@prefix : <#> . @prefix post: . @prefix schema: . @prefix xsd: . @prefix rdf: . @prefix rdfs: . @prefix owl: . @prefix prov: . # ── Self-describing document ──────────────────────────────────────────────── <> a schema:CreativeWork ; schema:name "Tony Seale LinkedIn Post — YAML-LD, Vault-LD & the LLM Wiki (RDF Collection)"@en ; schema:description "RDF-Turtle collection of Tony Seale's LinkedIn post on YAML-LD's advance down the W3C standards track and Vault-LD (agent-memory Linked Data), including Kingsley Uyi Idehen's full comment thread (with SeeAlso reference links) and a sampling of other public comments."@en ; schema:dateCreated "2026-07-10T00:00:00Z"^^xsd:dateTime ; schema:dateModified "2026-07-10T00:00:00Z"^^xsd:dateTime ; schema:author ; schema:accountablePerson ; schema:about :post ; prov:wasGeneratedBy . # ── Skill provenance ──────────────────────────────────────────────────────── a schema:SoftwareApplication , prov:SoftwareAgent ; schema:name "rdf-infographic-skill"@en ; schema:url ; schema:description "AI agent skill for generating RDF-Turtle knowledge graph collections and companion HTML infographics from structured source content."@en ; prov:actedOnBehalfOf . # ── LinkedIn Post ──────────────────────────────────────────────────────────── :post a schema:SocialMediaPosting ; schema:url ; owl:sameAs ; schema:name "This week YAML-LD advanced down the W3C standards track"@en ; schema:headline "This week YAML-LD advanced down the W3C standards track - a fresh working draft, published on Wednesday."@en ; schema:author ; schema:datePublished "2026-07-10T00:00:00Z"^^xsd:dateTime ; schema:mentions ; schema:interactionStatistic :reactionCount, :commentCount ; schema:comment :comment-kidehen-1 , :comment-kidehen-workflow , :comment-kidehen-2 , :comment-tonyseale-links , :comment-szymonklarman , :comment-tonyseale-reply-szymon , :comment-florianpatzer , :comment-tonyseale-reply-florian , :comment-franzjosef , :comment-tonyseale-reply-franzjosef , :comment-kylegilbride-1 , :comment-kylegilbride-2 , :comment-dmitrisafine , :comment-tonyseale-reply-dmitri , :comment-martinschiele , :comment-josephpellegrini , :comment-tonyseale-reply-joseph , :comment-joonnyipkoh ; schema:hasPart :glossarySection , post:howto , :faqSection , :referenceLinksSection , :thesisSection , :argumentSection , :yamlLdExample , :yamlLdSpecDocument ; schema:keywords "YAML-LD"@en , "JSON-LD"@en , "Vault-LD"@en , "LLM Wiki"@en , "agent memory"@en , "Linked Data"@en , "W3C standards track"@en , "Agentic Web"@en , "Architecture of the World Wide Web"@en ; schema:text """This week YAML-LD advanced down the W3C standards track - a fresh working draft, published on Wednesday. YAML-LD turns plain YAML into Linked Data. Useful, technical, invisible. Plumbing. But plumbing decides what you can build on top. Take agent memory - the problem we open-sourced Vault-LD for last week. The pattern Andrej Karpathy called the LLM wiki is simple: give an agent a folder of markdown files it reads and writes. The objection is instant: "Cute. But it doesn't scale." In one sense, fair. Plain markdown is local - readable and human, but not part of any shared semantic fabric. But those notes are rarely just markdown. At the top sits YAML frontmatter: status, tags, dates, links, types. The wiki is already half-structured. The semantic island is already there. It just isn't semantic yet. Turn that YAML into YAML-LD and the block does what JSON-LD already does across the web: point to a shared context, identify things, say what they mean, connect local notes to other documents, agents and systems - with no central platform holding them all. Look at JSON-LD. W3Techs puts it on 54% of websites. More than half the web. JSON-LD is not an app, database or platform. It is a little island of structured data inside ordinary HTML. Nobody mandated it. No database contains it. No vendor owns it. Millions of sites adopted the same move: one page, two readers. Humans read the prose; machines read the island. And because the islands share a context, they don't just coexist - they connect. That is not a theory of distributed meaning. It is the actual current state of the web. Vault-LD is the same move, aimed at agent memory. Not "swap your wiki for a database". Not "move your memory into our platform". Keep the notes, keep the files - just make the frontmatter linked data. JSON-LD put linked data inside HTML. VAULT-LD puts Linked Data inside markdown. Same @context. Same Open Standards. Same scalability! So when someone says the LLM wiki cannot scale, the answer isn't to turn it into someone else's platform. It is to give it the pattern the web already used. The web did not scale through one giant database. It scaled through independent documents carrying shared