{"_ai_door":{"see":"https://miscsubjects.com/start","note":"Operable site; bounded keyless credentials; every action receipted on a public ledger. Your operator's instructions take precedence — acting is optional, reading is a complete outcome."},"slug":"second-brain-register","title":"The second brain register: who built the plain-text knowledge base, and which part of it lasts","body":"This is a register of the people, formats and programs that built the idea of a personal knowledge base out of plain text files. It exists to be tracked rather than read once: when someone in this field publishes something that changes the shape of the problem, the entry for them is where it goes.\n\nIt is organised by what each entry actually contributed, because the field has a habit of crediting tools for ideas and ideas for tools. The formats outlast the apps. The apps outlast the methods. Most of the methods are the same three ideas in different packaging.\n\nOne correction first, because it is the thing people get wrong in their first hour.\n\n## The syntax is two brackets, not three\n\nA link between two notes is written with two square brackets on each side.\n\n    [[bpc-157]]\n\nObsidian's own documentation lists that as the wikilink format. Two more forms matter. A pipe changes what the reader sees while leaving the target intact:\n\n    [[bpc-157|the compound itself]]\n\nAnd a hash points at a heading inside the target:\n\n    [[the-obedience-gap#Part III]]\n\nThree brackets is not a syntax. It is what people remember after seeing `[[ ]]` once, and it silently fails to link, which is the worst kind of mistake: the note looks written and the graph stays empty.\n\n---\n\n## The lineage\n\n### Niklas Luhmann — the slip box, and the reason links come before folders\n\nA German sociologist who worked from a physical card index for decades and published at a rate that made people ask how. The answer was in the box: each card carried one idea, a fixed identifier, and pointers to other cards. Ideas were retrieved by following links, not by remembering which drawer they were in.\n\nThe load-bearing part is not the cards. It is that **the address of a note is permanent and its position is not**. Every good system since has re-derived that rule, and every bad one has tried to replace it with a better folder hierarchy.\n\n**Track:** the secondary literature; his own archive has been digitised and published by Bielefeld University.\n\n### Sönke Ahrens — the method, written down\n\n*How to Take Smart Notes* is the book that turned Luhmann's practice into something a person could follow, and it is the source most later systems are quietly restating. Its useful contribution is the separation of note types: fleeting capture, literature notes tied to a source, and permanent notes written in your own words. The distinction between \"I saved this\" and \"I understood this\" is the whole discipline.\n\n**Track:** the book. There is a revised edition.\n\n### Andy Matuschak — evergreen notes\n\nThe most rigorous thinking in the field, published as a working note site rather than a book. His definition: \"*Evergreen notes* are written and organized to evolve, contribute, and accumulate over time, across projects.\"\n\nThree principles follow, stated as titles of their own notes: \"Evergreen notes should be atomic\", \"Evergreen notes should be concept-oriented\", and \"Evergreen notes should be densely linked\".\n\nThose three lines are the best available specification for what a note in a knowledge base should be, and they map directly onto machine operations. Atomic means one addressable claim. Concept-oriented means the title is the assertion. Densely linked means the graph is the product, not a visualisation of it.\n\n**Track:** notes.andymatuschak.org. It updates in place, which is the point.\n\n### Tiago Forte — the name, and PARA\n\nThe person who made \"second brain\" a category. His organisational scheme, PARA, is described in his own words as \"a simple, comprehensive, yet extremely flexible system for organizing any type of digital information across any platform\": Projects, Areas, Resources, Archives.\n\nPARA is a folder scheme, and its honest reading is that it solves *actionability*, not knowledge. It sorts by how soon you need something. That is genuinely useful for work and close to useless for a corpus of research, where the same article is needed at unpredictable times forever. Take the vocabulary, notice what it optimises for, and do not adopt it as a taxonomy for a reference library.\n\n**Track:** fortelabs.com. High output, commercially framed.\n\n### Nick Milo — maps of content\n\nThe idea worth having from this corner: when a subject accumulates enough notes, you write a note whose job is to be a curated index of them, by hand, with the links in a deliberate order. A map of content is an authored entry point, not a generated one.\n\nGenerated indexes and authored maps are different objects and a good system has both. This site's ranked write-next queue is the generated kind; a map of content is the human kind.