# 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.

## CVE-2026-125080 - Cypher injection via orderBy placeholder in Spring Data Neo4j custom queries

DevFeed: [CVE-2026-125080 - Cypher injection via orderBy placeholder in Spring Data Neo4j custom queries](<https://devfeed.tech/articles/cve-2026-125080-cypher-injection-via-orderby-placeholder-in-spring-data-neo4j-custom-queries-145904.md>)

Original publisher: [Read original article](<https://cvefeed.io/vuln/detail/CVE-2026-125080>)

Author: CVEFEED.io

Published: 2026-11-20T09:19:56Z

Content type: news

Language: en

Sources: [Latest High/Critical Vulnerabilitiy Feed](<https://devfeed.tech/sources/latest-high-critical-vulnerabilitiy-feed.md>)

Topics: [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [cve](<https://devfeed.tech/tags/cve.md>), [cve-2026-125080](<https://devfeed.tech/tags/cve-2026-125080.md>), [cypher](<https://devfeed.tech/tags/cypher.md>), [database](<https://devfeed.tech/tags/database.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [queries](<https://devfeed.tech/tags/queries.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-data](<https://devfeed.tech/tags/spring-data.md>), [spring-data-neo4j](<https://devfeed.tech/tags/spring-data-neo4j.md>)

### AI overview

CVE-2026-125080 is a high-severity Cypher injection in Spring Data Neo4j custom-query handling of the `orderBy` placeholder. A remote attacker can exploit it when an application passes unvalidated user input as the sort-order value, potentially reading database contents through blind reads or writing read content into new nodes. Writing query results to files is also possible when APOC and APOC file export are enabled; that path is conditional. The description lists affected versions as 6.1.0-8.0.8 and 8.1.0-8.1.2, and gives a severity score of 8.2.

### Source excerpt

CVE ID :CVE-2026-125080 Published : Nov. 20, 2026, 9:19 a.m. | 1 hour, 42 minutes ago Description :Improper neutralization of special elements in data query logic (Cypher injection) in the orderBy placeholder handling for custom queries in Neo4j Spring Data Neo4j versions 6.1.0 through 8.0.8 and 8.1.0 through 8.1.2 allows a remote attacker to read database contents via blind reads, write read content into new nodes, or, if APOC and APOC file export are enabled, to write query results to a file in the database's accessible file system via crafted sort order parameters. Exploitation requires an application that passes unvalidated user input as the orderBy value to a custom Cypher query using the placeholder directive. Severity: 8.2 | HIGH Visit the link for more details, such as CVSS details, affected products, timeline, and more...

## Your Coding Agent Can Read the Code. Give It the History with Relate by Neo4j

DevFeed: [Your Coding Agent Can Read the Code. Give It the History with Relate by Neo4j](<https://devfeed.tech/articles/your-coding-agent-can-read-the-code-give-it-the-history-with-relate-by-neo4j-144105.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/developer/your-coding-agent-can-read-the-code-give-it-the-history-with-relate-by-neo4j/>)

Author: Kate Smith

Published: 2026-11-18T21:00:00Z

Content type: tutorial

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [code search](<https://devfeed.tech/topics/code-search.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [codex](<https://devfeed.tech/topics/codex.md>), [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-skill](<https://devfeed.tech/tags/agent-skill.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [api-key](<https://devfeed.tech/tags/api-key.md>), [cli](<https://devfeed.tech/tags/cli.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [developer](<https://devfeed.tech/tags/developer.md>), [extension](<https://devfeed.tech/tags/extension.md>), [git](<https://devfeed.tech/tags/git.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [history](<https://devfeed.tech/tags/history.md>), [load](<https://devfeed.tech/tags/load.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [relate](<https://devfeed.tech/tags/relate.md>), [repository](<https://devfeed.tech/tags/repository.md>), [security](<https://devfeed.tech/tags/security.md>), [source](<https://devfeed.tech/tags/source.md>)

### AI overview

Relate combines a repository's Git history and working tree in one graph, letting coding agents find co-changed files, prior change patterns, and contributors that source code alone may not reveal. In the FastAPI example, `api_key.py` repeatedly changed with three security modules that do not reference it; all three tested agents found those siblings with the graph, while none did from source code alone. The post shows importing history with `git-to-graph` and file text with `fs-to-graph`, then querying the store through read-only MCP or the CLI. The comparison also found that agents could identify tests and imported files from code, but needed history to identify relevant past contributors. File-text matching for unreferenced pairs is approximate, and `fs-to-graph` defaults to a 64 KB content cap, which can omit large files unless raised.

### Source excerpt

Load a repository's git history into a graph with Relate's git-to-graph extension, serve it read-only, and see what a coding agent finds with it that it cannot find in the source tree. In a popular open source codebase, security/api_key.py has... Read more ->

## Graph-RAG for Enterprise Documents: Building a Knowledge Graph from PDFs, Wikis, and Databases

DevFeed: [Graph-RAG for Enterprise Documents: Building a Knowledge Graph from PDFs, Wikis, and Databases](<https://devfeed.tech/articles/graph-rag-for-enterprise-documents-building-a-knowledge-graph-from-pdfs-wikis-and-databases-140616.md>)

Original publisher: [Read original article](<https://machinelearningmastery.com/graph-rag-for-enterprise-documents-building-a-knowledge-graph-from-pdfs-wikis-and-databases/>)

Author: Shittu Olumide

Published: 2026-11-18T11:00:00Z

Content type: tutorial

Language: en

Sources: [MachineLearningMastery.com](<https://devfeed.tech/sources/machinelearningmastery-com.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [Tutorial](<https://devfeed.tech/topics/tutorial.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [api](<https://devfeed.tech/tags/api.md>), [arangodb](<https://devfeed.tech/tags/arangodb.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [cmdb](<https://devfeed.tech/tags/cmdb.md>), [configuration-management-database](<https://devfeed.tech/tags/configuration-management-database.md>), [confluence](<https://devfeed.tech/tags/confluence.md>), [connection-pool](<https://devfeed.tech/tags/connection-pool.md>), [database](<https://devfeed.tech/tags/database.md>), [databases](<https://devfeed.tech/tags/databases.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-rag](<https://devfeed.tech/tags/graph-rag.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [pdfs](<https://devfeed.tech/tags/pdfs.md>), [python](<https://devfeed.tech/tags/python.md>), [rag](<https://devfeed.tech/tags/rag.md>), [wikis](<https://devfeed.tech/tags/wikis.md>)

### AI overview

The excerpt describes a three-tier Graph-RAG design that prioritizes live service-registry facts over wiki runbooks and PDF context. A small SPOC quad store holds registry and wiki facts with source labels; SQLite is used in the example, with Postgres presented as an isolated swap. Runbook prose is parsed with key-value regexes, while PDFs are extracted with pdfplumber, split into roughly 500-character chunks, and embedded in Chroma as a fallback. All tiers are queried and fused in one prompt: conflicting lower-priority facts are excluded, and PDF context can supplement structured facts. The example uses spaCy plus a known-service-name list and runs locally with Ollama and llama3.2. Production considerations include keeping registry data live, refreshing wiki/PDF indexes regularly, adapting extraction to real wiki formats, applying access controls before prompting, and using a graph database for larger connected datasets. The approach avoids a routing model but adds token cost and depends on the model following explicit rules.