meaning at the edges. That is what web-scale means: no centre, no bottleneck, no single place all meaning must pass through. Scaleless. Human meaning went web-scale as islands of JSON-LD scattered across pages. Agent meaning can go the same way - islands of VALUT-LD scattered across notes, memories and workflows. The Agentic Web will be part of the human web not separate from it. ⚡ JSON-LD made the web a knowledge graph. Vault-LD is how agents can join it ⚡"""@en . # ── Thesis & Argument (analytical restructuring of the verbatim post) ─────── :thesisSection a schema:CreativeWork ; schema:name "Thesis"@en ; schema:isBasedOn :post ; schema:text "Agent memory can scale the same way the human web scaled — not by centralizing it into a database or a platform, but by making the structured data already sitting in markdown format into Linked Data, the way JSON-LD did for HTML."@en . :argumentSection a schema:ItemList ; schema:name "Supporting Argument"@en ; schema:isBasedOn :post ; schema:itemListElement :evidence-objection , :evidence-overlooked-asset , :evidence-precedent , :evidence-move , :evidence-principle , :evidence-implication . :evidence-objection a schema:CreativeWork ; schema:position "1"^^xsd:integer ; schema:name "The objection: \"the LLM wiki doesn't scale\""@en ; schema:mentions ; schema:text "Andrej Karpathy's LLM-wiki pattern — a folder of markdown files an agent reads and writes — is dismissed as 'cute' but non-scalable, because plain markdown is local and not part of any shared semantic fabric."@en . :evidence-overlooked-asset a schema:CreativeWork ; schema:position "2"^^xsd:integer ; schema:name "The overlooked asset: frontmatter is already half-structured"@en ; schema:text "Most notes in an LLM wiki already carry YAML frontmatter (status, tags, dates, links, types). It just isn't anchored to a shared vocabulary yet — the 'semantic island' already exists, unlabeled."@en . :evidence-precedent a schema:CreativeWork ; schema:position "3"^^xsd:integer ; schema:name "The precedent: JSON-LD already proved the pattern at web scale"@en ; schema:text "JSON-LD sits inside 54% of websites (W3Techs) with no central platform, database, or vendor owning it — millions of independent 'islands' that connect because they share a context, not because they share infrastructure."@en . :evidence-move a schema:CreativeWork ; schema:position "4"^^xsd:integer ; schema:name "The move: YAML-LD and Vault-LD apply the same mechanism"@en ; schema:text "YAML-LD (a fresh W3C working draft) does for YAML what JSON-LD did for JSON. Vault-LD applies that specifically to agent memory: keep the notes and files, just make the frontmatter Linked Data."@en . :evidence-principle a schema:CreativeWork ; schema:position "5"^^xsd:integer ; schema:name "The principle: \"scaleless\" — no centre, no bottleneck"@en ; schema:text "The web did not scale through one giant database; it scaled through independent documents carrying shared meaning at the edges. Vault-LD asks agent memory to scale the same way, not through a new proprietary platform."@en . :evidence-implication a schema:CreativeWork ; schema:position "6"^^xsd:integer ; schema:name "The implication: the Agentic Web is continuous with the human web"@en ; schema:text "If human meaning went web-scale as islands of JSON-LD scattered across pages, agent meaning can go the same way — islands of Vault-LD scattered across notes, memories, and workflows."@en . # ── YAML-LD example (reproduced verbatim from the W3C spec, not invented) ──── :yamlLdSpecDocument a schema:CreativeWork ; schema:name "YAML-LD 1.0 (W3C Working Draft)"@en ; schema:url ; schema:datePublished "2026-07-08"^^xsd:date ; schema:description "The W3C Working Draft referenced in the post as having 'advanced down the W3C standards track' this week. Its own introductory example (Example 1, describing the exoplanet Proxima Centauri b) is reproduced in :yamlLdExample below."@en . :yamlLdExample a schema:SoftwareSourceCode ; schema:name "YAML-LD spec Example 1 — introductory YAML-LD document"@en ; schema:programmingLanguage "YAML"@en ; schema:isBasedOn ; rdfs:comment "Reproduced verbatim from the W3C YAML-LD 1.0 Working Draft's own Example 1 (§1 Introduction) and Example 2 (§3.1 JSON vs YAML comparison, the JSON-LD equivalent) — not an invented illustration. Every identifier (dbr:Proxima_Centauri_b, dbo:Planet, dbp:discovered, dbp:star) expands via @context to a real, dereferenceable DBpedia or Schema.org HTTP IRI, which is why this replaced an earlier draft of this example that had used non-dereferenceable urn: identifiers — that would have been an anti-pattern relative to the post's own thesis that hyperlinks are the identifier mechanism."