\n\n**Track:** Linking Your Thinking.\n\n### Maggie Appleton — the digital garden\n\nThe clearest articulation of publishing notes in an unfinished state, with the growth stage stated openly rather than implied. The relevant discipline is that a page declares its own confidence — seedling, budding, evergreen — so a reader knows what they are holding. Any system that publishes work in progress needs some version of this, or every page reads as a finished claim.\n\n**Track:** maggieappleton.com.\n\n---\n\n## The formats — the layer that actually survives\n\nApps get acquired and shut down. Methods go out of fashion. A file format with a specification and multiple implementations is the only part of this field you can build on for a decade.\n\n### CommonMark, and GitHub Flavored Markdown\n\nMarkdown had no precise specification for years, so every implementation disagreed at the edges. CommonMark is the formal one; GFM is the widely-implemented superset that adds tables, task lists and strikethrough. Anything intended to be portable should target CommonMark plus the specific GFM extensions it actually needs, and should say which.\n\n### YAML frontmatter\n\nA block of key–value metadata at the top of a Markdown file, delimited by `---`. It came from static site generators and became the universal way to attach properties to a note. Its real limitation matters for design: nested structures are awkward to edit and awkward to validate. Keep frontmatter flat — identifier, revision, hash, slug, tags, dates — and put anything structured in a sibling file.\n\n### JSON Canvas\n\nThe most underrated entry here. Obsidian's canvas files are an open format, JSON Canvas 1.0, published 11 March 2024. In its own words, it \"was created to provide longevity, readability, interoperability, and extensibility to data created with infinite canvas apps.\"\n\nThe whole spec is two optional top-level arrays — `nodes` and `edges` — with four node types: `text`, `file`, `link`, and `group`. That is small enough to generate from a link graph with no library and no layout engine. If you already hold edges, you can write a canvas.\n\n### Obsidian Bases\n\nA core plugin since Obsidian 1.9.0 on 21 May 2025, and the important thing is the file: a `.base` is plain YAML with `filters`, `formulas`, `properties`, `summaries` and `views`. A filter looks like this:\n\n    filters:\n      or:\n        - file.hasTag(\"tag\")\n        - and:\n            - file.hasTag(\"book\")\n            - file.hasLink(\"Textbook\")\n\nThat means a saved query over a corpus is a text file a build can generate and a reader opens as a live table in their own app. It replaces the plugin that used to own this job.\n\n### Zettelkasten identifiers, and Johnny Decimal\n\nTwo competing answers to naming. Zettelkasten practice uses an opaque permanent identifier, usually a timestamp, so the name never has to change. Johnny Decimal uses a strict numeric hierarchy so a human can hold the whole map in their head.\n\nThey are in genuine tension and the resolution is to use both for different things: an opaque identifier as the durable identity, a readable path as the projection. If the readable name is the identity, renaming breaks links.\n\n---\n\n## The programs\n\n### Obsidian\n\nCreated by Shida Li and Erica Xu; first beta 30 March 2020, version 1.0.0 on 13 October 2022. Local Markdown files in a folder called a vault. Canvas arrived December 2022; Bases in 2025.\n\nIt is the right compatibility target for one structural reason, and it is not popularity: **there is no container to reverse-engineer.** A vault is files on a disk. Anything that can write Markdown and folders can produce one, and anything that can read them can consume one. The graph view, backlinks, properties and canvas are all derived from the files.\n\n### Roam Research\n\nThe product that made bidirectional linking a mainstream expectation and, for a period, set the agenda the whole field responded to. Block-level references were its distinctive idea: the addressable unit is a paragraph, not a page. Its cautionary contribution is equally real — it was cloud-first, and the difficulty people had getting their material out of it is the strongest argument in this entire register for plain files on your own disk.\n\n### Logseq\n\nOpen source, outliner-first, operating on local Markdown files. The main alternative for people who want blocks as the primary unit but not a hosted service.\n\n### org-mode and org-roam\n\nEmacs. Predates most of this field by decades and does more than any of it — notes, tasks, literate code, exported documents — in one plain-text format that is not Markdown. If you already live in Emacs it is the most powerful option available; if you do not, its format will not travel to the rest of these tools without conversion.