### Source excerpt

Prerequisites You'll need Python 3.

## The knowledge layer for enterprise AI: Domain Ontology

DevFeed: [The knowledge layer for enterprise AI: Domain Ontology](<https://devfeed.tech/articles/the-knowledge-layer-for-enterprise-ai-domain-ontology-139351.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/developer/the-knowledge-layer-for-enterprise-ai-domain-ontology/>)

Author: Jocelyn Hoppa

Published: 2026-11-17T08:57:00Z

Content type: tutorial

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [data-governance](<https://devfeed.tech/topics/data-governance.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [business logic](<https://devfeed.tech/topics/business-logic.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [developer](<https://devfeed.tech/tags/developer.md>), [domain](<https://devfeed.tech/tags/domain.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [enterprise-architecture](<https://devfeed.tech/tags/enterprise-architecture.md>), [genai](<https://devfeed.tech/tags/genai.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-layer](<https://devfeed.tech/tags/knowledge-layer.md>), [ontology](<https://devfeed.tech/tags/ontology.md>), [semantic-layer](<https://devfeed.tech/tags/semantic-layer.md>)

### AI overview

The article presents a Neo4j domain ontology as a governed graph layer that lets enterprise agents resolve business terms by context and trace who owns each meaning and which rule enforces it. Its churn example preserves distinct enterprise, Retention, Customer Insight, and Credit Risk definitions instead of merging them; role-based stewardship and validity intervals let users identify the applicable meaning and recover historical definitions. Candidate terms and links extracted from wikis or report code retain source, extraction date, and confidence, remain proposed until a steward approves them, and can be checked against evaluable graph rules. The model links concepts, attributes, rules, roles, and process tasks, including separating changeable affordability thresholds into rules. The described build requires Neo4j 2026.02 or later, Enterprise Edition, and Cypher 25, with chapters 1 and 2 loaded first. It establishes definitions and rules; the article says the later data-products layer is needed to supply consumption-ready data and numbers.

### Source excerpt

This series is the practical build companion to Jesús Barrasa's knowledge layer manifesto. This chapter is built on the previous chapter 2: Processes. Building this at enterprise scale? Neo4j Context Engine is the new Neo4j product for building a knowledge... Read more ->

## Adaptive-Elbow Graph Traversal for Schema Retrieval in Text-to-SQL

DevFeed: [Adaptive-Elbow Graph Traversal for Schema Retrieval in Text-to-SQL](<https://devfeed.tech/articles/adaptive-elbow-graph-traversal-for-schema-retrieval-in-text-to-sql-138306.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20979>)

Author: Fabio Picariello, Salvatore Cipolla, Susanna Bonura, Vito Morreale

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [text2sql](<https://devfeed.tech/topics/text2sql.md>), [AI for SQL query generation](<https://devfeed.tech/topics/ai-for-sql-query-generation.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [cosine similarity search](<https://devfeed.tech/topics/cosine-similarity-search.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [database](<https://devfeed.tech/tags/database.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [graph](<https://devfeed.tech/tags/graph.md>), [join](<https://devfeed.tech/tags/join.md>), [llm](<https://devfeed.tech/tags/llm.md>), [precision](<https://devfeed.tech/tags/precision.md>), [question](<https://devfeed.tech/tags/question.md>), [recall](<https://devfeed.tech/tags/recall.md>), [relational-databases](<https://devfeed.tech/tags/relational-databases.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [schema](<https://devfeed.tech/tags/schema.md>), [schemas](<https://devfeed.tech/tags/schemas.md>), [selection](<https://devfeed.tech/tags/selection.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [sql](<https://devfeed.tech/tags/sql.md>), [text](<https://devfeed.tech/tags/text.md>), [traversal](<https://devfeed.tech/tags/traversal.md>)

### AI overview

AEGT (ElbowHop) retrieves database tables for text-to-SQL using an adaptive elbow cutoff and bidirectional foreign-key traversal. The cutoff selects a per-question schema size instead of a fixed top-k, while traversal can recover join-critical bridge tables that embedding similarity misses. Across BIRD Mini-Dev per-database pools (3-13 tables), its 11 schemas merged (74 tables), and a merged Spider-train graph (546 tables), the adaptive cutoff was the dominant mechanism: at matched recall it roughly doubled precision over a fixed budget on larger pools, with the advantage growing as pools expanded. Foreign-key traversal helped recover bridge tables in the single-hop, tight-budget case. The authors present the approach as a low-cost, recall-robust first retrieval stage for downstream selection or generation.

### Source excerpt

arXiv:2611.20979v1 Announce Type: new Abstract: LLM-based natural-language interfaces to relational databases are gated by a schema-retrieval step: the generator can only be as good as the slice of schema it is shown. On a database with hundreds of tables, that slice must be selected and the selection is two-sided---omit a needed table and the query becomes unrecoverable, include too many and the irrelevant ones act as noise that degrades the model's output. When an agentic retriever that lets the model inspect the schema can be too costly or too slow, the fallback is an embedder that ranks tables by cosine similarity and keeps a top-k. This fallback has two weaknesses: a fixed budget is suboptimal question by question, and embedding similarity overlooks foreign-key-linked tables that are necessary for joins. We present Adaptive-Elbow Graph Traversal (AEGT, ElbowHop for short), a property-graph table retriever that addresses both: an adaptive elbow cutoff replaces the fixed budget with a per-question one under a single aggressiveness parameter, and bidirectional foreign-key traversal deterministically recovers the bridge tables embedding similarity misses. We evaluate the retriever on 3 corpora of increasing candidate-pool size (BIRD Mini-Dev queried per database, 3--13 tables; its eleven schemas merged, 74; and a merged Spider-train graph, 546) and isolate the two mechanisms under a per-question budget-matched protocol. Across these settings the adaptive elbow emerges as the dominant mechanism---at matched recall it roughly doubles precision over a fixed budget on the larger pools, the margin widening as the pool grows---while the foreign-key traversal pays off on the join-critical bridge tables dense retrieval cannot reach, in the single-hop tight-budget case. We characterize the method as a low-cost, recall-robust first stage for schema retrieval on which a downstream selection or generation step can build.

