory database for AI agents and agentic systems. The announcement was made on November 12.

Written in Rust, Relate operates in-process, meaning it runs within an application rather than as a separate database server. It is released under the Apache 2.0 open-source licence.

The database uses the Cypher query language and includes a Model Context Protocol (MCP) server and a command-line interface. AI coding agents can use it to create databases during application development.

Data is stored in memory by default, with an option to save it to disk for longer-term storage.

A June 2026 Gartner report, Forecast Analysis: Agentic AI in DBMS, Worldwide, estimates that machine users will account for 75% of database management system workloads by 2029, compared with 10% in 2025. It also projects that AI agents could generate 10 to 100 times more interactions than human users.

Sudhir Hasbe, President of Technology and Chief Product Officer at Neo4j, said Relate is “designed to run in-process for agent sandboxes and agent memory as well as on mobile or edge devices.”

Agentic AIDigital Database
Comments (0)
Add Comment