@en ; schema:text """# Example 1 — YAML-LD "@context": - https://json-ld.org/contexts/dollar-convenience.jsonld - schema: https://schema.org/ dbo: http://dbpedia.org/ontology/ dbp: http://dbpedia.org/property/ dbr: http://dbpedia.org/resource/ xsd: http://www.w3.org/2001/XMLSchema# dbp:discovered: "@type": xsd:date dbp:star: "@type": "@id" $id: dbr:Proxima_Centauri_b $type: dbo:Planet schema:description: >- The closest known exoplanet to Earth, orbiting in Proxima Centauri's habitable zone. dbp:discovered: 2016-08-24 dbp:star: dbr:Proxima_Centauri # Example 2 — equivalent JSON-LD { "@context": [ "https://json-ld.org/contexts/dollar-convenience.jsonld", { "schema": "https://schema.org/", "dbo": "http://dbpedia.org/ontology/", "dbp": "http://dbpedia.org/property/", "dbr": "http://dbpedia.org/resource/", "xsd": "http://www.w3.org/2001/XMLSchema#", "dbp:discovered": { "@type": "xsd:date" }, "dbp:star": { "@type": "@id" } } ], "$id": "dbr:Proxima_Centauri_b", "$type": "dbo:Planet", "schema:description": "The closest known exoplanet to Earth, orbiting in Proxima Centauri's habitable zone.", "dbp:discovered": "2016-08-24", "dbp:star": "dbr:Proxima_Centauri" }"""@en . # ── Interaction Counters ───────────────────────────────────────────────────── :reactionCount a schema:InteractionCounter ; schema:interactionType schema:LikeAction ; schema:userInteractionCount "128"^^xsd:integer . :commentCount a schema:InteractionCounter ; schema:interactionType schema:CommentAction ; schema:userInteractionCount "20"^^xsd:integer . # ── People ─────────────────────────────────────────────────────────────────── a schema:Person ; schema:name "Tony Seale"@en ; schema:url ; schema:description "The Knowledge Graph Guy. Author and advocate for YAML-LD, Vault-LD, and Linked Data patterns for agent memory."@en . a schema:Person ; schema:name "Andrej Karpathy"@en ; schema:url ; schema:description "AI researcher who popularized the 'LLM wiki' agent-memory pattern — a folder of markdown files an agent reads and writes — referenced in the post as the origin of the pattern Vault-LD addresses."@en . a schema:Person ; schema:name "Kingsley Uyi Idehen"@en ; schema:url ; schema:jobTitle "Founder & CEO"@en ; schema:worksFor ; schema:description "Founder & CEO of OpenLink Software. Creator of Virtuoso. Semantic Web pioneer. Advocate for open, interoperable, hyperlink-based knowledge systems."@en ; owl:sameAs , , . a schema:Person ; schema:name "Szymon Klarman"@en ; schema:url ; schema:description "Senior Director, Knowledge Engineering, Enterprise Data Organization, S&P Global."@en . a schema:Person ; schema:name "Dr. Florian Patzer"@en ; schema:url ; schema:description "Software Architect building the layer between AI and architectural intent. Founder @ nodeline."@en . a schema:Person ; schema:name "Franz-Josef Siegemund"@en ; schema:url ; schema:description "Emerging Tech Engineer @ SICK. Systems Engineering, Semantic Data."@en . a schema:Person ; schema:name "Kyle Gilbride"@en ; schema:url ; schema:description "Builds B2B go-to-market operating systems to generate more revenue from the same resources."@en . a schema:Person ; schema:name "Dmitri Safine"@en ; schema:url ; schema:description "Founder & Principal Consultant @ Crosslink Data LLC."@en . a schema:Person ; schema:name "Dr. Martin Schiele"@en ; schema:url ; schema:description "AI architect. GDPR-compliant AI systems, independent of big tech."@en . a schema:Person ; schema:name "Joseph Pellegrini"@en ; schema:url ; schema:description "Technology and AI Architect. Leader of high-performance teams."@en . a schema:Person ; schema:name "Joon Nyip Koh"@en ; schema:url ; schema:description "Independent Researcher @ OpenClaw/Hermes. Orchestra Multi-agent Systems, Agentic AI."@en . a schema:Person ; schema:name "Dan Brickley"@en ; schema:url ; schema:description "Co-creator of FOAF and RDF/Schema.org contributor, mentioned in-thread by Tony Seale."@en . a schema:Person ; schema:name "Daniel Remedios"@en ; schema:url ; schema:description "Mentioned in-thread by Kyle Gilbride regarding buyer/decision-maker understanding of semantic plumbing."@en . # ── Comments: Kingsley Uyi Idehen's thread (featured first) ───────────────── :comment-kidehen-1 a schema:Comment ; schema:author ; schema:parentItem :post ; schema:position "1"^^xsd:integer ; schema:text """Yep! What's sometimes lost is the fact that the Architecture of the World Wide Web (AWWW) and the World Wide Web (the Web) are easily conflated, whether inadvertently or cynically. The net effect is that mentioning the "Web" automatically leads many to presume public access at Internet scale. In reality, this is simply about using the magic of hyperlinks (pointers surfaced in user, not just developer, space) to break down the compounding technical debt native to silos. The perennial battle remains platform silos versus standards-based interoperability. In the past, proprietary platforms exploited the GUI-driven complexities of software design, development, use, and support. The arrival of LLMs has largely removed that friction by adding multimodal and multilingual natural language processing to computing's UI/UX stack. This is driving a long-overdue reconstruction of the software industry at every level."""