## Neo4j Virtual Graph is now generally available

DevFeed: [Neo4j Virtual Graph is now generally available](<https://devfeed.tech/articles/neo4j-virtual-graph-is-now-generally-available-135999.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/news/neo4j-virtual-graph-is-now-generally-available/>)

Author: Stu Moore

Published: 2026-11-16T17:25:06Z

Content type: release

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [airport](<https://devfeed.tech/tags/airport.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [analyst](<https://devfeed.tech/tags/analyst.md>), [analysts](<https://devfeed.tech/tags/analysts.md>), [aura](<https://devfeed.tech/tags/aura.md>), [aura-graph-analytics](<https://devfeed.tech/tags/aura-graph-analytics.md>), [aws](<https://devfeed.tech/tags/aws.md>), [azure](<https://devfeed.tech/tags/azure.md>), [connected-data](<https://devfeed.tech/tags/connected-data.md>), [cypher-gql](<https://devfeed.tech/tags/cypher-gql.md>), [etl](<https://devfeed.tech/tags/etl.md>), [fraud-detection](<https://devfeed.tech/tags/fraud-detection.md>), [gcp](<https://devfeed.tech/tags/gcp.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [graph-technology](<https://devfeed.tech/tags/graph-technology.md>), [graph-visualization](<https://devfeed.tech/tags/graph-visualization.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [neo4j-aura](<https://devfeed.tech/tags/neo4j-aura.md>), [news](<https://devfeed.tech/tags/news.md>), [security](<https://devfeed.tech/tags/security.md>), [virtual-graph](<https://devfeed.tech/tags/virtual-graph.md>), [zero](<https://devfeed.tech/tags/zero.md>)

### AI overview

Neo4j Virtual Graph is generally available in Aura on GCP, with AWS and Azure support described as coming soon. It maps warehouse tables into a graph and translates Cypher queries into deterministic SQL executed in Snowflake, Databricks, Iceberg tables on S3, or BigQuery; data stays in the warehouse, and its access follows the connecting role's permissions and masking. Users can model graphs manually, from schema, or with AI, then query them through Neo4j tools and drivers. The excerpt highlights bounded quantified path patterns for traversals such as fraud and supply chain analysis, plus monitoring, pause/resume, and Private Link for dedicated environments. Virtual Graph is read-only and supports only part of Cypher; unsupported queries return error 42NG1. Warehouse execution means latency depends on compute and query complexity, with responses expected in seconds or minutes. The excerpt recommends AuraDB when writes, full Cypher, or millisecond response times are required. External IdPs, Aura MCP integration, and multi-source graphs are listed as forthcoming.

### Source excerpt

First on GCP, coming soon to AWS and Azure Today, Neo4j Virtual Graph is generally available in Neo4j Aura on GCP, with support for AWS and Azure to follow soon. Virtual Graph lets you build zero-ETL knowledge graphs, GraphRAG systems,... Read more ->

## Euler meets Codd

DevFeed: [Euler meets Codd](<https://devfeed.tech/articles/euler-meets-codd-135998.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/developer/euler-meets-codd/>)

Author: christoffer bergman

Published: 2026-11-16T11:43:00Z

Content type: article

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [databricks](<https://devfeed.tech/topics/databricks.md>), [graph theory](<https://devfeed.tech/topics/graph-theory.md>), [SQL](<https://devfeed.tech/topics/sql.md>), [BigQuery](<https://devfeed.tech/topics/bigquery.md>), [Snowflake streaming data architecture](<https://devfeed.tech/topics/snowflake-streaming-data-architecture.md>)

Tags: [analytics](<https://devfeed.tech/tags/analytics.md>), [aura](<https://devfeed.tech/tags/aura.md>), [aura-graph-analytics](<https://devfeed.tech/tags/aura-graph-analytics.md>), [bigquery](<https://devfeed.tech/tags/bigquery.md>), [cypher](<https://devfeed.tech/tags/cypher.md>), [cypher-gql](<https://devfeed.tech/tags/cypher-gql.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [databricks](<https://devfeed.tech/tags/databricks.md>), [developer](<https://devfeed.tech/tags/developer.md>), [fraud-detection](<https://devfeed.tech/tags/fraud-detection.md>), [graph](<https://devfeed.tech/tags/graph.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [query](<https://devfeed.tech/tags/query.md>), [snowflake](<https://devfeed.tech/tags/snowflake.md>), [sql](<https://devfeed.tech/tags/sql.md>), [virtual-graph](<https://devfeed.tech/tags/virtual-graph.md>)

### AI overview

Neo4j Virtual Graphs let users query relational data in Databricks with Cypher and explore it through Neo4j graph tools without copying the data. In a fraud-ring example, the author maps account and transaction tables to graph nodes and relationships, then finds chronologically ordered, decreasing transfers that return to their starting account. A bounded query returned the same rings as a native Neo4j graph, taking about 25 seconds versus 1.5 seconds; the author cautions this was not a scientific benchmark. Virtual Graphs provide graph query expression and visualization, but not native graph traversal speed, and the example required an upper bound because unbounded variable-length queries are unsupported. The described setup uses Aura, a paid feature requiring a credit card. The article says users can later import the data into a native graph using the same data source and model.

### Source excerpt

Neo4j Virtual Graph lets you query relational data in Databricks, Snowflake, BigQuery and similar platforms with Cypher/GQL, using Neo4j's full suite of graph tools.

## How to make graphs accessible

DevFeed: [How to make graphs accessible](<https://devfeed.tech/articles/how-to-make-graphs-accessible-136638.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/graph-database/how-to-make-graphs-accessible/>)

Author: michael worthington

Published: 2026-11-13T21:23:42Z

Content type: article

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Web Content Accessibility Guidelines](<https://devfeed.tech/topics/web-content-accessibility-guidelines.md>), [Data visualization](<https://devfeed.tech/topics/data-visualization.md>), [aria](<https://devfeed.tech/topics/aria.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [2-2](<https://devfeed.tech/tags/2-2.md>), [accessibility](<https://devfeed.tech/tags/accessibility.md>), [accessible](<https://devfeed.tech/tags/accessible.md>), [ada](<https://devfeed.tech/tags/ada.md>), [alt-text](<https://devfeed.tech/tags/alt-text.md>), [aria](<https://devfeed.tech/tags/aria.md>), [assets](<https://devfeed.tech/tags/assets.md>), [audio](<https://devfeed.tech/tags/audio.md>), [aura](<https://devfeed.tech/tags/aura.md>), [auradb](<https://devfeed.tech/tags/auradb.md>), [canvas](<https://devfeed.tech/tags/canvas.md>), [cloud-database](<https://devfeed.tech/tags/cloud-database.md>), [clustering](<https://devfeed.tech/tags/clustering.md>), [color](<https://devfeed.tech/tags/color.md>), [colors](<https://devfeed.tech/tags/colors.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [graph-visualization](<https://devfeed.tech/tags/graph-visualization.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [interactive](<https://devfeed.tech/tags/interactive.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [visualization](<https://devfeed.tech/tags/visualization.md>), [visualizing-graphs](<https://devfeed.tech/tags/visualizing-graphs.md>)

### AI overview

Graph accessibility is difficult because a graph's insight often lies in its topology--clusters, bridges, and overall patterns--which tables or linear text cannot fully preserve. WCAG 2.2 offers useful measures such as keyboard navigation, contrast, ARIA labels, and text alternatives, but the excerpt says there is no standardized framework for complex interactive graphs. Screen-reader design research offers structure, navigation, and description as dimensions, while sonification lacks an established grammar for arbitrary networks. Neo4j describes a layered approach: apply component-level accessibility measures and keyboard traversal where sensible; where needed, hide the canvas from screen readers with aria-hidden; and provide metadata or summaries of the graph's contents and insights. The article characterizes screen-reader traversal of dense graphs as potentially confusing and presents dynamically generated descriptions as a future possibility, not an established capability.

### Source excerpt

Build custom, interactive graph experiences with the Neo4j Graph Visualization Library, a flexible foundation that lets developers define the interactions their applications need.

