About us
Developers interested in learning about and working with graph databases for social, spatial, hierarchical or other highly connected data sets. We host hands-on lab sessions, technology reviews, topical lectures, and plenty of social beer nights. Curious about graphs, want to pimp your non-RDBMS skills? Join us! more at http://neo4j.com
Interested to speak at this or future meetups? Fill this form: https://dev.neo4j.com/submit-your-talk
Featured event
Graphs Gone Wild
Register: https://globalai.community/e/ack9t53d
Bring your coding agent. Pick an idea. Build something.
Graphs Gone Wild is for people experimenting with AI agents, memory, documents, graphs, MCP, and new developer tooling.
Use whatever stack you like: Cursor, Claude Code, Codex, Copilot, your own agent setup, frameworks, databases, models, or something completely experimental.
For this NODES 2026 pop-up, Neo4j will provide some of the building blocks, including Document Intelligence, Aura MCP, knowledge graphs, and Agent Memory.
More tools, technologies, and partners will be revealed soon.
The goal: build something interesting in a few hours. It does not need to be polished. A working experiment and a good demo are enough.
What can you build?
Anything around agents, connected knowledge, memory, documents, tools, or graphs.
Upcoming events
6
Munich Datageeks September Edition
JetBrains GmbH, Christoph-Rapparini-Bogen 23, 80639 München-Neuhausen-Nymphenburg, Germany, München, BY, DERegister: https://www.meetup.com/de-de/munich-datageeks/events/316577539
🎤 What changed in this room? Spatial memory for physical AI on a Neo4j graph by Jordi Spranger
Robots and AI agents forget the world the moment the camera stops. Spranic gives machines a persistent memory of physical space: capture a room with commodity hardware, turn it into a scene graph in Neo4j, capture it again, and ask the graph what changed. In 20 minutes I show the live pipeline end to end, the graph model behind it (objects, positions, visits, time), and why a graph database is the right substrate for spatial memory. Live demo included.
About Jordi Spranger:
Founder of Spranic (Spranger AI GmbH), building the spatial memory layer for physical AI. Speaker at WeAreDevelopers World Congress 2026.3 attendees- Network event
Neo4j Live: AgentMemory for .NET: Persistent AI Agent Memory Engine
·OnlineOnline2 attendees from 22 groups.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 Latorre ( https://www.linkedin.com/in/joslat/ )
Blog: https://neo4j.com/blog/developer/agentmemory-for-net-a-native-sibling-to-neo4j-agent-memory/
#neo4j #graphdatabase #agenticai #knowledgelayer #knowledgegraph #graphrag #AIAgents #dotnet #agentframework
1 attendee from this group - Network event
Road to NODES 2026
·OnlineOnline42 attendees from 31 groupsRegister: https://neo4j.registration.goldcast.io/series/94f27929-1670-4f2b-bfdd-ab4e48eb8c22
# Road to NODES 26 Workshops
Get hands-on with graphs and AI before NODES 2026, Neo4j's free 24-hour global conference on November 12. Road to NODES is a series of free, two-hour, live workshops that walk you through building real graph-powered systems step by step.
Sessions include:- Oct 1 — Build knowledge graphs from unstructured documents and structured data, then power similarity search with embeddings and Neo4j vector indexes.
- Oct 8 — Tackle hallucinations at the structural level with GraphRAG retrieval, semantic tool selection, multi-agent swarms, and agent steering.
- Oct 15 — Build a lightweight knowledge layer over your documents and SQL data using tables of contents, themes, and a semantic connections layer.
- Oct 22 — Query Snowflake, Databricks, or Google BigQuery directly with Cypher using Neo4j Virtual Graph, no data movement required.
- Oct 29 — Build a full graph-based agent memory stack with hierarchical context graphs and dynamic playbooks.
- Nov 5 — Build a memory layer with the Neo4j Agent Memory Service, combining short-term conversation history, long-term entities, and reasoning traces in one graph.
Each session runs live at multiple times to fit different time zones, so pick the slot and topics that work for you.
1 attendee from this group Graphs Gone Wild
CODE University of Applied Sciences, Donaustraße 44, 12043 Berlin, Germany, Berlin, BE, DERegister: https://globalai.community/e/ack9t53d
Bring your coding agent. Pick an idea. Build something.
Graphs Gone Wild is for people experimenting with AI agents, memory, documents, graphs, MCP, and new developer tooling.
Use whatever stack you like: Cursor, Claude Code, Codex, Copilot, your own agent setup, frameworks, databases, models, or something completely experimental.
For this NODES 2026 pop-up, Neo4j will provide some of the building blocks, including Document Intelligence, Aura MCP, knowledge graphs, and Agent Memory.
More tools, technologies, and partners will be revealed soon.
The goal: build something interesting in a few hours. It does not need to be polished. A working experiment and a good demo are enough.
What can you build?
Anything around agents, connected knowledge, memory, documents, tools, or graphs.1 attendee
Past events
301
