NODES AI 2026
as the organisers put it
Join us on April 15 for NODES AI - an online conference dedicated to the future of AI with graphs. We'll explore AI, context engineering, and intelligent agents.
| title | author | length |
|---|---|---|
| Opening Keynote: Exploring Context Graphs: From Data to Decisions - Extended Version | Emil Eifrem, Lasse Andresen, Animesh Koratana, William Lyon, Philip Rathle | 48m |
Panel argues that context graphs are a concrete layer that capture decision traces (agent tool calls, outcomes, why a deal closed) and stitch them into a… | ||
| Agent Reasoning with Graph World Models | Lucas Godfrey | 30m |
Claims that existing Neo4j graphs convert directly into lightweight world models and that storing two simple statistics per transition edge enables rollouts… | ||
| The AI Agent Memory Landscape | William Lyon | 29m |
Argues that context graphs plus three concrete memory types — short-term, long-term and reasoning memory — are the practical difference between demo agents and… | ||
| The GraphRAG System That Asks Back: Intelligent Probing with Contextual Answers | Rajarshee Dhar, Vivek Singh | 29m |
Claims a production system called AID (Assisted Intelligent Dialogue) that uses Neo4j graphs to turn vague support queries into targeted follow-ups, generating… | ||
| Building a Customer-Intelligence Brain: How GraphRAG Turns Data into Decisions | Eckhart Boehme | 31m |
Claims a working Customer-Intelligence system built by converting nine interviews into a Neo4j knowledge graph using the 12 Elements of Customer Progress… | ||
| Opening Keynote: Exploring Context Graphs: From Data to Decisions | Emil Eifrem, William Lyon, Lasse Andresen, Animesh Koratana, Philip Rathle | 26m |
Panel claims a decision trace—a recorded chain of agent tool calls and human interactions—lets systems capture the “why” behind outcomes and form a reusable… | ||
| From Data to Knowledge to Action - The Graph Intelligence Platform | Sudhir Hasbe | 21m |
Claims Neo4j closes the gap between enterprise data and AI by building a knowledge layer of ontologies, domain data, and decision traces so agents get context… | ||
| Agentic GraphRAG: Autonomous Knowledge Graph Construction and Adaptive Retrieval | Athulya Anil | 21m |
A multi-agent pipeline automatically infers schema and builds a Neo4j knowledge graph (using spaCy, a BAAI sentence transformer and lightweight LLM components)… | ||
| The Future of Enterprise AI Is Context Infrastructure, Not Better Models | Manuel Maguga Darbinian | 20m |
Claims that the real bottleneck is fragmented business context, not better LLMs, and demonstrates Spiintel: an ontology-driven intelligence foundation that… | ||
| Smarter MCP Servers: Using a Graph to Solve the Context Window Problem | Jonathan Giffard | 28m |
Compares three MCP server patterns—full-list, lazy-loading, and a graph-backed registry—and shows concrete savings: modeling an Aura API with 26 endpoints… | ||
| Adaptive GraphRAG: A Framework for Knowledge Graph Quality, Consistency, Evolution | Joshua Yu | 25m |
Adaptive GraphRAG is a Neo4j-based lifecycle for keeping generated knowledge graphs accurate and traceable as new text arrives, using Cypher, GDS, vector… | ||
| Lakehouse + Graph: Delta Lake, Unity Catalog and Neo4j for Governed AI Pipelines | Shaurya Agrawal | 25m |
Demonstrates a practical pipeline pairing Delta Lake bronze/silver/gold with Neo4j to power GraphRAG and feature extraction, using the Neo4j Spark Connector… | ||
| Graph Theory and Games: A Case Study on New York Times Connections | Shafik Quoraishee | 25m |
Represents each of the 16 puzzle words as graph nodes and the four hidden groups as colors, stores embeddings and word associations in a Neo4j-backed workflow… | ||
| Agentic AI Governance: Data Foundations & Real-Time Policy Enforcement | William Liang, Murthy Chandrapaty | 32m |
Adobe migrates PAS from Cosmos DB to a Neo4j property-centric graph, exploding properties into first‑class nodes to enable targeted traversals that prune… | ||
| Agentic AI with Knowledge Graphs on the JVM: A Music Graph in Practice | Luanne Misquita | 29m |
A Neo4j-backed personal record graph plus embeddings and GDS powers two JVM agents built with the Embabel Agent Framework: a chatty discovery agent that… | ||
| Agentic GraphRAG: Autonomous Knowledge Graph Construction and Adaptive Retrieval | Athulya Anil | 12m |
A multi-agent pipeline automatically infers schemas and builds a knowledge graph from 25 documents using agentic schema inference plus entity, relation… | ||
| Aura Agents in Action | Ed Sandoval, Kevin Kay, Jesse Osborne, Diego Giron | 31m |
Aura Agent runs atop AuraDB and exposes three concrete tool types: Cypher templates, vector similarity search, and a text to Cypher generator that turns ad‑hoc… | ||
| Beyond Recall: Creating Agentic Personas with Persistent, Evolving Memory | Mohamed Fazil | 21m |
Claims that Neo4j becomes a long‑term memory layer for agents, turning short‑lived chat into a Neo4j graph-native memory that stores nodes like user… | ||