## Using Neo4j Change Data Capture to Orchestrate Agents

DevFeed: [Using Neo4j Change Data Capture to Orchestrate Agents](<https://devfeed.tech/articles/using-neo4j-change-data-capture-to-orchestrate-agents-130390.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/developer/change-data-capture-to-orchestrate-agents/>)

Author: julian busch

Published: 2026-11-12T09:47:29Z

Content type: article

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Event-Streaming](<https://devfeed.tech/topics/event-streaming.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>), [Publish-subscribe pattern](<https://devfeed.tech/topics/pubsub.md>), [Python](<https://devfeed.tech/topics/python.md>)

Tags: [agent-orchestration](<https://devfeed.tech/tags/agent-orchestration.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-workflow](<https://devfeed.tech/tags/agentic-workflow.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent-development](<https://devfeed.tech/tags/ai-agent-development.md>), [ai-and-context](<https://devfeed.tech/tags/ai-and-context.md>), [ai-and-machine-learning](<https://devfeed.tech/tags/ai-and-machine-learning.md>), [cdc](<https://devfeed.tech/tags/cdc.md>), [change-data-capture](<https://devfeed.tech/tags/change-data-capture.md>), [cloud-orchestration](<https://devfeed.tech/tags/cloud-orchestration.md>), [cypher](<https://devfeed.tech/tags/cypher.md>), [data-orchestration](<https://devfeed.tech/tags/data-orchestration.md>), [developer](<https://devfeed.tech/tags/developer.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [multi-agent-orchestration](<https://devfeed.tech/tags/multi-agent-orchestration.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>)

### AI overview

Neo4j CDC can trigger agent handoffs directly from committed graph changes: a poller reads ordered change records with `db.cdc.query`, filters for transitions such as a `Task` moving from `PENDING` to `ACTIVE`, then dispatches an agent whose write-back can trigger the next step. This keeps task state, events, governance, and audit data queryable together in Cypher and avoids reconciling a separate broker. The excerpt describes graph-based dead-letter records, cursor replay within the transaction log's readable window, single-poller leases, and idempotent dispatch. Trade-offs include a roughly 750 ms polling floor per hop and possible loss if downtime exceeds log retention; Kafka is suggested for durable retention, while Temporal can handle durable timers or saga coordination. CDC requires AuraDB Business Critical or a self-managed Enterprise or Infinigraph edition.

### Source excerpt

You've built a multi-agent orchestration pipeline. One agent finishes its work and writes a result. The next agent should pick that result up and run. Something has to notice the first agent finished and wake the second one. The usual... Read more ->

## Announcing the Relate by Neo4j Hackathon 2026: Build AI Agents on an Embedded Graph Database

DevFeed: [Announcing the Relate by Neo4j Hackathon 2026: Build AI Agents on an Embedded Graph Database](<https://devfeed.tech/articles/announcing-the-relate-by-neo4j-hackathon-2026-build-ai-agents-on-an-embedded-graph-database-129710.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/graph-database/announcing-the-relate-by-neo4j-hackathon-2026-build-ai-agents-on-an-embedded-graph-database/>)

Author: Kate Smith

Published: 2026-11-12T01:55:00Z

Content type: news

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Hackathon](<https://devfeed.tech/topics/hackathon.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [build-ai-agents](<https://devfeed.tech/tags/build-ai-agents.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [connect](<https://devfeed.tech/tags/connect.md>), [connected-data](<https://devfeed.tech/tags/connected-data.md>), [database](<https://devfeed.tech/tags/database.md>), [developer](<https://devfeed.tech/tags/developer.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [event](<https://devfeed.tech/tags/event.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [hackathon](<https://devfeed.tech/tags/hackathon.md>), [launch](<https://devfeed.tech/tags/launch.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [nodes](<https://devfeed.tech/tags/nodes.md>), [online](<https://devfeed.tech/tags/online.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [relate](<https://devfeed.tech/tags/relate.md>)

### AI overview

Relate by Neo4j is an open-source embedded graph database for AI agents, offered as a library inside an application without a server or signup. Graphs can be kept in memory, a directory, or a single file; local relationship and vector lookups avoid network calls. The article highlights lightweight storage, structured JSON query results with capped rows, transactions for shared agent updates, and Rust, Python, CLI, and WebAssembly access. The month-long "Context, Connected" hackathon opens November 11 at 6 PM Pacific on Devpost and invites projects that use connected data to help agents solve concrete problems. Entries require a project description, public GitHub repository with setup instructions, and a 1-2 minute demo; working code or prompts used with Relate should be included. Judging scores six criteria equally, including usefulness, completeness, connected context, and agent capabilities. Three winners receive hardware valued at over $6,000 total; public voting separately determines a community favorite. The excerpt does not give the closing date or full rules.

### Source excerpt

Relate by Neo4j is a new open-source embedded database built for AI agents, launching at NODES 2026. To mark the launch, we're opening the Relate by Neo4j Hackathon, a month-long online event. The hackathon opens on November 11 at 6... Read more ->

## Meet Relate by Neo4j: An Embedded Database for AI Agents

DevFeed: [Meet Relate by Neo4j: An Embedded Database for AI Agents](<https://devfeed.tech/articles/meet-relate-by-neo4j-an-embedded-database-for-ai-agents-128024.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/news/meet-relate-by-neo4j-an-embedded-database-for-ai-agents/>)

Author: Kate Smith

Published: 2026-11-11T12:00:00Z

Content type: release

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [google-adk](<https://devfeed.tech/topics/google-adk.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [agent-mode](<https://devfeed.tech/tags/agent-mode.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-and-data](<https://devfeed.tech/tags/ai-and-data.md>), [app](<https://devfeed.tech/tags/app.md>), [application](<https://devfeed.tech/tags/application.md>), [audit](<https://devfeed.tech/tags/audit.md>), [aura](<https://devfeed.tech/tags/aura.md>), [bolt](<https://devfeed.tech/tags/bolt.md>), [browser](<https://devfeed.tech/tags/browser.md>), [build](<https://devfeed.tech/tags/build.md>), [claude](<https://devfeed.tech/tags/claude.md>), [context](<https://devfeed.tech/tags/context.md>), [cypher](<https://devfeed.tech/tags/cypher.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [developer](<https://devfeed.tech/tags/developer.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [news](<https://devfeed.tech/tags/news.md>), [nodes](<https://devfeed.tech/tags/nodes.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [relate](<https://devfeed.tech/tags/relate.md>)

### AI overview

Relate by Neo4j is an open-source graph database embedded in an application, CLI sandbox, or browser via WASM, avoiding a separate server. It stores connected facts and supports Cypher queries that combine graph traversal with vector and full-text search. Agents can use its installable skills or MCP endpoint; agent mode returns JSON or Toon with row limits and structured, retryable errors. Data can be ephemeral in memory or persisted transactionally to a directory or single file, backed by Parquet, JSON, or Markdown. The article describes uses including agent memory, codebase context, dependency audits, and sandbox analysis, with configurable memory and traversal limits. Relate is presented for local, single-process work; when a project outgrows that, the same Cypher can be used with Neo4j, with subgraphs exchanged with Aura and connections available over Bolt or HTTP.