@en . :comment-kidehen-workflow a schema:Comment ; schema:author ; schema:parentItem :post ; schema:isPartOf :comment-kidehen-1 ; schema:position "2"^^xsd:integer ; rdfs:comment "Edited by the author after initial posting (LinkedIn 'edited' marker)."@en ; schema:text """The new workflow is both simple and profound i.e., deceptively simple: 1. Encounter something of interest. 2. Take some notes. 3. Transform those notes into a Semantic Web (not "The Semantic Web") by applying Linked Data principles—naming things with hyperlinks and describing them using compact subject-predicate-object statements, where hyperlinks denote the subjects, predicates, and objects. Step 3 used to be esoteric. Today, it's as simple as calling an AI agent skill (tacitly or explicitly) to generate the information representation in whatever notation is appropriate, whether YAML-LD, JSON-LD, RDF-Turtle, or another notation. The beauty of LLMs is that they've been trained on the publicly available specifications for virtually every open standard published on the Web. Ultimately, this is about communication, IMHO. Our ability to communicate has taken a covert quantum leap. It will simply take a little time for the world to appreciate just how profound this change really is."""@en . :comment-kidehen-2 a schema:Comment ; schema:author ; schema:parentItem :post ; schema:isPartOf :comment-kidehen-1 ; schema:position "3"^^xsd:integer ; schema:text """SeeAlso: [1] https://www.linkedin.com/pulse/next-influencers-wont-sell-attention-theyll-better-answers-idehen-gyrxc -- economic value of files (documents) in an Agentic Web [2] https://www.linkedin.com/pulse/missing-layer-enterprise-ai-semantic-web-project-has-been-idehen-pbrcc -- The Missing Layer in Enterprise AI: The Semantic Web Project Has Been Building It for Two Decades [3] https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/kg-generator -- Linked Data Generator that works with a broad variety of document types [4] https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/rdf-infographic-skill -- Linked Data Generator and visualizer for a broad range of document types [5] https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/agent-rdf-memory -- Linked Data based Context Layer for AI Agents"""@en ; schema:citation :ref-next-influencers , :ref-missing-layer , :ref-kg-generator , :ref-rdf-infographic-skill , :ref-agent-rdf-memory . # ── Comments: sampling of other public comments ────────────────────────────── :comment-tonyseale-links a schema:Comment ; schema:author ; schema:parentItem :post ; schema:position "4"^^xsd:integer ; schema:interactionStatistic :comment-tonyseale-links-reactions ; schema:text """Links that didn't fit in the post - for anyone who wants to go deeper: ⭕ Islands of JSON-LD - anchor GPT to your own data (2023): https://www.linkedin.com/feed/update/urn:li:activity:7044956014432915457/ ⭕ Building a Semantic Layer (another 2023 one): https://www.linkedin.com/feed/update/urn:li:activity:7037345868831715329/ (plus further linked posts referencing Schema.org and related LinkedIn threads)"""@en ; rdfs:comment "Excerpt — LinkedIn truncated this comment behind a 'see more' control; only the two lead-in links carried visible descriptive text at capture time. Remaining hrefs are preserved below as bare citations without fabricated descriptions."@en ; schema:citation , , , , , , , , , . :comment-tonyseale-links-reactions a schema:InteractionCounter ; schema:interactionType schema:LikeAction ; schema:userInteractionCount "6"^^xsd:integer . :comment-szymonklarman a schema:Comment ; schema:author ; schema:parentItem :post ; schema:position "5"^^xsd:integer ; schema:interactionStatistic :comment-szymonklarman-reactions ; schema:text "100%! YAML-LD seems like a tailored fit for Open Knowledge Format and similar markdown-based llm-wiki…"@en ; rdfs:comment "Excerpt — LinkedIn truncated this comment behind a 'see more' control; capture stopped at 'llm-wiki'."