CommonThread AI CEO Tim Gosnell said graph databases are the natural foundation for enterprise AI because they connect fragmented data and its relationships, enabling trusted data pipelines that deliv…
Neo4j chief technology officer Philip Rathle said enterprises are converging on an enterprise knowledge layer architecture that grounds large language models in trustworthy data, moving beyond early g…
AgentHound, an open-source offensive security framework for AI agent infrastructure, has been released. The tool performs recon, fingerprinting, credential looting, model inversion, and persistence ac…
A developer advocates for self-hosting ArangoDB, a multi-model database that natively supports graph, document, and vector search with a single query language (AQL), eliminating the need to duct-tape …
A debate over whether AI agents should be built with simple loops or structured graphs has resurfaced, fueled by DeepLearning.AI's free Agentic Knowledge Graph Construction course. The course, taught …
AgentMemory for .NET, a native .NET implementation of Neo4j's graph-native agent memory model, has been released by independent developer José L. Latorre and verified 178 out of 178 against Neo4j's Te…
Neo4j's Enterprise Knowledge Layer proposes a shared, governed graph substrate to fix enterprise AI failures caused by scattered business context across agents, according to Jesús Barrasa. A benchmark…
Neo4j says graph technology can reduce AI hallucinations, citing a June arXiv paper showing that vector+graph RAG achieved 80% higher fine-grained truthfulness and more than double the precision and r…
An independent study by the UK's National Innovation Centre for Data (NICD) found that GraphRAG, a combination of vector and graph retrieval-augmented generation, makes AI agents 80% more truthful tha…
Neo4j acquired GraphAware, an intelligence analysis software company for government agencies, to compete with Palantir Gotham with its GraphAware Hume platform, according to Neo4j founder and CEO Emil…
Veracium, a provenance-aware memory plug-in for agentic systems, launches to resist injection and confabulation failures in naive agent memory by storing third-party claims as structurally quarantined…
Public sector AI systems fail on high-consequence workforce questions because they lack a knowledge layer that connects fragmented data, according to Neo4j's Global Head of Public Sector & Workforce I…
Hikari Systems released Slater v0.24.1, a low-memory graph database designed for read-heavy graphs that can serve hundreds of millions of nodes and billions of edges from a few hundred MB of RAM by pa…
Neo4j announced MCP for Aura, a hosted Model Context Protocol server included at no additional cost on Free, Professional, and Business Critical tiers of its Aura graph database service, with Virtual …
Neo4j has released Laravel Boost, an open-source package that integrates the official Neo4j MCP server into Laravel Boost, giving AI coding assistants live access to a Neo4j graph database and applica…
AI agents make decisions through a five-stage loop — understanding the goal, gathering context, deciding, acting, and learning — and failures typically begin when agents retrieve incomplete or disconn…
Enterprise AI fails not because of models or scaffolding but because agents lack the implicit business semantics that applications and humans supply themselves, according to Neo4j. The company propose…
A developer introduced graphwiki, a variant of Karpathy's LLM Wiki pattern that stores the maintained knowledge layer as a property graph in Neo4j instead of markdown pages. The design uses typed rela…
Netflix is overhauling search and discoverability using large language models, with generative AI workflows used in roughly 300 of its titles, co-CEO Ted Sarandos said on a July 16 Q2 call. The compan…
A developer who reverse-engineered Cognee, Graphiti, and Neo4j's agent-memory tools found they all rely on heavy knowledge-graph designs with ontologies, LLM extraction pipelines, and deduplication, w…