# Neo4j Neo4j is a graph intelligence platform and graph database for storing, querying, and analyzing connected data, with developer resources for building graph-powered applications. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Philip Rathle on why AI agents keep reaching for a knowledge graph DevFeed: [Philip Rathle on why AI agents keep reaching for a knowledge graph]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-08-05T23:21:28Z Content type: article Language: en Sources: [WorkOS Blog]() Topics: [Artificial Intelligence](), [Neo4j](), [Graphs](), [graph-database](), [data]() Tags: [agents](), [ai](), [ai-agents](), [data](), [graph](), [graph-database](), [knowledge-graph]() ### AI overview WorkOS CEO Michael Grinich interviews Neo4j CTO Philip Rathle about using knowledge graphs as an AI knowledge layer. Rathle argues that agents need deterministic, explainable access to structured company data for questions where accuracy, sovereignty, and access controls are critical, while noting that graph retrieval can provide context for better model decisions. ### Source excerpt Neo4j CTO Philip Rathle on why over 70% of new business is now the AI knowledge layer, where agents need deterministic answers, and how error rates compound. ## Building a Production AI Deep Research Agent with Temporal, Neo4j, Auth0, and Redpanda DevFeed: [Building a Production AI Deep Research Agent with Temporal, Neo4j, Auth0, and Redpanda]() Original publisher: [Read original article]() Author: Chandler Mayo Published: 2026-06-10T00:00:00Z Content type: article Language: en Sources: [Temporal Blog]() Topics: [AI Agent](), [Orchestration](), [Persistence](), [observability](), [Security](), [Auth0](), [Neo4j]() Tags: [agents](), [ai](), [ai-agents](), [auth0](), [community](), [infrastructure](), [observability](), [orchestration](), [parallel](), [pdf](), [persistence](), [production](), [security](), [streaming](), [teams]() ### AI overview The article describes a production-oriented deep research agent built by four teams using Temporal, Neo4j, Auth0, and Redpanda. It explains how orchestration, persistence, security, and event streaming support a long-running, multi-agent workflow. ### Source excerpt Four teams built a production AI deep research agent using Temporal, Neo4j, Auth0, and Redpanda, revealing the infrastructure beneath every great AI agent. ## Inside Neo4j's Agent Memory DevFeed: [Inside Neo4j's Agent Memory]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-05-19T08:55:51Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [Neo4j](), [Graphs](), [Artificial Intelligence](), [Retrieval Augmented Generation (RAG)]() Tags: [agent](), [ai](), [graph](), [knowledge-graph](), [memory](), [rag](), [retrieval-augmented-generation-rag]() ### AI overview The article presents Neo4j knowledge graphs as a model for durable agent memory. It argues that file-based logs and vector indexes lack identity and relationship tracking, while a structured graph can connect entities, preferences, and facts across a growing knowledge base. ### Source excerpt The knowledge-graph patterns that turn one-shot conversations into compounding intelligence. ## Neo4j storage internals DevFeed: [Neo4j storage internals]() Original publisher: [Read original article]() Published: 2020-08-09T00:00:00Z Content type: tutorial Language: en Sources: [Gaurav Sarma's Blog]() Topics: [Neo4j](), [graph-database](), [Graphs](), [Databases]() Tags: [graph-database](), [indexes](), [internals](), [storage]() ### AI overview This article examines Neo4j storage internals and compares graph database relationship traversal with the join-based approach used by MySQL. It explains Neo4j's index-free adjacency and fixed-record-size pointer scheme, while discussing storage and cluster-size comparisons with MongoDB and Cassandra. ### Source excerpt I was exploring Neo4j and came upon this [video](https://www. youtube... ## I wish I knew my consumers - Maven Reverse Dependency DevFeed: [I wish I knew my consumers - Maven Reverse Dependency]() Original publisher: [Read original article]() Author: roar Published: 2013-01-31T12:49:05Z Content type: article Language: en Sources: [Finn.no]() Topics: [Reverse Dependencies](), [Maven](), [Neo4j](), [graph-database](), [Library](), [bug]() Tags: [bug](), [dependency](), [graph-database](), [libraries](), [maven](), [reverse-dependencies]() ### AI overview The article describes a Maven plugin that records project dependencies in a Neo4j graph database and examines reverse dependencies to identify applications using a Maven project, including the versions they use. The plugin was created to help developers notify users when shared libraries are fixed or changed. ### Source excerpt At FINN.no being a developer fixing bugs in a library is a breeze. Getting every user of your library to use the fix, however, is a different story. How to know who to notify? I mean, I know my library's dependencies, but who "out there" has dependency to the component where I just fixed a bug? I wish. Enter maven-dependency-graph. The idea was born on the plane back home from a Copenhagen hosted conference. Graph database. Download neo4j and start dabbling at a maven plugin. Flying time Copenhagen - Oslo was too short, all of a sudden. From there, the idea slept for a couple of years. Until the need arose somewhere among the developers. With 100+ different applications running with common core services and libraries, everybody suddenly needed to know who depended on their code which had recently been bugfixed. So the old idea was dusted off and once more saw the light of day. We needed to upgrade the server installation and the API to neo4j - which took some time to grasp; but after some playing around, it became obvious and easy. The idea was to have every project report its dependencies to a graph database, building the tree of dependencies on each commit. This constitutes one half of the plugin. Over time, all projects will have reported their dependencies, and from there on part two of the plugin comes into use. It will examine the reverse dependencies to the current maven project, and report all incoming dependencies to it in the maven log. Hey, presto! We now know who out there uses us! And even which version they are using, thanks to two different keys into the built-in lucene index engine. The plugin is published on github @ Finn Technology's account. Feel free! @gardleopard and @roarjoh Usage examples Dependencies to current maven project: mvn no.finntech:dependency-mapper-maven-plugin:read [INFO] Scanning for projects... [INFO] [INFO] ------------------------------------------------------------------------ [INFO] Building greenpages thrift-client 3.4.5-SN