Over breakfast I spotted ‘Data Structures: Theory and Practice’ by Alfs Berztiss published 1971. Could not resist seeing what he had to say about graphs. “Let us now take a new approach ….”
Traverse, an embedded/server graph database similar to Neo4j and Memgraph that runs in production serving tens of millions of nodes and edges under high loads is now available in preview
Traverse, an embedded/server graph database similar to Neo4j and Memgraph that runs in production serving tens of millions of nodes and edges under high loads is now available in preview.
Built from the ground up with a new query engine, it works across all operating systems with a single binary and has 99.95% openCypher compatibility and Bolt 5.x/6 support. Comes with a built-in IDE, gRPC, WebSockets, HTTP API, and MCP. Supports hot-swapping databases and TCP socket ingestion. It's tested against all known vendors and beats overall on all tested Pokec datasets.
We wanted to take it a step further so we're including Silicon, a research unikernel build that runs enterprise software on Firecracker or Cloud Hypervisor and boots in under 100 ms. So fast it can boot platforms during a request. Traverse Silicon / Unikernel build is also available for preview.
Silicon has a durable filesystem, SiliconFS, prioritizing crash safety. Unikernels provide full hardware isolation with no running OS, and the binary is under 10 MB. The attack surface is minimal since there is no operating system to exploit.
Researchers, students, companies, and individuals can freely use the software, and given the simple embedded vs. server CLI architecture, AI builders can get started very quickly.
Available preview: https://lnkd.in/dWvETFmp - Screenshot from console.
Traverse, an embedded/server graph database similar to Neo4j and Memgraph that runs in production serving tens of millions of nodes and edges under high loads is now available in preview
Is a "Personal Wiki" just a Knowledge Graph in disguise?
Is a "Personal Wiki" just a Knowledge Graph in disguise? 🤔
Andrej Karpathy’s idea of flat .md files "Second Brain" is incredibly popular right now. But we need to talk about the "Efficiency Gap."
Karpathy’s solution:
✅ Readable
✅ Simple to start
📛 Inefficient at 10k+ nodes
📛 Massive token waste
📛 High latency for relationship-heavy queries
If you have nodes and you have links, you have a Graph.
Using an Agent to crawl flat files is a "brute force" approach to RAG. By moving to a GraphRAG architecture, you stop using tokens to "discover" relationships and start using them to "reason" over them.
Elegance is great for a weekend project. Efficiency is required for a production-grade system.
#AI #GraphRAG #Productivity #KnowledgeGraph
Is a "Personal Wiki" just a Knowledge Graph in disguise?
We all have systems for organizing things. Sometimes these systems are expressed outwards, like organizing a spice rack or a closet. Humans interact with organizational systems daily, with the likes of navigation systems, online shopping, the grocery store and even search engines.
Agentic GraphRAG for Capital Markets | Amazon Web Services
This blog post shows you how to transform days of manual financial analysis into seconds of comprehensive insights by building an Agentic GraphRAG solution for capital markets. You’ll see the architecture, graph schema design, and agent setup that lets business users ask complex questions in plain language. Capital markets firms track financial relationships across multiple […]
A presentation on agent memory. What differentiates products is graph design
If AGI means long-running autonomous tasks & multi-day agents, then persistent memory for agents is no longer optional. Memory is the new battleground in 2026. Especially after OpenClaw, I've seen a wild range of exploration, abstraction, and implementation around agent memory. Some go with complicated graph+vector+SQL retrieval, some just give up and rely on LLM+markdown+grep. I put together a presentation on agent memory, hope it helps people get started on this topic. | 19 comments on LinkedIn
A free white paper on AI taxonomy building. See practical methods for AI-assisted taxonomy creation for semantic search, knowledge graphs, and GraphRAG.
𝐖𝐡𝐞𝐫𝐞 𝐚𝐫𝐞 𝐭𝐡𝐞 𝐭𝐚𝐱𝐨𝐧𝐨𝐦𝐢𝐞𝐬 𝐢𝐧 𝐭𝐡𝐞 𝐬𝐞𝐦𝐚𝐧𝐭𝐢𝐜 𝐰𝐞𝐛 𝐬𝐭𝐚𝐜𝐤
I love the RDF “layer cake” as a helpful abstraction for understanding how our technologies build on one another. From URIs and RDF at the base up through ontologies, constraints, and reasoning. And yet, something essential seems to be missing: The everyday enterprise #vocabularies, #glossaries, and #taxonomies that organizations rely on to describe their world.
