LoginSign Up
← Back to all sparks
N

Neo4j

ANALYTICS
Velocity6.3

neo4j-cli ships explicitly for AI agents — Neo4j makes its 'AX' bet concrete.

graph databaseai agentsaura cloudgraph analyticscypher 25developer experience
◆Current state
Neo4j is shipping in three lanes simultaneously: developer/agent surface (the new neo4j-cli covering Aura management, Cypher, and ops, designed for human, developer and agent consumption), Aura cloud capacity and ops (2TB high-memory GCP instances, inactive-member pruning, tighter password policy), and graph analytics maturation (project-level ML model persistence in AGA, Lakehouse export from Microsoft Fabric, Cypher 25 GQL features). Dashboards and Explore are gaining interactivity in parallel.
◆Where it's heading
The arc is toward treating AI agents as a first-class user of the platform, not an integration consumer. Calling out 'AX' alongside DX/UX in the CLI announcement is unusual — most database vendors are still adding MCP servers or chat assistants. Coupled with the GenAI token functions in the April Aura release and AGA's model persistence, Neo4j is consolidating the 'graph as memory substrate for AI agents' position it's been telegraphing for two years.
◆Prediction
Likely next: an MCP server fronting the same surface as neo4j-cli, deeper GenAI-native primitives in Cypher 25 (vector ops, embeddings as first-class types), and continued Aura capacity climbs to support larger graph-RAG workloads. Microsoft Fabric integration will probably extend further given the bidirectional Lakehouse work.

◆Recent moves

  1. 6d ago

    neo4j-cli has arrived!

    ⚡ SPARK

    neo4j-cli launches as the first step toward a unified CLI, covering Aura management, Cypher queries against any Neo4j instance, and explicitly designed for developers, humans, and AI agents (AX). The framing treats agent users as a first-class audience — unusual for database tooling.

    View source ↗
  2. 8d ago

    🚀 High Memory 2TB Instances now available for AuraDB on GCP

    AuraDB Business Critical and VDC on GCP can now provision up to ~2TB RAM and 5TB storage, with expanded memory-to-storage ratios. Removes a ceiling for larger graph workloads on GCP, matching capacity options previously available on other clouds.

  3. 15d ago

    Tidy Up Your Org with Automated User Pruning 🧹

    Aura Organizations can now auto-prune inactive members after a configurable 30–365 day window, with up to three warning emails. A standard admin-hygiene capability for enterprise account management; activity tracked from Console or Aura API actions.

  4. 20d ago

    Project-level Machine Learning Model Persistence in Aura Graph Analytics

    Trained ML models in Aura Graph Analytics now persist in a project-level Model Catalog across sessions, not just within a single Graph Data Science session. Removes a real production blocker — previously, model lifecycle was tied to ephemeral compute.

    View source ↗
  5. 27d ago

    Aura Console User Password Requirements

    Aura Console minimum password length goes to 16 characters for new users and password resets, aligning with NIST guidance. Standard credential-policy update; existing users unaffected until they rotate.

  6. 28d ago

    Dashboard actions now available

    Dashboard Actions ship to all Aura tiers, enabling cell-driven filtering, parameter-selection checklists, and drilldowns. Moves the Dashboards tool from static views toward interactive applications — a meaningful step for analyst workflows.

    View source ↗