This Week in Neo4j: Road to NODES, MCP, GraphRAG, BandtoBand and more

Alexander Erdl

Senior Developer Marketing Manager

Dattaraj Rao

Welcome to This Week in Neo4j, your fix for news from the world of graph databases!

This edition invites you to sharpen your graph skills in our hands-on Road to NODES workshops, build GraphRAG locally, explore everyday AI with Neo4j MCP and discover the ultimate rock band knowledge graph.

Join our Neo4j User Research panel! Sign up to share your experiences with a researcher and influence the future of Neo4j products.
What’s in it for you? A chance to connect directly with product development teams, get paid compensation, hear about what we are working on, and more!


Happy Graphing,

Alexander Erdl

 

COMING UP!

Dattaraj is the author of “Keras to Kubernetes: The journey of a Machine Learning model to Production” and leads the AI Research Lab at Persistent, where he drives thought leadership in AI/ML across the company.

Connect with him on LinkedIn.

Together with Sadashiv Borkar, Dattaraj is a Featured NODES 2025 Speaker. Their session is “Agentic AI for Enterprise Knowledge Graph Management”, where they will talk about the intersection of agentic artificial intelligence (AI) and enterprise knowledge graphs. This enables enterprises to transform complex business processes into intelligence guided by a standard business Ontology.


Dattaraj Rao

 

Road to NODES: Hands-On Workshops


We have scheduled our hands-on workshops ahead of NODES for this year! Whether you’re new to graph databases or building GenAI apps that actually understand context, our workshop series has something for you. From Neo4j Fundamentals to advanced GraphRAG, agentic AI and persistent memory, you’ll get hands-on with the graph-powered tools behind the next generation of intelligent apps.

 

MCP: Neo4j MCP Server: Your ADHD-Friendly House-Moving Assistant


In this post, Irina Loghin demonstrates how Neo4j’s Model Context Protocol (MCP) transforms everyday chaos – like moving houses – into a structured, actionable graph. The MCP server takes natural language prompts and builds a graph (tasks, sub‑tasks, dependencies), complete with energy and time estimates and ADHD‑friendly insights, helping you manage life’s complexity with clarity.

 

GRAPHRAG: Building GraphRAG Locally


Ananyyaaa walks through creating an entirely local GraphRAG pipeline – using Neo4j as a graph and vector store, Hugging Face embeddings, LangChain and Ollama with Mistral. This setup demonstrates how to chunk text, embed it, index it in the graph, retrieve relevant passages and generate answers from a CPU‑only environment. Experiment with GraphRAG on your machine — ideal for offline or privacy‑conscious workflows.

 

BandtoBand: Rock ‘N Roll Family Tree


kevin2 shared his cool project BandToBand.com in the Community Forum! It is treating bands as nodes connected when they share members—creating a massive, interconnected “family tree” where every band in the dataset is reachable from every other by shared membership paths. You can explore and analyse over 34,000 bands, 84,000 artists and 76,000 albums.

 

 

POST OF THE WEEK:
Sharmistha Chatterjee



Please share it if you like it!