Ontologies benefit enormously from well designed taxonomies as they bridge formally modeled knowledge with the language actually used inside a company. Conversely, we can start from the other direction: enriching the familiar enterprise vocabulary with more formal semantic structures. This creates a reinforcing loop in which terms evolve to classes, and relationships with greater clarity and consistency.
A successful knowledge graph likely needs both worlds to some degree. The formal semantics of #RDFS, #OWL, and #SHACL give us powerful reasoning capabilities and data model flexible enough to represent our business. But the taxonomies and vocabularies provide the shared language that makes KG meaningful for real users and real business processes.
𝘚𝘰 𝘸𝘩𝘦𝘳𝘦, 𝘵𝘩𝘦𝘯, 𝘢𝘳𝘦 𝘵𝘢𝘹𝘰𝘯𝘰𝘮𝘪𝘦𝘴 𝘪𝘯 𝘰𝘶𝘳 𝘙𝘋𝘍 𝘴𝘵𝘢𝘤𝘬?
The RDF stack focuses entirely on formalization and technical expressiveness. That focus makes sense when explaining inference, constraints, and data modeling. But it does not reflect how knowledge graphs are created and governed in organizations: Where taxonomy management, metadata stewardship, and terminology alignment are daily challenges.
That gap is precisely why I enjoy conversations about interoperability and alignment matter so much. And it’s why I’m especially excited to be and speak at the upcoming Taxonomy Bootcamp conference in London in two weeks. (Interested in joining? I’ve got a speaker discount!).
What’s your take on this? Does SKOS belong in the RDF stack? Or do we need another good abstraction on how the ontologies build on each other apart from formal semantics? (Thinking not only of SKOS but also PROV/DCTERMS/DCAT, etc.) | 17 comments on LinkedIn
Utilization of Ontology to Develop Artificial Intelligence Systems in the Healthcare Industry
Ontologies play a crucial role in healthcare systems due to the diversity of concepts, roles, users, and diagnostic and therapeutic methods. They facilitate the development of knowledge bases and the sharing and representation of information. With ...
Ontology-grounded knowledge graphs for mitigating hallucinations in large language models for clinical question answering - PubMed
Ontology-grounded knowledge graphs provide a reliable and verifiable method for mitigating hallucinations in LLM-based clinical question answering. By embedding structured clinical semantics into the reasoning process, the framework enhances factual accuracy, reproducibility, and safety in biomedica …
Ontology-Enhanced Knowledge Graph Completion using Large Language Models
Large Language Models (LLMs) have been extensively adopted in Knowledge Graph Completion (KGC), showcasing significant research advancements. However, as black-box models driven by deep neural...
I Built a Knowledge Graph Recommender to Understand Where Graphs Actually Fail
I Built a Knowledge Graph Recommender to Understand Where Graphs Actually Fail By Kartikeya Mandhar | UCLA MSBA I’ve had a complicated relationship with knowledge graphs. The idea that you can …
VKG vs KG: The Practical Guide No One Gives You When Building Semantic Platforms
VKG vs KG: The Practical Guide No One Gives You When Building Semantic Platforms A practical guide to choosing between Virtual Knowledge Graphs and Knowledge Graphs for multi-source, ontology-driven …
Context Engineering as Your Competitive Edge | Towards Data Science
If you have both unique domain expertise and know how to make it usable to your AI systems, you’ll be hard to beat.
Articulating knowledge through graphs
Many teams dump their available data into an embedding database without knowing what’s inside. This is a sure recipe for failure. You need to know the semantics of your data. Your knowledge representation should reflect the core objects, processes, and KPIs of the business in a way that is interpretable both by humans and by machines. For humans, this ensures maintainability and governance. For AI systems, it ensures retrievability and correct usage. The model must not only access information, but also understand which source is appropriate for which task.
Graphs are a promising approach because they allow you to structure knowledge while preserving flexibility. Instead of treating knowledge as an archive of loosely connected documents, you model the core objects of your business and the relationships between them.
Depending on what you need to encode, here are some graph types to consider:
Taxonomies or ontologies that define core business objects — deals, segments, accounts, reps — along with their properties and relationships
Canonical knowledge graphs that capture more complex, non-hierarchical dependencies
Context graphs that record past decision traces and allow retrieval of precedents
Graphs are powerful as a representation layer, and RAG variants such as GraphRAG provide a blueprint for their integration. However, graphs don’t grow on trees. They require an intentional design effort — you need to decide what the graph encodes, how it is maintained, and which parts are exposed to the model in a given reasoning cycle. Ideally, you can view this not as a one-off investment, but turn it into a continuous effort where human users collaborate with the AI system in parallel to their daily work. This will allow you to build its knowledge while engaging users and supporting adoption.