### Source excerpt

Your agent works with a lot of different kinds of data: customer records, documents and tickets, plans that span sessions, records of what it did and who approved it. To be quick and reliable, an agent needs context it can... Read more ->

## Build a Knowledge Layer: Connect Your Data Sources with a Composite Database

DevFeed: [Build a Knowledge Layer: Connect Your Data Sources with a Composite Database](<https://devfeed.tech/articles/build-a-knowledge-layer-connect-your-data-sources-with-a-composite-database-127286.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/graph-database/build-a-knowledge-layer-connect-your-data-sources-with-a-composite-database/>)

Author: corydon baylor

Published: 2026-11-10T14:00:00Z

Content type: article

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [governance](<https://devfeed.tech/tags/governance.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [graph-databases](<https://devfeed.tech/tags/graph-databases.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [knowledge-layer](<https://devfeed.tech/tags/knowledge-layer.md>), [link](<https://devfeed.tech/tags/link.md>), [links](<https://devfeed.tech/tags/links.md>)

### AI overview

A composite database gives an AI agent one connection to multiple graphs while routing each query to a named constituent with a `USE` clause. In the Nordtell Bank demo, it brings together a virtual graph over banking systems, a business-plan document graph, lending policy, an ontology, and decision history; the graphs remain separately owned, governed, and stored without copying their source records. Cross-graph relationships cannot be written into the source constituents, so a separate writable shadow database stores links between them. Its lightweight `:Shadow` nodes keep source graph and ID references plus identity properties, leaving full records and source graphs unchanged.

### Source excerpt

In this series 1. Give Your AI Agents the Shared Context to Succeed 2. Map Your Data with an Ontology 3. Turn Your Existing Data into Context 4. Connect Your Data Sources with a Composite Database 5. Ground Decisions in... Read more ->

## Build a Knowledge Layer: Map Your Data with an Ontology

DevFeed: [Build a Knowledge Layer: Map Your Data with an Ontology](<https://devfeed.tech/articles/build-a-knowledge-layer-map-your-data-with-an-ontology-127287.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/graph-database/build-a-knowledge-layer-map-your-data-with-an-ontology/>)

Author: corydon baylor

Published: 2026-11-10T14:00:00Z

Content type: article

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [data](<https://devfeed.tech/topics/data.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [build](<https://devfeed.tech/tags/build.md>), [context](<https://devfeed.tech/tags/context.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [knowledge-layer](<https://devfeed.tech/tags/knowledge-layer.md>), [map](<https://devfeed.tech/tags/map.md>), [ontology](<https://devfeed.tech/tags/ontology.md>), [sources](<https://devfeed.tech/tags/sources.md>)

### AI overview

An ontology gives an AI agent a map of multiple data sources so it can locate information and understand how sources relate before querying. The example uses generic `DataProduct` and `SchemaEntity` nodes, with `RELATES` storing source-specific relationship names as properties; four links describe source roles: `RESOLVES`, `SUPPLEMENTS`, `GOVERNS` and `CITES`. Agents first call `get_schema_help` to inspect the map and confirmed labels, then `ontology_guided_query` to run a guarded, read-only query. The approach keeps source details out of repeated prompts, which the article says can grow large, become stale and consume tokens. For larger-scale ontology management, it describes Neo4j Context Engine as in private preview, with a six-layer business ontology managed through Context Studio.

### Source excerpt

In this series 1. Give Your AI Agents the Shared Context to Succeed 2. Map Your Data with an Ontology 3. Turn Your Existing Data into Context 4. Connect Your Data Sources with a Composite Database 5. Ground Decisions in... Read more ->

## Build a Knowledge Layer: Ground Decisions in Precedent

DevFeed: [Build a Knowledge Layer: Ground Decisions in Precedent](<https://devfeed.tech/articles/build-a-knowledge-layer-ground-decisions-in-precedent-127284.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/agentic-ai/build-a-knowledge-layer-ground-decisions-in-precedent/>)

Author: corydon baylor

Published: 2026-11-10T14:00:00Z

Content type: article

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [approach](<https://devfeed.tech/tags/approach.md>), [auradb](<https://devfeed.tech/tags/auradb.md>), [build](<https://devfeed.tech/tags/build.md>), [connect](<https://devfeed.tech/tags/connect.md>), [context](<https://devfeed.tech/tags/context.md>), [context-graph](<https://devfeed.tech/tags/context-graph.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [existing](<https://devfeed.tech/tags/existing.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [knowledge-layer](<https://devfeed.tech/tags/knowledge-layer.md>), [layer](<https://devfeed.tech/tags/layer.md>), [more](<https://devfeed.tech/tags/more.md>), [series](<https://devfeed.tech/tags/series.md>), [sources](<https://devfeed.tech/tags/sources.md>), [this](<https://devfeed.tech/tags/this.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

A context graph gives a loan-decision agent persistent memory of prior decisions and their reasons, so it can retrieve precedent before making a new recommendation and record its own decision afterward. The example stores each decision with links to the customer, applied policy rules, and any escalation; because the composite database does not allow relationships between its constituents, the context graph keeps simplified copies and uses shared rule IDs to connect decisions to policy rules. Precedent is defined deterministically as an earlier decision that failed the same rule, retrieved with a query over the applicant's failed rule IDs. The post contrasts this with asking a model to assess the whole history, which it says grows slower and less predictably, and embedding or graph-similarity matching, whose results depend on the scoring method. In the Rosa's Bakery example, other graphs supply applicant facts and the lending policy supplies rules; two matching prior cases inform a recommendation to decline. The excerpt describes this approach but does not establish broader performance or fairness outcomes.

### Source excerpt

In this series 1. Give Your AI Agents the Shared Context to Succeed 2. Map Your Data with an Ontology 3. Turn Your Existing Data into Context 4. Connect Your Data Sources with a Composite Database 5. Ground Decisions in... Read more ->

## Agentic GraphRAG and an explorer for your own stack

DevFeed: [Agentic GraphRAG and an explorer for your own stack](<https://devfeed.tech/articles/agentic-graphrag-and-an-explorer-for-your-own-stack-123940.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/developer/agentic-graphrag-and-an-explorer-for-your-own-stack/>)

Author: Jocelyn Hoppa

Published: 2026-11-09T08:39:50Z

Content type: article

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [api](<https://devfeed.tech/tags/api.md>), [developer](<https://devfeed.tech/tags/developer.md>), [document-intelligence](<https://devfeed.tech/tags/document-intelligence.md>), [explorer](<https://devfeed.tech/tags/explorer.md>), [getting-started](<https://devfeed.tech/tags/getting-started.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>)

### AI overview

The article presents graph-explorer-kit, a Neo4j GraphRAG library and browser explorer that turns a Document Intelligence graph into an API-backed agent experience. In a UFO-records example, files become provenance-linked chunks, entities and relationships; the larger corpus yielded 54,044 records, 58,429 relationships and 24,971 passages. A ProjectSpec defines domain schema and retrieval guidance, while the kit offers retriever, agent-tool and HTTP API integrations. Its agent can combine hybrid document search, Cypher graph queries, entity lookup and graph overview to answer questions that span multiple records; Cypher writes are rejected. The kit supports Microsoft Foundry or OpenAI, and embedding dimensions must match the configured model. Adoption adds its own chunk label, embeddings and readable source names; dry-run previews changes and undo removes them. The explorer displays retrieved passages, extracted entities and neighboring graph context. The author cautions that this neighboring context is a separate lookup, scans can be noisy, and redacted witnesses are not merged.