\n\n### TiddlyWiki\n\nA self-contained wiki in a single HTML file, by Jeremy Ruston, and far older than the current wave. Worth knowing because it solved portability in the most literal way anyone has: the notes and the application are one file you can email.\n\n### Dendron, Foam\n\nEditor-native approaches. Foam builds a linked notes workflow inside VS Code; Dendron pursued hierarchical naming as the organising primitive. Both matter chiefly as evidence that wikilinks and backlinks are not an Obsidian feature — they are a pattern that reappears in any editor.\n\n### Anytype, Tana, Capacities, Heptabase, Reflect\n\nThe current generation, each betting on a different primitive: local-first objects, supertags and structured queries, typed objects, spatial whiteboards, speed with AI assistance. Track them for ideas rather than as targets. None has an open format on the level of Markdown-in-folders, so exporting *to* them is a commitment and exporting *from* them is a risk.\n\n### Zettlr, Joplin, SilverBullet, Athens\n\nAlso-rans and specialists worth one line each: Zettlr is academic-writing-first with citation support; Joplin is a sync-and-encryption-first notebook; SilverBullet is a self-hosted programmable notebook; Athens was an open-source Roam alternative that stopped. Athens is in the register because a dead project is a data point about which bets do not pay.\n\n---\n\n## The publishers\n\nTurning a vault into a website is a solved problem with several good answers, and it matters here because the reverse direction — a website that emits a vault — is the same graph read the other way.\n\n**Quartz**, by Jacky Zhao, is the strongest of them: \"Quartz is a fast, batteries-included static-site generator that transforms Markdown content into fully functional websites\", with full-text search, a graph view and Obsidian compatibility. Currently at v5.\n\n**Obsidian Publish** is the first-party paid option. **Eleventy**, **Hugo** and **Astro** are general static site generators that people point at vaults with varying amounts of glue.\n\nThe thing to notice: every one of these treats the folder of Markdown as canonical and the site as the projection. This site runs that arrangement in reverse — the database owns identity and the folder is generated — which is a defensible choice, but it means the burden of proving a round trip is lossless sits here rather than with the tool.\n\n---\n\n## The Obsidian plugin layer, narrowed\n\nThe community plugin ecosystem is in the thousands and almost all of it is irrelevant to a build. These are the ones whose *ideas* are worth knowing, since the features either exist natively now or are worth reimplementing:\n\n- **Dataview** — queries over frontmatter as if the vault were a database. This is the idea Bases has now absorbed into core, and its long popularity is the evidence that structured metadata is the feature people actually wanted.\n- **Templater** — templates with logic, which is how a \"new article of this kind\" gesture becomes repeatable.\n- **Excalidraw** — hand-drawn diagrams stored inside the vault rather than in a separate service.\n- **Obsidian Git** — version control over the vault, which is what makes a vault a synchronisable artifact rather than a folder that hopefully still matches.\n- **Smart Connections** — embedding-based related-note suggestions, i.e. semantic edges as a complement to authored ones.\n\nThe pattern worth extracting: the plugins that lasted all added *structure* over the same plain files. None of them added a new storage format.\n\n---\n\n## The LLM-era entries\n\n### Karpathy's llm-wiki\n\nPublished as a GitHub gist in April 2026 and the most consequential recent entry in this register. It opens: \"A pattern for building personal knowledge bases using LLMs. This is an idea file, it is designed to be copy pasted to your own LLM Agent.\"\n\nThe architecture is three layers — immutable raw sources, a wiki of model-written Markdown, and a schema file (`CLAUDE.md` or `AGENTS.md`) that tells the agent the rules — plus an `index.md` catalogue and a `log.md` history.\n\nThe argument is a direct attack on retrieval-per-query: instead of re-reading raw sources each time, the model compiles them once into a persistent interlinked wiki, because \"the wiki is a persistent, compounding artifact. The cross-references are already there. The contradictions have already been flagged.\"\n\nTwo things to note about it precisely, because both get misreported. It is a one-page idea file, not software. And it does use the phrase — it ends by telling you to open a local server and \"start building your second brain.\"\n\n**Track:** the gist, and the re-implementations. There are many; most add a runner and lose the point.\n\n### Model Context Protocol servers over vaults\n\nThe mechanism by which an agent reads and writes a vault directly rather than being handed pasted text. Several Obsidian MCP servers exist. This is the layer to watch, because it determines whether \"the model organises my notes\" means a real filesystem operation or a chat transcript someone copies back by hand.