The National Center for Ontological Research (NCOR) is partnering with Webworld Technologies, Inc. (WTI) to support the development and modernization of the Common Core Ontologies (CCO)
the National Center for Ontological Research (NCOR), I am pleased to share that we are partnering with Webworld Technologies, Inc. (WTI) to support the development and modernization of the Common Core Ontologies (CCO)
Enterprise search, foundation models, productivity AI, and HR analytics are all racing to own the enterprise stack and all hitting the same wall. The missing layer is not a feature any of them will ship. It is a category of its own.
Graph technology in 2026: Insights and predictions from data and graph experts
We interviewed a number of individuals who work with graphs or in the world of data to get their perspectives on how graph and connected data are evolving—and where they might be headed.
For AI decision systems, five knowledge layers are emerging
𝐀 𝐮𝐬𝐞𝐟𝐮𝐥 𝐭𝐚𝐤𝐞𝐚𝐰𝐚𝐲 𝐟𝐫𝐨𝐦 𝐭𝐡𝐞 𝐜𝐮𝐫𝐫𝐞𝐧𝐭 “𝐜𝐨𝐧𝐭𝐞𝐱𝐭 𝐠𝐫𝐚𝐩𝐡” 𝐜𝐨𝐧𝐯𝐞𝐫𝐬𝐚𝐭𝐢𝐨𝐧
👉 𝐎𝐧𝐞 𝐠𝐫𝐚𝐩𝐡 𝐢𝐬 𝐮𝐬𝐮𝐚𝐥𝐥𝐲 𝐧𝐨𝐭 𝐞𝐧𝐨𝐮𝐠𝐡
The more practical design pattern is a stack of context layers, each with a distinct responsibility. In recent discussions (including Year of the Graph Vol. 30 ) by George Anadiotis, the strongest point is not hype around a new term. It is the shift from “context as retrieved text” to context as operational infrastructure. For AI decision systems, five knowledge layers are emerging:
👉𝐊𝐧𝐨𝐰𝐥𝐞𝐝𝐠𝐞 / 𝐒𝐞𝐦𝐚𝐧𝐭𝐢𝐜 𝐥𝐚𝐲𝐞𝐫
𝐂𝐨𝐧𝐜𝐞𝐩𝐭𝐬: 𝙿𝚊𝚜𝚜𝚎𝚗𝚐𝚎𝚛, 𝙵𝚕𝚒𝚐𝚑𝚝, 𝙸𝚝𝚒𝚗𝚎𝚛𝚊𝚛𝚢, 𝙲𝚘𝚗𝚗𝚎𝚌𝚝𝚒𝚘𝚗
𝐑𝐞𝐥𝐚𝐭𝐢𝐨𝐧𝐬𝐡𝐢𝐩𝐬: 𝙿𝚊𝚜𝚜𝚎𝚗𝚐𝚎𝚛 𝒃𝒐𝒐𝒌𝒔 𝙸𝚝𝚒𝚗𝚎𝚛𝚊𝚛𝚢, 𝙸𝚝𝚒𝚗𝚎𝚛𝚊𝚛𝚢 𝒊𝒏𝒄𝒍𝒖𝒅𝒆𝒔 𝙵𝚕𝚒𝚐𝚑𝚝𝙻𝚎𝚐, 𝙵𝚕𝚒𝚐𝚑𝚝 𝒂𝒓𝒓𝒊𝒗𝒆𝒔_𝒂𝒕 𝙰𝚒𝚛𝚙𝚘𝚛𝚝
𝐃𝐞𝐟𝐢𝐧𝐢𝐭𝐢𝐨𝐧𝐬: 𝚖𝚒𝚜𝚜𝚎𝚍_𝚌𝚘𝚗𝚗𝚎𝚌𝚝𝚒𝚘𝚗 = 𝚊𝚌𝚝𝚞𝚊𝚕_𝚊𝚛𝚛𝚒𝚟𝚊𝚕_𝚝𝚒𝚖𝚎 +𝚖𝚒𝚗𝚒𝚖𝚞𝚖_𝚌𝚘𝚗𝚗𝚎𝚌𝚝𝚒𝚘𝚗_𝚝𝚒𝚖𝚎𝚗𝚎𝚡𝚝_𝚕𝚎𝚐_𝚍𝚎𝚙𝚊𝚛𝚝𝚞𝚛𝚎_𝚝𝚒𝚖𝚎
👉𝐆𝐨𝐯𝐞𝐫𝐧𝐚𝐧𝐜𝐞 𝐥𝐚𝐲𝐞𝐫
𝐏𝐨𝐥𝐢𝐜𝐲: “Do not expose passenger PII to operations recommendations”
𝐑𝐮𝐥𝐞: “Compensation above 300 EUR requires Revenue Approver”
