Neo4j

Kemi had a graph of The Odyssey sitting in #Neo4j Aura: characters, songs, places, and actors, all connected by relationships written as specific verbs. She loves a good data visualization, so she explored it two ways: first as a force-directed layout, then as an interactive hive plot. In this video, Kemi chats through how force-directed layouts handle rich graphs, and how hive plots give you a different view, one axis per label. Her blog walks through the four data modelling decisions she made before writing any d3.js: → Simplifying labels during export → Using specific relationship verbs → Storing directionality → Modeling the voyage as a chain of hops, not numbered stops Every piece of interactivity traces back to one of those four. More details: https://bit.ly/4rj0NgP

Did you miss William Lyon's webinar on context graphs? Check out how #contextgraphs unify short-term messages, long-term entities, and reasoning traces in one queryable structure, and how successful execution patterns get distilled into reusable skills new agents can use from day one. Don't miss it! https://bit.ly/46qfKnM #AIagents

We are getting ready for #GraphSummit London, our last GraphSummit of this incredible 2026! We are super happy to announce part of the agenda with Russell Adams, from Capgemini, Nicolas Guinard from SIA Partners, Hussein Jouni from L'Oréal, and Rupert Walter from KPMG. These experts will join Emil Eifrem, Ivan Zoratti, Stephen Chin, Jesús Barrasa, and other #Neo4j experts to discuss how a knowledge layer gives enterprise AI the context, memory, and reasoning it needs to move from pilot to trustworthy production. There's still time to register, don't miss it! https://bit.ly/4cFTud2 #GenAI #agentic #knowledgelayer #enterpriseAI

A valid doubt: Graphs, knowledge graphs, & context graphs: Which one do you need? Graphs answers: What is connected? #Knowledgegraph: What do the connections mean? #Contextgraph: What matters right now? Nathan Barney goes deep into all these and explains the differences between them. Save and share! https://bit.ly/3Ttr8MF

Wrote up my quick experiment using TypeSafe AI #Jev for Neo4j knowledge graph navigation. Works quite well, and the API is easy to use and fast. Great job kicking off this wave of excitement and enthusiasm for decision models, that can go into the hotter loops of your code. https://lnkd.in/eAYbQU2W

GraphSummit NYC is in the books, and what a room it was 🚀 Emil Eifrem opened with the knowledge layer for trustworthy AI. Sudhir Hasbe walked through where the Neo4j Graph Intelligence Platform is headed next. And in between: a new financial crime intelligence offering with GraphAware, a fireside chat with Dell Technologies, and a customer panel where Pfizer, RBC, and Blitzy talked candidly about what it actually takes to build a knowledge layer at scale. The day didn't stop at the main stage. In the afternoon, folks got hands-on in our GraphRAG workshop and dug into strategy in the Executive Program, featuring sessions by Felix Van de Maele of Collibra, a fireside chat between Maribel Lopez and Kerry Khoo-Fazari, PhD Engineering of RBC, and an interactive discussion with Jesús Barrasa and Bryan Nairn. None of this happens without the people who showed up to share it. Thank you to our partners, speakers, and the community who made GraphSummit NYC 2026 unforgettable! #GraphSummit2026 #neo4j

"We can join what is not joinable and retrieve relationships from different sources" GraphTalk Manufacturing in Munich was the perfect scenario to listen to about how #Neo4j is used in different industries. Thank you, Michael Derfler, from Siemens, Uta Schäfer, from Robert Bosch, and Jan Frieling from CIMPA! Check out more stories here: https://bit.ly/4dUbK3n Where will we be next? https://bit.ly/4ahv2gI

Neo4j Live: AgentMemory for .NET: Persistent AI Agent Memory Engine .NET developers building AI agents have felt this gap: Neo4j Agent Memory shipped for Python and TypeScript, but .NET was left bolting things together. José L. Latorre closes it with AgentMemory for .NET - a from-scratch implementation verified 178/178 against Neo4j's own Agent Memory Test Compatibility Kit. In this livestream, he shows how the same three memory layers - short-term, long-term (POLE+O), and reasoning - now live natively in .NET, wired straight into Microsoft Agent Framework and Semantic Kernel, so your agent remembers by design, not by hoping it calls the right tool at the right time. Guest: Jose Luis Latorre Blog: https://lnkd.in/de9AzwRF #neo4j #graphdatabase #agenticai #knowledgelayer #knowledgegraph #graphrag #AIAgents #dotnet #agentframework

ICYMI "Infrastructure tax" is a barrier to AI innovation. Today, we are announcing MCP for Aura, a hosted MCP server built into your Aura instance. MCP for Aura eliminates the tax by providing a fully hosted, native MCP server within Neo4j Aura, allowing developers to connect AI agents to their graph data in minutes. You connect your AI client, authenticate with the Aura login you already use, and start querying your graph in natural language. ✅ Zero installs ✅ Native OAuth authentication ✅ Includes specific tools for Get Schema, Read, and Read-Write, allowing developers to control exactly what an AI agent can access. ✅ Grounded Reasoning More details on how to install, what you need, and an example, here: https://bit.ly/4b63qf7 #AI #MCP #CLAUDE