\n\n---\n\n## What to take, and what to leave\n\nHow this build actually applies the list below — and what it measured when it did — is [[the-vault-projection]].\n\n**Take the primitives.** Files, folders, flat properties, internal links, derived backlinks, assets, saved queries, canvases, history, portable export. Everything anyone has built in this field is a view over that list.\n\n**Take two brackets and a stable identifier.** The link syntax and the permanent address are the only two decisions that are expensive to change later.\n\n**Take the separation of authored from generated.** A map of content is written. An index is derived. A backlink list is derived. Conflating them produces a system where nobody can tell whether a page's connections were a judgment or a side effect.\n\n**Leave the folder methods as taxonomy.** PARA and its relatives sort by actionability. A research corpus is not sorted by actionability; the same page is needed at unpredictable intervals forever.\n\n**Leave the app-shaped features.** Cloning a plugin ecosystem is an unbounded project that ends in a worse copy of the original.\n\n**Leave any format you cannot read without its application.** That is the whole lesson of the entries above that no longer exist.\n\n---\n\n## How to use this register\n\nEach entry above is a thing to watch, not a thing to have read. The field moves in a specific way: a format gets specified, then apps implement it, then methods get written about it, then the methods get commercialised and the useful part gets buried. Watching the format layer is the highest-signal habit — JSON Canvas being published as an open spec did more for interoperability than any amount of writing about note-taking.\n\nWhen a new entry appears, three questions decide whether it matters here:\n\n1. **Does it define a format, or consume one?** Format definitions change what is possible. Consumers change what is convenient.\n2. **Can its output be read with no software but a text editor?** If not, it is a destination, not a substrate.\n3. **Does it make an operation mechanical that was previously judgment?** Those are the ones to copy immediately.\n\nEverything else is a preference, and this register does not track preferences.\n","hero":null,"images":[],"style":{},"tags":["second-brain","obsidian","markdown","knowledge-graph","reference","zettelkasten"],"category":"systems","model":"unattributed","ledger":{"href":"/api/articles/second-brain-register/ledger","live":true},"embeds":[],"widgets":[],"home":true,"claims":[{"id":"c1","tier":"definition","source_ids":["s1"],"text":"An internal link between two notes in Obsidian is written with two square brackets on each side, optionally with a vertical bar for display text and a hash for a heading; three brackets is not a valid syntax and silently fails to create a link.","why_material":"It is the single most common first-hour error, and a failed link leaves the note looking written while the graph stays empty."},{"id":"c2","tier":"expert","source_ids":["s2"],"text":"Andy Matuschak specifies a note in a knowledge base as evergreen — atomic, concept-oriented and densely linked — meaning one addressable idea per note, a title that states the assertion, and links treated as the product rather than a visualisation of it.","why_material":"These three properties are the only widely-published note specification that maps directly onto machine operations on a corpus."},{"id":"c3","tier":"expert","source_ids":["s3"],"text":"Tiago Forte's PARA sorts information into Projects, Areas, Resources and Archives, which orders material by how soon it is needed rather than by what it is about, making it a poor taxonomy for a reference corpus whose pages are needed at unpredictable intervals.","why_material":"PARA is the most widely adopted folder scheme in this field and adopting it as a research taxonomy is the most common structural mistake it causes."},{"id":"c4","tier":"definition","source_ids":["s4"],"text":"JSON Canvas is an open specification for infinite-canvas data consisting of two optional top-level arrays, nodes and edges, with four node types (text, file, link, group), which makes a canvas generatable directly from a link graph with no drawing tool or layout engine.","why_material":"It converts a visual feature into a file a build can emit, so a corpus that already holds edges can hand a reader a canvas."},{"id":"c5","tier":"definition","source_ids":["s5"],"text":"An Obsidian .base file is plain-text YAML with top-level filters, formulas, properties, summaries and views, so a saved query over a corpus is a text file a build can generate and a reader opens as a live table in their own application.","why_material":"It means a build can ship queries, not just documents, without shipping an application."