𝐂𝐨𝐧𝐬𝐭𝐫𝐚𝐢𝐧𝐭: “Any rebooking recommendation must include a valid contract check and risk score”
👉𝐎𝐩𝐞𝐫𝐚𝐭𝐢𝐨𝐧𝐚𝐥 / 𝐄𝐯𝐞𝐧𝐭 𝐥𝐚𝐲𝐞𝐫
𝐄𝐯𝐞𝐧𝐭𝐬: FlightDelayed(F1001, +45m), PassengerCheckedIn(P123, F1001), GateChanged(F1002, G12)
𝐒𝐭𝐚𝐭𝐞 𝐝𝐞𝐫𝐢𝐯𝐞𝐝 𝐟𝐫𝐨𝐦 𝐞𝐯𝐞𝐧𝐭𝐬: itinerary_status = at_risk, estimated_missed_connections=27
👉𝐃𝐞𝐜𝐢𝐬𝐢𝐨𝐧 / 𝐏𝐫𝐨𝐯𝐞𝐧𝐚𝐧𝐜𝐞 𝐥𝐚𝐲𝐞𝐫
𝐃𝐞𝐜𝐢𝐬𝐢𝐨𝐧𝐏𝐫𝐨𝐩𝐨𝐬𝐚𝐥 𝐃-𝟏𝟎𝟒𝟐:“Rebook Passenger P123 to F1010”
𝐄𝐯𝐢𝐝𝐞𝐧𝐜𝐞: delay event E-7781, missed-connection score 0.91, seat availability snapshot
𝐂𝐡𝐞𝐜𝐤𝐬: policy gate passed, no PII violation, compensation threshold not triggered
𝐀𝐩𝐩𝐫𝐨𝐯𝐚𝐥: Ops Controller approved at 10:42
𝐎𝐮𝐭𝐜𝐨𝐦𝐞: Passenger rebooked successfully; arrival delay reduced by 3h
👉𝐀𝐜𝐭𝐢𝐨𝐧/𝐏𝐞𝐫𝐦𝐢𝐬𝐬𝐢𝐨𝐧 𝐥𝐚𝐲𝐞𝐫
𝐑𝐞𝐛𝐨𝐨𝐤𝐢𝐧𝐠 𝐀𝐠𝐞𝐧𝐭: can propose rebook_now for low/medium risk
𝐎𝐩𝐬 𝐂𝐨𝐧𝐭𝐫𝐨𝐥𝐥𝐞𝐫: can approve low risk, can escalate medium/high
𝐏𝐨𝐥𝐢𝐜𝐲/𝐑𝐞𝐯𝐞𝐧𝐮𝐞 𝐀𝐩𝐩𝐫𝐨𝐯𝐞𝐫: required to approve compensation or high-cost alternatives.
𝐒𝐲𝐬𝐭𝐞𝐦 𝐞𝐧𝐟𝐨𝐫𝐜𝐞𝐦𝐞𝐧𝐭: action blocked if role tries to execute outside its rights.
🤔 𝐖𝐡𝐲 𝐭𝐡𝐢𝐬 𝐦𝐚𝐭𝐭𝐞𝐫𝐬 𝐧𝐨𝐰
👉 The hard part is no longer only retrieval quality.
👉 The hard part is temporal validity, decision traceability, and enforceable control across the full decision lifecycle.
So yes, context graphs are valuable. But for enterprise AI, the real architecture is multi-layered: meaning+governance+operations+provenance+permissions.
A new era of enterprise architecture is emerging: technology, data, and business architecture are converging into one decision-ready context foundation.
For AI decision systems, five knowledge layers are emerging
Finding the Fastest Way Out: How Dijkstra’s Algorithm Finds Shortest Paths
Imagine you’re an explorer searching an old mine for abandoned treasure. You have in your possession an old map that shows all the chambers and the tunnels connecting them. Each chamber is a node in our graph, and each tunnel… Read more →