### Source excerpt

What got me building this was a pattern I kept noticing. People start out not knowing how to build a knowledge graph. The Document Intelligence feature solves that: you point it at your files and get a graph inside Neo4j... Read more ->

## The Neo4j Ontology Graph Specification: A pragmatic, open, AI-first approach

DevFeed: [The Neo4j Ontology Graph Specification: A pragmatic, open, AI-first approach](<https://devfeed.tech/articles/the-neo4j-ontology-graph-specification-a-pragmatic-open-ai-first-approach-119746.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/developer/the-neo4j-ontology-graph-specification-a-pragmatic-open-ai-first-approach/>)

Author: john stegeman

Published: 2026-11-05T19:57:17Z

Content type: release

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [RDF (Resource Description Framework)](<https://devfeed.tech/topics/rdf.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-native](<https://devfeed.tech/tags/ai-native.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [applications](<https://devfeed.tech/tags/applications.md>), [automation](<https://devfeed.tech/tags/automation.md>), [data](<https://devfeed.tech/tags/data.md>), [developer](<https://devfeed.tech/tags/developer.md>), [domain](<https://devfeed.tech/tags/domain.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [interoperability](<https://devfeed.tech/tags/interoperability.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [ontologies](<https://devfeed.tech/tags/ontologies.md>), [ontology](<https://devfeed.tech/tags/ontology.md>), [open](<https://devfeed.tech/tags/open.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [source](<https://devfeed.tech/tags/source.md>), [specification](<https://devfeed.tech/tags/specification.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

The Neo4j Ontology Graph Specification is an open-source, versioned JSON or YAML format for expressing graph domain knowledge so databases, applications, and AI agents can use a shared model. It captures nodes, relationships, Neo4j properties, cardinality, constraints, references to external definitions, and named extensions for indexes and data-source mappings. Descriptions, aliases, and implied labels add context beyond a schema's structural labels. The same ontology can support database constraints, data enrichment, and application or agent interpretation. Published JSON Schema enables structural validation, while built-in validators check Neo4j creation and data-source mappings; JVM, JavaScript/TypeScript, and Go SDKs are available. The specification documents mappings to selected RDFS and SHACL constructs and links elements to external terms, but does not define an RDF-based serialization. The excerpt presents it as a complementary graph-oriented format for broader application and AI uses.

### Source excerpt

We're announcing the Neo4j Ontology Graph Specification, an open-source specification for representing domain knowledge in a machine-readable form that enables interoperability and automation across data, applications, and AI systems. Ontologies are critical components of AI systems and enterprise applications, and... Read more ->

## Build Custom Graph Visualizations with Neo4j NVL

DevFeed: [Build Custom Graph Visualizations with Neo4j NVL](<https://devfeed.tech/articles/build-custom-graph-visualizations-with-neo4j-nvl-119747.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/graph-database/neo4j-graph-visualization-library/>)

Author: michael worthington

Published: 2026-11-03T23:13:03Z

Content type: article

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [UI/UX Design](<https://devfeed.tech/topics/ui-ux-design.md>)

Tags: [applications](<https://devfeed.tech/tags/applications.md>), [auradb](<https://devfeed.tech/tags/auradb.md>), [cloud-database](<https://devfeed.tech/tags/cloud-database.md>), [custom](<https://devfeed.tech/tags/custom.md>), [developers](<https://devfeed.tech/tags/developers.md>), [flexible](<https://devfeed.tech/tags/flexible.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [graph-visualization](<https://devfeed.tech/tags/graph-visualization.md>), [interactive](<https://devfeed.tech/tags/interactive.md>), [library](<https://devfeed.tech/tags/library.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [visualization](<https://devfeed.tech/tags/visualization.md>), [visualizing-graphs](<https://devfeed.tech/tags/visualizing-graphs.md>)

### AI overview

Neo4j NVL separates graph rendering from interaction so applications can define workflows without a fixed interaction model. The @neo4j-nvl/base package provides the visualization foundation; its .getHits method adds information about graph elements beneath a pointer event, which the host application can use to update its UI and NVL state. Developers who want conventional graph interactions can add @neo4j-nvl/interaction-handlers. React wrappers are available in @neo4j-nvl/react, and a Design System component provides UI elements such as tooltips and legends. The excerpt says NVL is free to use with a Neo4j license and points to boilerplates, API documentation, and examples. It describes use across Neo4j products, including Query, Python Graph Visualization, Importer, and Bloom.

### Source excerpt

Build custom, interactive graph experiences with the Neo4j Graph Visualization Library, a flexible foundation that lets developers define the interactions their applications need.

## Seamless graph intelligence for your Snowflake data estate: The Neo4j and Snowflake partnership

DevFeed: [Seamless graph intelligence for your Snowflake data estate: The Neo4j and Snowflake partnership](<https://devfeed.tech/articles/seamless-graph-intelligence-for-your-snowflake-data-estate-the-neo4j-and-snowflake-partnership-117135.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/knowledge-graph/graph-intelligence-for-your-snowflake-data-estate/>)

Author: Keaton Crowe

Published: 2026-11-03T16:41:24Z

Content type: article

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [CRUD](<https://devfeed.tech/topics/crud.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [data](<https://devfeed.tech/tags/data.md>), [data-warehouse](<https://devfeed.tech/tags/data-warehouse.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [fail](<https://devfeed.tech/tags/fail.md>), [genai](<https://devfeed.tech/tags/genai.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [intelligence](<https://devfeed.tech/tags/intelligence.md>), [it](<https://devfeed.tech/tags/it.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [language](<https://devfeed.tech/tags/language.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large](<https://devfeed.tech/tags/large.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [like](<https://devfeed.tech/tags/like.md>), [llms](<https://devfeed.tech/tags/llms.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [partnership](<https://devfeed.tech/tags/partnership.md>), [snowflake](<https://devfeed.tech/tags/snowflake.md>)

### AI overview

Neo4j and Snowflake offer three ways to add graph capabilities to a Snowflake data estate. Virtual Graph (in Public Preview) models Snowflake data in place, translates Cypher queries into SQL pushed to Snowflake, and returns results as a graph without moving data; it uses existing governance and supports AI-assisted schema design and natural-language query translation. Graph Analytics for Snowflake, available in the Snowflake Marketplace, uses SQL and elastic compute to create in-memory graphs, run more than 65 algorithms, write results to Snowflake tables, and shut down when finished; charges are based on consumed resources. For workloads needing millisecond latency, transactional CRUD, ACID compliance, or queries across data sources, the text recommends a native Neo4j database such as AuraDB, with Snowflake data import for selected subgraphs. The source reports Audience Acuity cut identity-resolution processing across 2B+ signals from weeks to under 24 hours using Graph Analytics.