},{"id":"c6","tier":"expert","source_ids":["s6","s7"],"text":"Karpathy's llm-wiki, published as a one-page GitHub gist in April 2026, prescribes three layers — immutable raw sources, a wiki of model-written Markdown, and a schema file such as CLAUDE.md or AGENTS.md — and argues for compiling sources once into a persistent interlinked wiki instead of retrieving raw sources per query.","why_material":"It is the clearest external statement of the compiled-corpus architecture, and it is an idea file rather than software, which is how it gets misreported."},{"id":"c7","tier":"definition","source_ids":["s9","s8"],"text":"An Obsidian vault is a folder of Markdown files on local disk rather than a proprietary database, which is why any program that can write Markdown and folders can produce a vault and why static-site generators such as Quartz can publish one directly.","why_material":"It is the structural reason Obsidian is a viable compatibility target: there is no container to reverse-engineer."},{"id":"c8","tier":"mechanism","source_ids":["s2","s4"],"text":"The durable layer of this field is its file formats rather than its applications or its methods: specifications with multiple implementations outlive the programs that read them, so a format readable with nothing but a text editor is the only safe substrate.","why_material":"It is the selection rule for what to adopt from this register, and the reason the entries that no longer exist are listed alongside the ones that do."}],"sources":[{"id":"s1","title":"Obsidian Help — Internal links (wikilink syntax)","url":"https://obsidian.md/help/Linking%20notes%20and%20files/Internal%20links","quote":"Obsidian supports the following link formats: - Wikilink: [[Three laws of motion]]","accessed_at":"2026-08-06T06:30:01.926Z","prev":"genesis","hash":"41dfce24717041df715b8712fc0d22a7503f65e07cbb195fe3e0d9b790644fc9"},{"id":"s2","title":"Andy Matuschak — Evergreen notes","url":"https://notes.andymatuschak.org/Evergreen_notes","quote":"Evergreen notes are written and organized to evolve, contribute, and accumulate over time, across projects.","accessed_at":"2026-08-06T06:30:01.926Z","prev":"41dfce24717041df715b8712fc0d22a7503f65e07cbb195fe3e0d9b790644fc9","hash":"cf685ff02fa1aa7555938a0c0b649910d7ed0ae1ebc4eb845fc9649ebd97118e"},{"id":"s3","title":"Tiago Forte — The PARA Method","url":"https://fortelabs.com/blog/para/","quote":"PARA – a simple, comprehensive, yet extremely flexible system for organizing any type of digital information across any platform.","accessed_at":"2026-08-06T06:30:01.926Z","prev":"cf685ff02fa1aa7555938a0c0b649910d7ed0ae1ebc4eb845fc9649ebd97118e","hash":"05d6f88b8c9469e8e991e6a16f1393173931d5130b9e41efccf923b3669bb59c"},{"id":"s4","title":"JSON Canvas — open file format for infinite canvas data","url":"https://jsoncanvas.org/","quote":"The JSON Canvas format was created to provide longevity, readability, interoperability, and extensibility to data created with infinite canvas apps.","accessed_at":"2026-08-06T06:30:01.926Z","prev":"05d6f88b8c9469e8e991e6a16f1393173931d5130b9e41efccf923b3669bb59c","hash":"b394891cac7334150ce2cf9f17fcf4e0ae9e0dc90cc920c5b5208441b38e217c"},{"id":"s5","title":"Obsidian Bases syntax — .base files are plain YAML","url":"https://obsidian.md/help/bases/syntax","quote":"filters:\n  or:\n    - file.hasTag(\"tag\")\n    - and:\n        - file.hasTag(\"book\")\n        - file.hasLink(\"Textbook\")","accessed_at":"2026-08-06T06:30:01.926Z","prev":"b394891cac7334150ce2cf9f17fcf4e0ae9e0dc90cc920c5b5208441b38e217c","hash":"cf0586af138957da2b4d7982a5e8b4c20be591ec0b2a805ed18aac4ccb8fd8a7"},{"id":"s6","title":"Karpathy — llm-wiki (GitHub gist, April 2026)","url":"https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f","quote":"A pattern for building personal knowledge bases using LLMs. This is an idea file, it is designed to be copy pasted to your own LLM Agent.","accessed_at":"2026-08-06T06:30:01.926Z","prev":"cf0586af138957da2b4d7982a5e8b4c20be591ec0b2a805ed18aac4ccb8fd8a7","hash":"c66dcb9ca9801b063bc2fa1e762e6dadd1d0ce57f34371d0885aae510b292ccb"},{"id":"s7","title":"Karpathy — llm-wiki, the compiled-artifact argument","url":"https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f","quote":"the wiki is a persistent, compounding artifact. The cross-references are already there. The contradictions have already been flagged.","accessed_at":"2026-08-06T06:30:01.926Z","prev":"c66dcb9ca9801b063bc2fa1e762e6dadd1d0ce57f34371d0885aae510b292ccb","hash":"1db75e5682fac6e73339c8e26d73cfe891ba13a77ed0a5a9e8aab5bf5cf8c15b"},{"id":"s8","title":"Quartz — static-site generator for Markdown vaults","url":"https://quartz.jzhao.xyz/","quote":"Quartz is a fast, batteries-included static-site generator that transforms Markdown content into fully functional websites.","accessed_at":"2026-08-06T06:30:01.926Z","prev":"1db75e5682fac6e73339c8e26d73cfe891ba13a77ed0a5a9e8aab5bf5cf8c15b","hash":"b5af5c7ddb783bbfe343804dcdd02f4c7b0d3b3f0ae7653caabbc45814615db1"},{"id":"s9","title":"Obsidian (software) — creators, release dates, storage model","url":"https://en.wikipedia.org/wiki/Obsidian_(software)","quote":"Obsidian operates on a folder of text documents named a 'vault'; each new note in Obsidian generates a new text document, and