| Build Intelligent AI Agents With Context Engineering | Michael Hunger | 31m |
Claims that engineering what goes into an LLM’s context—not bigger windows—cuts failures by steering retrieval, tool use, and memory. Uses graph RAG and a… | ||
| Building a Cross-Border KG: AI Powered Entity Resolution & Risk Detection | Artem Sentsov | 26m |
ClearPic.ai aggregates five years of public registries, court PDFs and media across seven jurisdictions into a unified knowledge graph of ~25M data points… | ||
| Building Secure Services with AI Agents: Patterns From Real-World Engineering | Marat Kenzhebulatov | 22m |
Recommends running agents inside a Docker container with strict privileges, a command whitelist, and no long‑lived credentials in agent context so agents… | ||
| Building Smarter Mobile Apps with On-device AI Agents & GraphRAG | Ashita Prasad | 30m |
Shows a concrete developer path: start with an LLM-only agent (Claude 3.7 Sonnet on Amazon Bedrock) that confidently misanswers (claims Transcendence’s Wally… | ||
| Complex Querying of Cyber Knowledge Graph for Robust Cyber Defense | Joseph Aguayo, Mahantesh Halappanavar, Samantha Silva, Siddhartha Shankar Das, Moqsadur Rahman | 35m |
A production Neo4j knowledge graph ingests CVE/CWE/CAPEC/CPE feeds (336,000 CVEs, ~620,000 CPEs) and adds ~350,000 inferred edges using V2W BERT and VWC BERT… | ||
| From AI Workflows to Graph-Native Reasoning: A Dify Plugin for Querying Neo4j | Nikola Milosevic | 31m |
Open-source Neo4j query plugin for Dify that runs parameterized Cypher inside agentic workflows, authenticates to Aura or self-hosted instances, and enforces a… | ||
| Fusing NLP and Graph: Building a Conversational Agent for Enriched Financial Data | Alix de Cremoux, Gabriel Laffitte | 30m |
Built an end-to-end pipeline that turns 400‑page PDFs into a validated knowledge graph by combining LLM extraction, graph matching, and a reasoning agent… | ||
| Ghost-busting with Neo4j Graph Analytics in Snowflake | Timothy J Spann, Stu Moore | 29m |
Demo shows Neo4j Graph Analytics running inside Snowflake using a native app plus a PKE meter agent that reads a private share, builds graph views, runs… | ||
| Graph-Powered Compliance: Building Intelligent Regulatory Mapping with AI and Neo4j | Chandana Mulpuri | 16m |
Demonstrates a working system that models regulations, controls, assets and evidence in a single Neo4j graph, uses LLMs to extract requirements into… | ||
| Graph-Powered Storyworlds: Using Neo4j To Keep 1M+ Word LitRPG Epics Coherent w/ AI | Prem Chandrasekaran | 27m |
A Neo4j-backed pipeline extracts entities, stats, quests and timelines from DOCX/Markdown manuscripts into a narrative knowledge graph that tracks continuity… | ||
| How to Build the Next Wave of Graph-Based Agentic AI | Charles Borderie | 30m |
Claims a Text2Graph failure mode and shows a fine-tuned Perseus pipeline that produces ontology-driven graphs with “99% output validity” and 100%… | ||
| Infinigraph: Vector Data at Scale | Hannah Tse Debenham | 23m |
Neo4j ships InfiniGraph: a sharded property database that moves node and relationship properties to separate property shards, keeping a lightweight graph shard… | ||
| Multi-Agent Shared Graph Memory: Building Collective Knowledge for Agents | Vaibhava Lakshmi Ravideshik | 21m |
Argues that multi-agent systems fail from lack of shared memory and proposes a concrete architecture using Neo4j + Quadrant where Neo4j is the persistent world… | ||
| Neurosymbolic Architecture in Production with Neo4j, GDS, Node2Vec & LLM Grounding | João Cunha | 30m |
Kipon runs a production neurosymbolic pipeline on Neo4j + AuraDS combining Node2Vec structural embeddings with LLM semantic vectors to produce a unified vector… | ||
| Semiont: A Graph Based, AI Native Wiki and Annotator | Adam Pingel | 30m |
Semiont is an open source, Apache 2 licensed AI-native wiki that stores document annotations as durable graph and git-backed events, using W3C Web Annotation… | ||
| Temporal Substrate Architecture: Building Persistent Identity for Autonomous Agents | Conor O'Shea | 31m |
Claims a production architecture that gives agents a sense of time using Neo4j and an MCP server with a two‑layer temporal substrate (process/time) and… | ||
| EventKernel: Multi-Hop Reasoning and GraphRAG for AI-Powered Event Intelligence | Divakar Kumar | 27m |
Claims a hybrid retrieval that beats vector-only by anchoring embeddings to a Neo4j domain graph and running deterministic traversals; the demo populates ~50… | ||
| MemMachine: Agents That Learn, Memory That Lasts | Christian Kniep | 30m |
Introduces MemMachine as an open-source memory layer that uses a Neo4j graph backend for episodic, factual, semantic and profile memory and claims portability… | ||
| The Searchable Grid: Building a GraphRAG-Powered Digital Twin for Real-Time Insights | Lijimol George, Boobalan Sivaprakasam, Mathumitha Ganesan Sathiyabama | 31m |
Claimed system unifies GIS, AMI, asset health and DER into a semantic Neo4j graph and layers a GraphRAG-powered Digital Twin that answers plain-English queries… | ||
| nothing matches | ||