Content

AI, XR, DevOps, graph theory, knowledge graphs, and digital sovereignty. Deep dives, tutorials, and analysis from across the GraphWiz knowledge base.

All224 AI123 Graphs67 GraphRAG5 Knowledge Graphs6 Visualization1 Algorithms2 Security10 GNN1 LLMs & Graphs2 Agentic AI3

Graphs →AI →

August 3, 2026· ~4 min read

Multimodal Knowledge Graphs: When the Graph Learns to See and Hear

Multimodal knowledge graphs add images, audio, 3D and spatiotemporal structure: construction, MLLM-guided completion, multimodal GraphRAG, and benchmarks.

multimodalknowledge-graphsmultimodal-ragmmkg+2 more

August 2, 2026· ~4 min read

The GQL Era: Query Languages for Property Graphs in 2026

Graph query languages are the fastest-growing — and thinnest — research cell: the 2026 GQL wave, NL2GQL, expressive power, query layer as product surface.

gqlcypher

← Previous 1...12 13 14...38 Next →

graph-query-languages

property-graphs

+3 more

August 1, 2026· ~14 min read

Sovereign AI on Your Desk: Why Two DGX Sparks Beat the Cloud

Two NVIDIA DGX Sparks, a bonded 400 Gbps interconnect, and DeepSeek-V4-Flash on-premises — a complete look at sovereign AI inference in 2026.

dgx-sparksovereign-aideepseekvllm+4 more

August 1, 2026· ~5 min read

Graph-Powered OSINT: From Data to Investigation with Agentic AI

Open-source intelligence has always been a graph problem: entities, relationships, provenance. The 2026 shift is that generative and agentic AI can do the investigation part too. This article reviews the emerging OSINT+graph research: entity resolution, temporal threat intelligence, agentic collection, and the hallucination risk that makes graphs essential.

osintthreat-intelligencegraph-securitycyber-investigations+3 more

July 30, 2026· ~5 min read

AgentMemory for .NET: Using Neo4j Knowledge Graphs as AI Agent Memory

How Neo4j's new AgentMemory SDK for .NET uses knowledge graphs as the persistence substrate for AI agent memory — enabling structured recall,…

AgentMemoryNeo4jDotNetAI-Agents+4 more

July 30, 2026· ~6 min read

Applying the CaRE Protocol to Agent Benchmarks: Compute-Aware Evaluation for Skill and Memory Harnesses

We applied the CaRE compute-aware evaluation protocol (arXiv:2607.24763) to our agent benchmark suites — Agent Skill Bench and AMBench.…

CaREBenchmarkingLLM-EvaluationAI-Agents+4 more