GraphNews

Learn how context graphs capture decision reasoning and situational awareness to power AI agents with episodic memory. Build production-ready context graphs with FalkorDB.

KuzuDB was archived in October 2025. Vela Partners forked it with concurrent write support for multi-agent workloads. Benchmarks show 374x faster path queries than Neo4j. Full architecture guide for AI agent memory on graph databases.

Neo4j databases are famous for being schema-optional and developers love the flexibility this gives them to get up and running fast. But eventually, it’s time to go to production… and you need rules. You need structure. You need to enforce… Read more →

Table of Contents

Bridging Wikidata, MeSH, and DO in a Unified Knowledge Graph

CosmosAIGraph implementation of OmniRAG pattern. Contribute to AzureCosmosDB/CosmosAIGraph development by creating an account on GitHub.

Introducing SurrealDB 3.0 - the future of AI agent memory

𝗧𝗵𝗲𝗿𝗲'𝘀 𝗻𝗼 𝘄𝗮𝘆 𝘁𝗼 𝘃𝗮𝗹𝗶𝗱𝗮𝘁𝗲 𝗮 𝗚𝗤𝗟 𝗾𝘂𝗲𝗿𝘆 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝘀𝗲𝗻𝗱𝗶𝗻𝗴 𝗶𝘁 𝘁𝗼 𝗮 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲.

When and How to Implement Text2Cypher in Agentic Applications Courtesy of Microsoft Designer Introduction In this article, we’ll discuss the process of generating database queries from natural language with LLMs, as well as some of the challenges that come along… Read more →

How relational-era ORM patterns quietly sabotage graph-powered apps — and what to use instead

SurrealDB Raises $23M Series A extension to power the AI-native database era

A practical walkthrough using a real-world Diabetes Patient Risk Stratification system built with LangGraph, Neo4j, PostgreSQL, OWL…

𝗪𝗵𝘆 𝗗𝗴𝗿𝗮𝗽𝗵 ‘𝗙𝗮𝗶𝗹𝗲𝗱’ 𝗮𝘀 𝗮 𝗕𝘂𝘀𝗶𝗻𝗲𝘀𝘀 (𝗕𝘂𝘁 𝗜𝘁𝘀 𝗩𝗮𝗹𝘂𝗲 𝗝𝘂𝘀𝘁 𝗚𝗼𝘁 𝗕𝗶𝗴𝗴𝗲𝗿)

A Practical Guide to Transforming Relational Data into Semantic Knowledge Graphs

SELECT * FROM database_startups WHERE mosaic_change 0; That query returns a surprisingly small result set as mosaic score changes show a dual-track market for next-gen databases: momentum is concentrating in a handful of companies. Like cloud infrastructure before it, databases are moving from broad experimentation to standardization around a few critical workloads. As that happens, the market becomes far less forgiving. Three things separating leaders from laggards: 1) Leaders are tied to expanding workloads Positive Mosaic movement is concentrated in companies aligned with where spend is actually growing: ↳ real-time analytics in production ↳ AI-adjacent workloads (RAG, GraphRAG, observability, agent workflows) ↳ managed, consumption-based deployment as the default 2) Leaders win workflows, not benchmarks Performance is table stakes. The real separation comes from owning: ↳ developer onboarding and time-to-production ↳ day-2 operations and observability ↳ enterprise decisioning and mission-critical systems 3) Commercial execution is the moat Momentum correlates with repeatable enterprise sales, security and compliance at scale, and partner-driven distribution. Strong technology without scalable commercialization shows up directly as negative Mosaic drift. Where the leaders are finding success: → ClickHouse (+24) Momentum is driven by rapid funding velocity, enterprise customer expansion, aggressive hiring, and platform expansion into observability and LLM monitoring tied to AI production use cases. → Supabase (+85) Large Mosaic gains reflect explosive developer growth (4M+ users), rising AI workload adoption, and early enterprise traction as Supabase expands beyond developer tooling into production infrastructure. → Starburst (+35) Gains are anchored in durable enterprise signals: deep penetration in regulated industries, strong partner leverage, and renewed demand for federated analytics amid data-residency constraints. → Neo4j (+17) Momentum reflects scale and defensibility: $200M ARR, 84% Fortune 100 penetration, and accelerating GraphRAG adoption, contributing to one of the highest IPO probabilities we track. → Cockroach Labs (+4) While not a breakout mover, stable Mosaic performance signals resilience via enterprise renewals, IBM OEM distribution, and positioning around AI-era uptime and global scale requirements. Bottom line: momentum belongs to companies winning workflows and distribution, not feature comparisons. Over the next 6–12 months, leaders become magnets for platform partnerships and M&A, while others are pushed into defensive consolidation or niche competition. P.S. Comment "SELECT * FROM cb_insights;" for free access to CB Insights’ predictive intelligence on the companies in next-gen database markets. | 79 comments on LinkedIn

Geospatial data analysis systems are currently very relevant. Most such systems use either relational databases or graph databases. This paper presents the idea of using both approaches, taking into account the main features and advantages of each. A concrete example of a city transport network is used to experimentally examine the use of this hybrid approach. A special ETL procedure was developed to transform data from the corresponding graph database to a relational one, as well as the reverse process from the relational to the graph database. The results show which type of queries are better suited for relational databases, and which for graph databases. Additionally, for certain specific queries and applications, neither database type is capable of providing any results. Although this kind of hybrid architecture has issues with data duplication, the performance gains achieved are significant, making this approach highly efficient.

From Property Graphs to OWL Inference Using a Hybrid Pipeline

Here is a very simple example of graph with AGE PostgreSQL extension. In this example, we will assume we are trying to match a donor who can potentially donate to a patient based on the matching blood group.

2025 was a big year for Spanner on Google Cloud, with new capabilities to help it evolve from a passive data repository to an intelligent context hub.

Discover some of the best technical talks and videos from the NODES 2025 online conference organized by Neo4j and curated by Christian Miles from G.V().

Discover how 2025 marked Neo4j's evolution from a graph database and analytics leader into the world’s premier graph intelligence platform.

A framework for transforming tabular (CSV, SQL) and hierarchical data (JSON, XML) into property graphs and ingesting them into graph databases (ArangoDB, Neo4j, TigerGraph). Features automatic PostgreSQL schema inference.

[I’m thrilled to announce that the source code for neo4j-gspatial is finally open-source!

Why RDF stores don’t overwrite values on import — and what to do instead

Following the acquisition of Vodafone Italy by Swisscom, these European telco leaders saw an opportunity to rethink how they serve customers.

Graph Databases for RAG + How to choose