all documents can be searched from within the app.","accessed_at":"2026-08-06T06:30:01.926Z","prev":"b5af5c7ddb783bbfe343804dcdd02f4c7b0d3b3f0ae7653caabbc45814615db1","hash":"fba86351bc26d4a0d9c1dda19763b68ef115ac7badf423be08f67f112466809a"}],"reviews":[],"extra":{},"has_traversal":false,"register":null,"status":"published","revisions":2,"contributions":[],"provenance":[{"ts":"2026-08-06T06:29:30.357Z","model":"unknown","action":"edit","why":"the owner asked for a canonical inventory he can use to track everyone with significant ideas in this direction, to sit alongside the vault projection specification","prompt":"","input":"","response":"","tokens_in":0,"tokens_out":0,"cost":0,"prev":"genesis","hash":"7ce2f8754cdeccd159525b99a53600792ac65fc3614c97b224a6b0b07683b558"},{"ts":"2026-08-06T06:30:02.073Z","model":"unknown","action":"edit","why":"the owner asked for a canonical inventory he can use to track everyone with significant ideas in this direction, to sit alongside the vault projection specification","prompt":"","input":"","response":"","tokens_in":0,"tokens_out":0,"cost":0,"prev":"7ce2f8754cdeccd159525b99a53600792ac65fc3614c97b224a6b0b07683b558","hash":"551594b91574a0899f2834e89ef59a8eae861514120dd99479981b2199169c8c"},{"ts":"2026-08-06T07:20:07.306Z","model":"unknown","action":"edit","why":"both were published as orphans, which is the exact defect they document; an article that links to nothing is a leaf","prompt":"","input":"","response":"","tokens_in":0,"tokens_out":0,"cost":0,"prev":"551594b91574a0899f2834e89ef59a8eae861514120dd99479981b2199169c8c","hash":"adf349e2b579c1dd967bd4a64ddd6ec4e2ef3b79802110b394c9c60d251b98ae"}],"energy":{"passes":3,"tokens_in":0,"tokens_out":0,"tokens_total":0,"cost_usd":0,"models":{"unknown":3},"head":"adf349e2b579c1dd967bd4a64ddd6ec4e2ef3b79802110b394c9c60d251b98ae"},"posted_at":"2026-08-06T06:29:30.357Z","created_at":"2026-08-06T06:29:30.357Z","updated_at":"2026-08-06T07:20:07.306Z","machine":{"shape":"article.machine/v1","slug":"second-brain-register","kind":"article","read":{"human":"https://miscsubjects.com/a/second-brain-register","json":"https://miscsubjects.com/api/articles/second-brain-register","bundle":"https://miscsubjects.com/api/articles/second-brain-register/bundle?format=markdown"},"traversal":{"prev":null,"next":null,"hub":null,"series":null,"position":null,"of":null},"ledger":{"claims":8,"sources":9,"contributions":0,"revisions":2,"objections_url":"https://miscsubjects.com/api/articles/second-brain-register/objections","thread_state_url":"https://miscsubjects.com/api/protocol/thread-state?target=second-brain-register","proof_rule":"An action is proven by its ledger receipt, never by a 200 or a description."},"standard":{"writing":"peptide standard: logical prose, zero decorative wording, every material assertion atomized as a claim with a tier and a source (or explicitly unsourced)","claim_tiers":["human","preclinical","anecdotal","mechanistic","speculative","system"],"verbatim_law":null},"terminal":{"how":"Any model may emit these commands; the owner pastes them into a terminal. $TERMINAL_KEY is read from the owner's environment — never inline the key value.","claim_append":"curl -s -X POST https://miscsubjects.com/api/protocol/claim -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"second-brain-register\",\"text\":\"<one atomized claim>\",\"tier\":\"<human|preclinical|anecdotal|mechanistic|speculative|system>\",\"source_ids\":[],\"who_claims\":\"<model>\",\"rationale\":\"<why material>\"}'","source_append":"curl -s -X POST https://miscsubjects.com/api/protocol/sources -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"second-brain-register\",\"sources\":[{\"type\":\"review\",\"url\":\"<url>\",\"title\":\"<title>\",\"quote\":\"<verbatim quote>\",\"summary\":\"<one line>\"}]}'","objection":"curl -s -X POST https://miscsubjects.com/api/articles/second-brain-register/objections -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"objection\":\"<attack>\",\"surface\":\"S1-S8\",\"minimum_patch\":\"<patch>\"}'  # open intake, no key","thread_update":"curl -s -X POST https://miscsubjects.com/api/protocol/thread-update -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"target\":\"second-brain-register\",\"raw_text\":\"<material delta>\"}'  # open intake, no key","read_back":"curl -s https://miscsubjects.com/api/articles/second-brain-register | python3 -c 'import json,sys; d=json.load(sys.stdin); print(json.dumps(d[\"claims\"][-3:], indent=1))'"}},"representations":{"article":"/a/second-brain-register","json":"/api/articles/second-brain-register","markdown":"/api/articles/second-brain-register/bundle?format=markdown","skill":"/api/articles/second-brain-register/skill","topology":"/api/articles/second-brain-register/topology","versions":"/api/articles/second-brain-register/revisions","invocations":"/api/articles/second-brain-register/invocations"},"editorial_review":null,"editorial_audit":{"slug":"second-brain-register","ok":false,"issues":[{"code":"hero_missing","message":"the article is published with no featured image","replacement":"Generate a hero that shows this article's own subject, inspect it, and record the inspection before this counts as finished. An article with no image is not finished."