### Source excerpt

Modern data warehouse providers like Snowflake deliver a consolidated platform for an organization's data and AI ecosystem. Large Language Models (LLMs) offer extraordinary evolutionary capabilities in human-to-IT interactions. Yet traditional analytics and vector searches alone often fail to uncover the... Read more ->

## Unmasking fraud networks: How graph-grounded Copilots stop P2P fraud in Microsoft Fabric

DevFeed: [Unmasking fraud networks: How graph-grounded Copilots stop P2P fraud in Microsoft Fabric](<https://devfeed.tech/articles/unmasking-fraud-networks-how-graph-grounded-copilots-stop-p2p-fraud-in-microsoft-fabric-108431.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/graph-database/unmasking-fraud-neo4j-in-microsoft-fabric/>)

Author: Keaton Crowe

Published: 2026-10-30T15:43:30Z

Content type: article

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [multi-accounting fraud](<https://devfeed.tech/topics/multi-accounting-fraud.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>), [Purview](<https://devfeed.tech/topics/purview.md>), [Azure](<https://devfeed.tech/topics/azure.md>), [Microsoft](<https://devfeed.tech/topics/microsoft.md>)

Tags: [account](<https://devfeed.tech/tags/account.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [azure](<https://devfeed.tech/tags/azure.md>), [banks](<https://devfeed.tech/tags/banks.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [device](<https://devfeed.tech/tags/device.md>), [fabric](<https://devfeed.tech/tags/fabric.md>), [financial-services](<https://devfeed.tech/tags/financial-services.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [fraud-detection](<https://devfeed.tech/tags/fraud-detection.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [ip](<https://devfeed.tech/tags/ip.md>), [microsoft-fabric](<https://devfeed.tech/tags/microsoft-fabric.md>), [networks](<https://devfeed.tech/tags/networks.md>), [p2p](<https://devfeed.tech/tags/p2p.md>), [transactions](<https://devfeed.tech/tags/transactions.md>)

### AI overview

The excerpt describes a Microsoft Fabric and Neo4j approach to P2P fraud investigations: OneLake consolidates data in Delta tables, Neo4j turns those tables into property graphs, and graph algorithms help distinguish strong links from noisy shared infrastructure. Relational joins can treat a shared private card and a public Wi-Fi IP alike, creating many false leads. Neo4j can filter high-traffic hubs, focus on rare identifiers and payment paths, and use Graph Data Science algorithms such as Weakly Connected Components to group strongly connected accounts. In the example, accounts A-102, A-104, A-106, and A-107 are grouped with fraudulent A-101, while A-103 is excluded based only on shared coffee shop Wi-Fi. The resulting graph metrics can be written to OneLake for Fabric Data Agents and Copilots to query with network context. The excerpt also names Fabric governance features and describes enabling Neo4j through the Workload Hub or Azure Marketplace.

### Source excerpt

Every second, financial networks log millions of data points across disconnected internal systems: debit transactions, peer-to-peer (P2P) transfers, device fingerprints, phone numbers, and IP addresses. But when organized crime rings strike, standard relational databases hit a wall trying to trace... Read more ->

## Cloudera expands its AI ecosystem with partnerships and packaged blueprints

DevFeed: [Cloudera expands its AI ecosystem with partnerships and packaged blueprints](<https://devfeed.tech/articles/cloudera-expands-its-ai-ecosystem-with-partnerships-and-packaged-blueprints-105438.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/28/cloudera-expands-its-ai-ecosystem-with-partnerships-and-packaged-blueprints/>)

Author: Paul Gillin

Published: 2026-10-28T19:21:09Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [digital sovereignty](<https://devfeed.tech/topics/digital-sovereignty.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [NVIDIA NIM](<https://devfeed.tech/topics/nvidia-nim.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-applications](<https://devfeed.tech/tags/ai-applications.md>), [ai-projects](<https://devfeed.tech/tags/ai-projects.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [blueprints](<https://devfeed.tech/tags/blueprints.md>), [cloudera](<https://devfeed.tech/tags/cloudera.md>), [cloudera-ai](<https://devfeed.tech/tags/cloudera-ai.md>), [cloudera-ai-anywhere](<https://devfeed.tech/tags/cloudera-ai-anywhere.md>), [cloudera-anywhere-cloud](<https://devfeed.tech/tags/cloudera-anywhere-cloud.md>), [cloudera-blueprints](<https://devfeed.tech/tags/cloudera-blueprints.md>), [cloudera-enterprise-ai-ecosystem](<https://devfeed.tech/tags/cloudera-enterprise-ai-ecosystem.md>), [cloudera-inc](<https://devfeed.tech/tags/cloudera-inc.md>), [control](<https://devfeed.tech/tags/control.md>), [costs](<https://devfeed.tech/tags/costs.md>), [data](<https://devfeed.tech/tags/data.md>), [data-infrastructure](<https://devfeed.tech/tags/data-infrastructure.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprises](<https://devfeed.tech/tags/enterprises.md>), [inc](<https://devfeed.tech/tags/inc.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [mistral](<https://devfeed.tech/tags/mistral.md>), [mistral-ai-sas](<https://devfeed.tech/tags/mistral-ai-sas.md>), [neo4j-inc](<https://devfeed.tech/tags/neo4j-inc.md>), [news](<https://devfeed.tech/tags/news.md>), [nvidia-corp](<https://devfeed.tech/tags/nvidia-corp.md>), [partnerships](<https://devfeed.tech/tags/partnerships.md>), [sovereign-ai](<https://devfeed.tech/tags/sovereign-ai.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>)

### AI overview

Cloudera announced ready-to-deploy AI Blueprints built with Nvidia workflows and Cloudera's data management, security, and governance capabilities, aiming to reduce integration work between pilots and production. Initial packages target financial transaction analysis, clinical documentation, telecom network configuration, and synthetic video detection, and use Nvidia NIM microservices, Nemotron models, and GPU-accelerated processing. Cloudera also expanded partnerships with Neo4j, Mistral AI, and Vast Data: Neo4j graphs add relationship context for AI agents, while Mistral models can be deployed locally and customized with enterprise data. Cloudera says customers can run workloads across public or private clouds, on-premises, and edge environments to retain control of data, models, infrastructure, and costs. The article notes that sovereign AI involves model execution, data lineage, infrastructure, and operations as well as data location, and that organizations can choose deployment models suited to each workload.

### Source excerpt

Cloudera Inc. has announced an expansion of its enterprise artificial intelligence ecosystem, introducing preconfigured AI applications built with Nvidia Corp. technology and expanding partnerships with Neo4j Inc. and Mistral AI SAS. Cloudera said the initiatives are intended to help enterprises move AI projects into production while maintaining control over their data, infrastructure and deployment costs. [...] The post Cloudera expands its AI ecosystem with partnerships and packaged blueprints appeared first on SiliconANGLE.