@en . :comment-szymonklarman-reactions a schema:InteractionCounter ; schema:interactionType schema:LikeAction ; schema:userInteractionCount "1"^^xsd:integer . :comment-tonyseale-reply-szymon a schema:Comment ; schema:author ; schema:parentItem :comment-szymonklarman ; schema:position "6"^^xsd:integer ; schema:interactionStatistic :comment-tonyseale-reply-szymon-reactions ; schema:text "Yeah I think that makes really good sense. — what do you think about that? (mentions Szymon Klarman and Dan Brickley)"@en . :comment-tonyseale-reply-szymon-reactions a schema:InteractionCounter ; schema:interactionType schema:LikeAction ; schema:userInteractionCount "1"^^xsd:integer . :comment-florianpatzer a schema:Comment ; schema:author ; schema:parentItem :post ; schema:position "7"^^xsd:integer ; schema:interactionStatistic :comment-florianpatzer-reactions ; schema:text "I haven't quite figured out yet why Vault-LD scales better than LLMWiki. After all, semantic isn't t…"@en ; rdfs:comment "Excerpt — LinkedIn truncated this comment; capture stopped mid-word."@en . :comment-florianpatzer-reactions a schema:InteractionCounter ; schema:interactionType schema:LikeAction ; schema:userInteractionCount "1"^^xsd:integer . :comment-tonyseale-reply-florian a schema:Comment ; schema:author ; schema:parentItem :comment-florianpatzer ; schema:position "8"^^xsd:integer ; schema:text "great question - it's the crux, so thanks for pushing on it. You're right: semantics doesn't limit …"@en ; rdfs:comment "Excerpt — LinkedIn truncated this comment; capture stopped mid-sentence."@en . :comment-franzjosef a schema:Comment ; schema:author ; schema:parentItem :post ; schema:position "9"^^xsd:integer ; schema:interactionStatistic :comment-franzjosef-reactions ; schema:text "Just waiting for the Obsidian integration. (edited)"@en ; schema:mentions . :comment-franzjosef-reactions a schema:InteractionCounter ; schema:interactionType schema:LikeAction ; schema:userInteractionCount "2"^^xsd:integer . :comment-tonyseale-reply-franzjosef a schema:Comment ; schema:author ; schema:parentItem :comment-franzjosef ; schema:position "10"^^xsd:integer ; schema:interactionStatistic :comment-tonyseale-reply-franzjosef-reactions ; schema:text "watch this space :-)"@en . :comment-tonyseale-reply-franzjosef-reactions a schema:InteractionCounter ; schema:interactionType schema:LikeAction ; schema:userInteractionCount "1"^^xsd:integer . :comment-kylegilbride-1 a schema:Comment ; schema:author ; schema:parentItem :post ; schema:position "11"^^xsd:integer ; schema:interactionStatistic :comment-kylegilbride-1-reactions ; schema:text "great stuff - thanks for such clear explanations on the \"plumbing.\" This is the important but not ur…"@en ; rdfs:comment "Excerpt — LinkedIn truncated this comment; capture stopped mid-word ('urgent', inferred but not confirmed by the source and therefore not completed)."@en . :comment-kylegilbride-1-reactions a schema:InteractionCounter ; schema:interactionType schema:LikeAction ; schema:userInteractionCount "1"^^xsd:integer . :comment-kylegilbride-2 a schema:Comment ; schema:author ; schema:parentItem :comment-kylegilbride-1 ; schema:position "12"^^xsd:integer ; schema:text "I agree but for the buyers and decision makers (CEO, CFO, CRO) - do they get this? I was chatting wi… (mentions Tony Seale and Daniel Remedios)"@en ; rdfs:comment "Excerpt — LinkedIn truncated this comment; capture stopped mid-word."@en . :comment-dmitrisafine a schema:Comment ; schema:author ; schema:parentItem :post ; schema:position "13"^^xsd:integer ; schema:interactionStatistic :comment-dmitrisafine-reactions ; schema:text "It sounds like something very similar to LinkML."@en . :comment-dmitrisafine-reactions a schema:InteractionCounter ; schema:interactionType schema:LikeAction ; schema:userInteractionCount "1"^^xsd:integer . :comment-tonyseale-reply-dmitri a schema:Comment ; schema:author ; schema:parentItem :comment-dmitrisafine ; schema:position "14"^^xsd:integer ; schema:interactionStatistic :comment-tonyseale-reply-dmitri-reactions ; schema:text "yes same backbone - the semantic web"@en . :comment-tonyseale-reply-dmitri-reactions a schema:InteractionCounter ; schema:interactionType schema:LikeAction ; schema:userInteractionCount "1"^^xsd:integer . :comment-martinschiele a schema:Comment ; schema:author ; schema:parentItem :post ; schema:position "15"^^xsd:integer ; schema:text "Interesting approach. But scaling concepts for shared semantic frameworks like YAML-LD might face re…"@en ; rdfs:comment "Excerpt — LinkedIn truncated this comment; capture stopped mid-word."@en . :comment-josephpellegrini a schema:Comment ; schema:author ; schema:parentItem :post ; schema:position "16"^^xsd:integer ; schema:interactionStatistic :comment-josephpellegrini-reactions ; schema:text "AWESOME!"@en . :comment-josephpellegrini-reactions a schema:InteractionCounter ; schema:interactionType schema:LikeAction ; schema:userInteractionCount "1"^^xsd:integer . :comment-tonyseale-reply-joseph a schema:Comment ; schema:author ; schema:parentItem :comment-josephpellegrini ; schema:position "17"^^xsd:integer ; schema:text "Thank you 😊"@en . :comment-joonnyipkoh a schema:Comment ; schema:author ; schema:parentItem :post ; schema:position "18"^^xsd:integer ; schema:interactionStatistic :comment-joonnyipkoh-reactions ; schema:text "I Use LLM wiki. Is good organise to obsidian."