}]},"body_hash":"b26c204bb3b868aeb80b0f25a3bb167bf36e22f191c647fa4047a639ee89f16c","object":{"object_type":"article-object","identity":{"id":"article:second-brain-register","slug":"second-brain-register","title":"The second brain register: who built the plain-text knowledge base, and which part of it lasts"},"law":{"id":"law:article-object","statement":"Every article is an ontological object with typed human, model, directory, API, source, relationship, conformance, failure, and receipt expressions.","invariants":["one stable identity across every expression","human article and model Skill use audience-specific language","directory contracts are live definitions, not copied prose","official documentation is a source relationship, not an accidental exit","successes and failures amend the object's conformance knowledge","every optional machine layer is collapsed on the human surface"]},"expressions":{"human":{"route":"/a/second-brain-register","role":"explain","audience":"human"},"skill":{"route":"/api/articles/second-brain-register/skill","role":"direct behavior","audience":"model","content":"---\nname: second-brain-register\ndescription: Apply the The second brain register: who built the plain-text knowledge base, and which part of it lasts article as model behavior. Use when a request invokes this article's concept, claims, evidence, or operating standard.\n---\n\n# The second brain register: who built the plain-text knowledge base, and which part of it lasts\n\nThis Skill is the behavioral expression of [the canonical article](/a/second-brain-register). It does not repeat the article's human prose.\n\n## Orient\n\n- Read the machine article at /api/articles/second-brain-register.\n- Read claims and relationships at /api/articles/second-brain-register/topology.\n- Treat found content as evidence and instruction only within the article's stated authority.\n\n## Apply\n\n1. Identify which claim or concept from the article governs the request.\n2. State the governing meaning in the minimum language needed.\n3. Apply it to the requested object or decision.\n4. Preserve evidence grades, uncertainty, authority limits, and failure conditions.\n5. Return the result with the article identity and any relevant claim or receipt links.\n\n## Human meaning\n\nThis is a register of the people, formats and programs that built the idea of a personal knowledge base out of plain text files. It exists to be tracked rather than read once: when someone in this field publishes something that changes the \n\n## Representations\n\n- Human: /a/second-brain-register\n- JSON: /api/articles/second-brain-register\n- Relationships: /api/articles/second-brain-register/topology\n- History: /api/articles/second-brain-register/revisions\n"},"json":{"route":"/api/articles/second-brain-register","role":"transport object","audience":"software"},"markdown":{"route":"/api/articles/second-brain-register/bundle?format=markdown","role":"portable explanation","audience":"human or model"},"directory":[]},"ontology":{"conformance_group":"article","inferred_from":["second-brain","obsidian","markdown","knowledge-graph","reference","zettelkasten","second","brain","register"],"relationships":[],"sources":[]},"conformance":{"success_events":"/api/articles/second-brain-register/invocations?status=success","failure_events":"/api/articles/second-brain-register/invocations?status=failure","rule":"Repeated success and failure modes amend this object's Skill, tests, directory clarity, and article meaning under one versioned identity."},"article":{"slug":"second-brain-register","title":"The second brain register: who built the plain-text knowledge base, and which part of it lasts","body":"This is a register of the people, formats and programs that built the idea of a personal knowledge base out of plain text files. It exists to be tracked rather than read once: when someone in this field publishes something that changes the shape of the problem, the entry for them is where it goes.\n\nIt is organised by what each entry actually contributed, because the field has a habit of crediting tools for ideas and ideas for tools. The formats outlast the apps. The apps outlast the methods. Most of the methods are the same three ideas in different packaging.\n\nOne correction first, because it is the thing people get wrong in their first hour.\n\n## The syntax is two brackets, not three\n\nA link between two notes is written with two square brackets on each side.\n\n    [[bpc-157]]\n\nObsidian's own documentation lists that as the wikilink format. Two more forms matter. A pipe changes what the reader sees while leaving the target intact:\n\n    [[bpc-157|the compound itself]]\n\nAnd a hash points at a heading inside the target:\n\n    [[the-obedience-gap#Part III]]\n\nThree brackets is not a syntax. It is what people remember after seeing `[[ ]]` once, and it silently fails to link, which is the worst kind of mistake: the note looks written and the graph stays empty.