## Finding the Ultimate Beneficial Owner in a Pile of KYC Documents with Document Intelligence

DevFeed: [Finding the Ultimate Beneficial Owner in a Pile of KYC Documents with Document Intelligence](<https://devfeed.tech/articles/finding-the-ultimate-beneficial-owner-in-a-pile-of-kyc-documents-with-document-intelligence-95718.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/graph-database/finding-the-ultimate-beneficial-owner-in-a-pile-of-kyc-documents-with-document-intelligence/>)

Author: corydon baylor

Published: 2026-10-22T12:48:00Z

Content type: tutorial

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [aura-graph-analytics](<https://devfeed.tech/tags/aura-graph-analytics.md>), [auradb](<https://devfeed.tech/tags/auradb.md>), [community-detection](<https://devfeed.tech/tags/community-detection.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [cypher](<https://devfeed.tech/tags/cypher.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [intelligence](<https://devfeed.tech/tags/intelligence.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [kyc](<https://devfeed.tech/tags/kyc.md>)

### AI overview

A knowledge graph built from 20 KYC documents reveals Dorian Voss as a likely undisclosed ultimate beneficial owner of Anchor Point Partners LLC, despite the loan application describing him only as a guarantor. A Cypher traversal finds two ownership paths: Voss -> Vantage Point Estates -> Anchor Point, and Voss -> Meridian Holdings -> Northgate Ventures -> Cobalt Trading -> Anchor Point. Meridian, Northgate, and Cobalt also form a closed ownership loop. Louvain community detection, applied to a projected graph containing OWNS and OFFICER_OF links in both directions, separates Voss's personal holding chain from the loop's tighter corporate core. The walkthrough uses Neo4j Aura, Aura Graph Analytics, Python 3.10 or newer, and notebooks; analytics run in a temporary billed session that the example explicitly deletes. Document Intelligence uses an LLM, so its generated graph is nondeterministic; restoring the provided backup reproduces the tutorial's graph.

### Source excerpt

With Document Intelligence, you can build a knowledge graph from your existing documents, including plain text files, PDFs, and Microsoft Word files, without writing a single line of code. Documents that previously sat unused and unqueried can now be searched... Read more ->

## Bringing Neo4j into Laravel

DevFeed: [Bringing Neo4j into Laravel](<https://devfeed.tech/articles/bringing-neo4j-into-laravel-95717.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/developer/bringing-neo4j-into-laravel/>)

Author: Jocelyn Hoppa

Published: 2026-10-22T08:14:00Z

Content type: article

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Laravel](<https://devfeed.tech/topics/laravel.md>), [Eloquent ORM](<https://devfeed.tech/topics/eloquent.md>)

Tags: [database](<https://devfeed.tech/tags/database.md>), [developer](<https://devfeed.tech/tags/developer.md>), [eloquent](<https://devfeed.tech/tags/eloquent.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [laravel](<https://devfeed.tech/tags/laravel.md>), [laravel-eloquent](<https://devfeed.tech/tags/laravel-eloquent.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [php](<https://devfeed.tech/tags/php.md>), [query](<https://devfeed.tech/tags/query.md>)

### AI overview

Neo4j Laravel lets Laravel applications use Neo4j alongside relational databases through a named Laravel database connection, parameterized Cypher queries, the Query Builder, and Eloquent-style models. It supports graph relationship queries and model operations such as lazy and eager loading, attaching, syncing, and detaching, plus transactions, pagination, soft deletes on supported models, query logging, and optional Laravel Debugbar integration. The article presents Neo4j as a secondary connection for relationship-heavy data while MySQL, PostgreSQL, or SQLite handle conventional records. It cautions that using Neo4j as the default connection may limit Laravel features that rely on conventional database behavior and Eloquent authentication, so the documented constraints should be reviewed before choosing an architecture.

### Source excerpt

Graph Database Power Without Leaving the Laravel Ecosystem Laravel developers are used to working with Eloquent, the Query Builder, database connections, and familiar application patterns. But what happens when the data your application needs is not just about records, but... Read more ->

## Neo4j Context Engine Gives AI Agents a Shared Knowledge Layer, 6-Layer Business Ontology, and Graph-Native Memory

DevFeed: [Neo4j Context Engine Gives AI Agents a Shared Knowledge Layer, 6-Layer Business Ontology, and Graph-Native Memory](<https://devfeed.tech/articles/neo4j-context-engine-gives-ai-agents-a-shared-knowledge-layer-6-layer-business-ontology-and-graph-native-memory-90572.md>)

Original publisher: [Read original article](<https://www.storagereview.com/news/neo4j-context-engine-ai-agents-knowledge-layer-ontology-graph-native-memory>)

Author: Harold Fritts

Published: 2026-10-20T07:00:00Z

Content type: news

Language: en

Sources: [StorageReview.com](<https://devfeed.tech/sources/storagereview-com.md>)

Topics: [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [stack-internal](<https://devfeed.tech/topics/stack-internal.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-orchestration](<https://devfeed.tech/tags/ai-orchestration.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [applications](<https://devfeed.tech/tags/applications.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [business-logic](<https://devfeed.tech/tags/business-logic.md>), [data-platforms](<https://devfeed.tech/tags/data-platforms.md>), [databases](<https://devfeed.tech/tags/databases.md>), [developer](<https://devfeed.tech/tags/developer.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [knowledge-layer](<https://devfeed.tech/tags/knowledge-layer.md>), [layer](<https://devfeed.tech/tags/layer.md>), [memory](<https://devfeed.tech/tags/memory.md>), [native](<https://devfeed.tech/tags/native.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [ontology](<https://devfeed.tech/tags/ontology.md>), [product](<https://devfeed.tech/tags/product.md>)

### AI overview

Neo4j announced the Context Engine, which provides AI agents with a shared knowledge layer for reasoning over enterprise data. Its six-layer ontology links data sources, business logic, and AI assets, while Context Studio provides governance and tooling. Context Memory stores structured agent memory and uses graph algorithms to turn recurring interactions into reusable knowledge.

### Source excerpt

Neo4j announced the Neo4j Context Engine today, a product built to give AI agents a shared, reusable knowledge layer for reasoning over enterprise data. The problem it targets is one most agent deployments hit early: an agent does not know what "customer," "account," "supplier," or "risk" means inside a particular company, because that meaning is The post Neo4j Context Engine Gives AI Agents a Shared Knowledge Layer, 6-Layer Business Ontology, and Graph-Native Memory appeared first on StorageReview.com.

## Neo4j Context Engine: Rapidly build dependable enterprise agents

DevFeed: [Neo4j Context Engine: Rapidly build dependable enterprise agents](<https://devfeed.tech/articles/neo4j-context-engine-rapidly-build-dependable-enterprise-agents-90570.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/news/neo4j-context-engine/>)

Author: Alyssa Di Pasqualucci

Published: 2026-10-20T06:50:00Z

Content type: release

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [context](<https://devfeed.tech/topics/context.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [data](<https://devfeed.tech/tags/data.md>), [governance](<https://devfeed.tech/tags/governance.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [news](<https://devfeed.tech/tags/news.md>)

### AI overview

Neo4j announces Context Engine, a private-preview offering designed to help enterprise AI agents use business concepts, processes, policies, and data with governance and explainability. It combines a graph-based business ontology, access to enterprise information using GraphRAG, and memory and learning capabilities to support agent reasoning and actions.

### Source excerpt

Today we're announcing Neo4j Context Engine, which enables AI agents to accurately answer questions about your business and reliably execute its processes, with every answer and step governed and explainable. Neo4j Context Engine, part of the Neo4j Graph Intelligence Platform,... Read more ->

[Next page](<https://devfeed.tech/topics/neo4j.md?cursor=WyIyMDI2LTEwLTIwVDA2OjUwOjAwKzAwOjAwIiwgIjlkODg4NTE3LWEwZjgtNGE5NS05MDlhLTc5MDkzMzdiZjUyMSJd>)