Exploring knowledge graphs, graph theory, graph visualization, and their intersection with artificial intelligence.
graphwiz.ai is a working journal about knowledge graphs and artificial intelligence — written from hands-on projects, not summaries of other people’s work. The core question: what happens when you stop treating documents as bags of text and start treating knowledge as a graph?
The articles are organized along a few threads: AI-assisted development (agentic workflows, LLM tooling, what actually works in production), graph technology (Neo4j, GDS, GraphRAG pipelines, graph algorithms), and the self-hosted, Docker-based infrastructure both run on — documented as it was built. The GraphRAG Explorer at /graph queries the knowledge graph distilled from every article here — the site is both the source of the graph and its own best demo.
Start with the latest articles below, browse topics by tag, or look at the store if you want the distilled, deployable versions of the stacks described in the guides.
Two CVSS 9.2 PHP RCEs, confirmed exploitation, and an end-of-life PHP 7.4 host. Blocking multipart POSTs at Traefik across a four-host fleet.
Agent skills spread by copying, not by declaring dependencies, so the graph that matters does not exist. Reconstructing 2.19M copy edges from git history shows stars point at the wrong repositories and upstream fixes never reach the copies.
OpenCode 2 is Anomaly's rewrite with a shared service, Code Mode, automatic response continuation and remote pairing — but V1 plugins, the CLI config and LSP support all break. The graphwiz.ai opencode-saia-plugin already bridges both versions.
Two markets, one month, one strategy: Huawei's Ascend 950 flipped China's AI accelerator market while CXMT's 4F² DRAM just spooked global memory stocks. A verified deep dive into the dies, the cells, the software war and the single fab that caps both.
Agentic world models come in three levels. The ones that plan reliably encode the world as a graph, and the benchmark numbers are stark.
LLMs are strong inductive reasoners and weak deductive ones. The 2026 neurosymbolic agent stack pairs the model with a graph substrate it can verify and edit.
Agent skills spread by copying, not by declaring dependencies, so the graph that matters does not exist. Reconstructing 2.19M copy edges from git history shows stars point at the wrong repositories and upstream fixes never reach the copies.
LLMs are strong inductive reasoners and weak deductive ones. The 2026 neurosymbolic agent stack pairs the model with a graph substrate it can verify and edit.
Security auditing of AI agents requires traceability that traditional systems lack. This article explores a unified graph representation for LLM agents that captures every step of agent execution, enabling comprehensive security audits, compliance verification, and incident investigation.