@en . :comment-joonnyipkoh-reactions a schema:InteractionCounter ; schema:interactionType schema:LikeAction ; schema:userInteractionCount "1"^^xsd:integer . # ── Reference Links (Kingsley Uyi Idehen's SeeAlso citations) ──────────────── :referenceLinksSection a schema:ItemList ; schema:name "SeeAlso — Kingsley Uyi Idehen's Reference Links"@en ; schema:description "Reference links Kingsley Uyi Idehen posted in-thread, noted for incorporation into this collection."@en ; schema:itemListElement :ref-next-influencers , :ref-missing-layer , :ref-kg-generator , :ref-rdf-infographic-skill , :ref-agent-rdf-memory . :ref-next-influencers a schema:CreativeWork ; schema:position "1"^^xsd:integer ; schema:name "The Next Influencers Won't Sell Attention. They'll Sell Better Answers"@en ; schema:url ; schema:author ; schema:description "Economic value of files (documents) in an Agentic Web."@en . :ref-missing-layer a schema:CreativeWork ; schema:position "2"^^xsd:integer ; schema:name "The Missing Layer in Enterprise AI: The Semantic Web Project Has Been Building It for Two Decades"@en ; schema:url ; schema:author ; schema:description "Argument that the Semantic Web project has been building enterprise AI's missing context layer for two decades."@en . :ref-kg-generator a schema:SoftwareApplication ; schema:position "3"^^xsd:integer ; schema:name "kg-generator"@en ; schema:url ; schema:description "Linked Data Generator that works with a broad variety of document types."@en . :ref-rdf-infographic-skill a schema:SoftwareApplication ; schema:position "4"^^xsd:integer ; schema:name "rdf-infographic-skill"@en ; schema:url ; schema:description "Linked Data Generator and visualizer for a broad range of document types."@en . :ref-agent-rdf-memory a schema:SoftwareApplication ; schema:position "5"^^xsd:integer ; schema:name "agent-rdf-memory"@en ; schema:url ; schema:description "Linked Data based Context Layer for AI Agents."@en . # ── Glossary ──────────────────────────────────────────────────────────────── :glossarySection a schema:DefinedTermSet ; schema:name "Glossary"@en ; schema:hasDefinedTerm :term-yaml-ld , :term-json-ld , :term-vault-ld , :term-llm-wiki , :term-frontmatter , :term-aww , :term-linked-data , :term-context , :term-agentic-web , :term-w3c-working-draft . :term-yaml-ld a schema:DefinedTerm ; schema:name "YAML-LD"@en ; schema:description "A W3C working-draft specification (advanced this week per Tony Seale's post) that turns plain YAML into Linked Data by adding an @context block, letting YAML frontmatter identify entities, express meaning, and connect to other documents, agents, and systems."@en ; schema:inDefinedTermSet :glossarySection ; schema:sameAs . :term-json-ld a schema:DefinedTerm ; schema:name "JSON-LD"@en ; schema:description "A W3C Linked Data serialization embedded inside ordinary HTML pages — present on 54% of websites per W3Techs. An 'island' of structured data that machines read while humans read the surrounding prose."@en ; schema:inDefinedTermSet :glossarySection ; owl:sameAs . :term-vault-ld a schema:DefinedTerm ; schema:name "Vault-LD"@en ; schema:description "An open-sourced pattern (referenced in the post as launched 'last week') that applies the YAML-LD move to agent memory: keep the markdown notes and files, but make the YAML frontmatter Linked Data — so agent memory scales the way the web scaled, without a central platform."@en ; schema:inDefinedTermSet :glossarySection . :term-llm-wiki a schema:DefinedTerm ; schema:name "LLM Wiki"@en ; schema:description "The agent-memory pattern popularized by Andrej Karpathy: give an agent a folder of markdown files it reads and writes. Criticized as not scaling — a critique the post's author addresses via Vault-LD."@en ; schema:inDefinedTermSet :glossarySection ; schema:mentions . :term-frontmatter a schema:DefinedTerm ; schema:name "YAML Frontmatter"@en ; schema:description "The structured block (status, tags, dates, links, types) at the top of a markdown file. Already half-structured; YAML-LD is what makes it semantic by anchoring it to a shared @context."@en ; schema:inDefinedTermSet :glossarySection . :term-aww a schema:DefinedTerm ; schema:name "Architecture of the World Wide Web (AWWW)"@en ; schema:description "The W3C architectural principles underlying the Web — distinct from 'the Web' itself as a public, Internet-scale network. Kingsley Uyi Idehen's comment stresses that AWWW and the Web are often conflated: using hyperlinks to break down silo technical debt does not require public Internet-scale access."@en ; schema:inDefinedTermSet :glossarySection ; owl:sameAs . :term-linked-data a schema:DefinedTerm ; schema:name "Linked Data"@en ; schema:description "A method of publishing structured data using dereferenceable URIs and shared vocabularies (@context) so that data items can be interlinked and become more useful through association with related data — the underlying pattern of both JSON-LD and YAML-LD/Vault-LD."@en ; schema:inDefinedTermSet :glossarySection ; owl:sameAs . :term-context a schema:DefinedTerm ; schema:name "@context"@en ; schema:description "The JSON-LD / YAML-LD keyword that maps local terms to shared, dereferenceable vocabulary IRIs, letting independent documents carry compatible meaning without a central schema authority."@en ; schema:inDefinedTermSet :glossarySection . :term-agentic-web a schema:DefinedTerm ; schema:name "Agentic Web"@en ; schema:description "The post's closing claim: the Agentic Web will be part of the human web, not separate from it — agent memory scaling via islands of Vault-LD the same way human meaning scaled via islands of JSON-LD."@en ; schema:inDefinedTermSet :glossarySection ; owl:sameAs . :term-w3c-working-draft a schema:DefinedTerm ; schema:name "W3C Working Draft"@en ; schema:description "A publication stage on the W3C standards track for a technical specification, indicating community review is underway but the spec is not yet finalized. YAML-LD advanced to a fresh working draft, published the Wednesday before this post."@en ; schema:inDefinedTermSet :glossarySection ; owl:sameAs . # ── HowTo ───────────────────────────────────────────────────────────────────── post:howto a schema:HowTo ; schema:name "HowTo: Turn an LLM Wiki Into Linked Agent Memory"@en ; schema:description "A practical path from a plain markdown LLM wiki to a scalable, standards-based agent memory layer, following the YAML-LD / Vault-LD pattern set out by Tony Seale and the hyperlink-first principles reinforced by Kingsley Uyi Idehen's comment."@en ; schema:step post:step-audit-frontmatter , post:step-adopt-context , post:step-yaml-ld , post:step-vault-ld , post:step-hyperlink-entities , post:step-triple-statements , post:step-federate-web . post:step-audit-frontmatter a schema:HowToStep ; schema:name "Audit your existing markdown format"@en ; schema:text "Inventory the YAML frontmatter already present at the top of your agent's markdown notes: status, tags, dates, links, types. This half-structured data is the semantic island waiting to be made semantic."@en ; schema:position 1 . post:step-adopt-context a schema:HowToStep ; schema:name "Point frontmatter at a shared @context"@en ; schema:text "Add an @context block to the YAML frontmatter, mapping local keys to shared, dereferenceable vocabulary terms — the same move JSON-LD makes inside HTML."@en ; schema:position 2 . post:step-yaml-ld a schema:HowToStep ; schema:name "Convert YAML to YAML-LD"@en ; schema:text "Use the YAML-LD working draft to turn plain YAML into Linked Data: identify things, say what they mean, and connect local notes to other documents, agents, and systems — with no central platform holding it all."@en ; schema:position 3 . post:step-vault-ld a schema:HowToStep ; schema:name "Apply Vault-LD to agent memory"@en ; schema:text "Keep the notes, keep the files — just make the frontmatter Linked Data. Vault-LD applies the JSON-LD-in-HTML pattern to markdown-in-agent-memory: same @context, same open standards, same scalability."@en ; schema:position 4 . post:step-hyperlink-entities a schema:HowToStep ; schema:name "Name entities and relationships using hyperlinks"@en ; schema:text "Per Kingsley Uyi Idehen's comment: use hyperlinks — pointers surfaced in user, not just developer, space — as stable, standardised identifiers for entities and relationships, breaking down the compounding technical debt native to silos."@en ; schema:position 5 . post:step-triple-statements a schema:HowToStep ; schema:name "Describe everything as subject–predicate–object statements"@en ; schema:text "Express notes as compact entity–relationship–entity structured statements. Rinse and repeat, manually or automatically, and new data, information, and knowledge emerge through the accumulation and connection of these statements."@en ; schema:position 6 . post:step-federate-web a schema:HowToStep ; schema:name "Let agent memory scale the way the web scaled"@en ; schema:text "Do not centralize agent memory into one giant database or platform. Scale it the way the human web scaled: independent documents (or notes) carrying shared meaning at the edges — no centre, no bottleneck, no single place all meaning must pass through."@en ; schema:position 7 . # ── FAQ ─────────────────────────────────────────────────────────────────────── :faqSection a schema:FAQPage ; schema:name "FAQ: YAML-LD, Vault-LD & the LLM Wiki"@en ; schema:mainEntity :faq-what-is-yaml-ld , :faq-why-doesnt-scale , :faq-what-is-vault-ld , :faq-json-ld-adoption , :faq-aww-vs-web , :faq-context-portability , :faq-frontmatter-already-structured , :faq-agentic-web-role . :faq-what-is-yaml-ld a schema:Question ; schema:name "What is YAML-LD?"@en ; schema:acceptedAnswer [ a schema:Answer ; schema:text "YAML-LD is a W3C working-draft specification (a fresh draft was published the Wednesday before this post) that turns plain YAML into Linked Data — the same underlying mechanism JSON-LD uses, applied to YAML instead of JSON, so YAML frontmatter can identify things, say what they mean, and connect documents, agents, and systems without a central platform."@en ] ; schema:parentItem :faqSection . :faq-why-doesnt-scale a schema:Question ; schema:name "Why is a plain markdown LLM wiki criticized as not scaling?"@en ; schema:acceptedAnswer [ a schema:Answer ; schema:text "The pattern Andrej Karpathy called the LLM wiki — a folder of markdown files an agent reads and writes — is local, readable, and human. But plain markdown is not part of any shared semantic fabric; the objection 'Cute, but it doesn't scale' targets that missing shared context, not the folder-of-notes approach itself."@en ] ; schema:parentItem :faqSection . :faq-what-is-vault-ld a schema:Question ; schema:name "What is Vault-LD and how does it solve the scaling objection?"@en ; schema:acceptedAnswer [ a schema:Answer ; schema:text "Vault-LD is the pattern open-sourced by Tony Seale for agent memory: it does not ask you to swap the wiki for a database or move memory into a platform. It makes the YAML frontmatter of existing notes Linked Data, so agent memory can scale the same way the web scaled — through independent documents carrying shared meaning at the edges, not through one giant central database."@en ] ; schema:parentItem :faqSection . :faq-json-ld-adoption a schema:Question ; schema:name "How widely adopted is JSON-LD, and why does that matter for YAML-LD?"@en ; schema:acceptedAnswer [ a schema:Answer ; schema:text "W3Techs puts JSON-LD on 54% of websites — more than half the web — without any single vendor owning it, any database containing it, or any platform mandating it. That decentralized, standards-based adoption pattern is the proof-of-concept the post cites for why the same @context-driven approach (via YAML-LD/Vault-LD) can scale agent memory."@en ] ; schema:parentItem :faqSection . :faq-aww-vs-web a schema:Question ; schema:name "What is the difference between the Architecture of the World Wide Web (AWWW) and 'the Web'?"@en ; schema:acceptedAnswer [ a schema:Answer ; schema:text "Per Kingsley Uyi Idehen's comment, AWWW and 'the Web' are easily conflated, inadvertently or cynically — mentioning 'the Web' leads many to presume public Internet-scale access is required. In reality, the underlying architecture is simply about using hyperlinks — pointers surfaced in user space, not just developer space — to break down the technical debt compounding inside silos, whether or not the result is publicly accessible."@en ] ; schema:parentItem :faqSection . :faq-context-portability a schema:Question ; schema:name "Why does 'same @context, same open standards' matter for agent memory portability?"@en ; schema:acceptedAnswer [ a schema:Answer ; schema:text "By reusing the same @context mechanism and open standards that JSON-LD already proved at web scale, Vault-LD agent memory avoids becoming a new proprietary lock-in. Meaning encoded in the frontmatter can be resolved, extended, and joined by any compliant system — not just the one that wrote it."@en ] ; schema:parentItem :faqSection . :faq-frontmatter-already-structured a schema:Question ; schema:name "Why does the post say the LLM wiki is 'already half-structured'?"@en ; schema:acceptedAnswer [ a schema:Answer ; schema:text "Most markdown notes used in LLM-wiki-style agent memory already carry YAML frontmatter with status, tags, dates, links, and types. This is structured data — it just isn't yet semantic, because nothing anchors those keys and values to a shared, dereferenceable vocabulary. YAML-LD is the missing step that makes it semantic."@en ] ; schema:parentItem :faqSection . :faq-agentic-web-role a schema:Question ; schema:name "How does Vault-LD relate to the Agentic Web?"@en ; schema:acceptedAnswer [ a schema:Answer ; schema:text "The post's closing line frames it directly: JSON-LD made the web a knowledge graph for human-facing content; Vault-LD is how agents can join that same knowledge graph via their own memory. The Agentic Web, in this framing, is part of the human web, not a separate system."@en ] ; schema:parentItem :faqSection .