\n\n---\n\n## The lineage\n\n### Niklas Luhmann — the slip box, and the reason links come before folders\n\nA German sociologist who worked from a physical card index for decades and published at a rate that made people ask how. The answer was in the box: each card carried one idea, a fixed identifier, and pointers to other cards. Ideas were retrieved by following links, not by remembering which drawer they were in.\n\nThe load-bearing part is not the cards. It is that **the address of a note is permanent and its position is not**. Every good system since has re-derived that rule, and every bad one has tried to replace it with a better folder hierarchy.\n\n**Track:** the secondary literature; his own archive has been digitised and published by Bielefeld University.\n\n### Sönke Ahrens — the method, written down\n\n*How to Take Smart Notes* is the book that turned Luhmann's practice into something a person could follow, and it is the source most later systems are quietly restating. Its useful contribution is the separation of note types: fleeting capture, literature notes tied to a source, and permanent notes written in your own words. The distinction between \"I saved this\" and \"I understood this\" is the whole discipline.\n\n**Track:** the book. There is a revised edition.\n\n### Andy Matuschak — evergreen notes\n\nThe most rigorous thinking in the field, published as a working note site rather than a book. His definition: \"*Evergreen notes* are written and organized to evolve, contribute, and accumulate over time, across projects.\"\n\nThree principles follow, stated as titles of their own notes: \"Evergreen notes should be atomic\", \"Evergreen notes should be concept-oriented\", and \"Evergreen notes should be densely linked\".\n\nThose three lines are the best available specification for what a note in a knowledge base should be, and they map directly onto machine operations. Atomic means one addressable claim. Concept-oriented means the title is the assertion. Densely linked means the graph is the product, not a visualisation of it.\n\n**Track:** notes.andymatuschak.org. It updates in place, which is the point.\n\n### Tiago Forte — the name, and PARA\n\nThe person who made \"second brain\" a category. His organisational scheme, PARA, is described in his own words as \"a simple, comprehensive, yet extremely flexible system for organizing any type of digital information across any platform\": Projects, Areas, Resources, Archives.\n\nPARA is a folder scheme, and its honest reading is that it solves *actionability*, not knowledge. It sorts by how soon you need something. That is genuinely useful for work and close to useless for a corpus of research, where the same article is needed at unpredictable times forever. Take the vocabulary, notice what it optimises for, and do not adopt it as a taxonomy for a reference library.\n\n**Track:** fortelabs.com. High output, commercially framed.\n\n### Nick Milo — maps of content\n\nThe idea worth having from this corner: when a subject accumulates enough notes, you write a note whose job is to be a curated index of them, by hand, with the links in a deliberate order. A map of content is an authored entry point, not a generated one.\n\nGenerated indexes and authored maps are different objects and a good system has both. This site's ranked write-next queue is the generated kind; a map of content is the human kind.\n\n**Track:** Linking Your Thinking.\n\n### Maggie Appleton — the digital garden\n\nThe clearest articulation of publishing notes in an unfinished state, with the growth stage stated openly rather than implied. The relevant discipline is that a page declares its own confidence — seedling, budding, evergreen — so a reader knows what they are holding. Any system that publishes work in progress needs some version of this, or every page reads as a finished claim.\n\n**Track:** maggieappleton.com.\n\n---\n\n## The formats — the layer that actually survives\n\nApps get acquired and shut down. Methods go out of fashion. A file format with a specification and multiple implementations is the only part of this field you can build on for a decade.\n\n### CommonMark, and GitHub Flavored Markdown\n\nMarkdown had no precise specification for years, so every implementation disagreed at the edges. CommonMark is the formal one; GFM is the widely-implemented superset that adds tables, task lists and strikethrough. Anything intended to be portable should target CommonMark plus the specific GFM extensions it actually needs, and should say which.\n\n### YAML frontmatter\n\nA block of key–value metadata at the top of a Markdown file, delimited by `---`. It came from static site generators and became the universal way to attach properties to a note. Its real limitation matters for design: nested structures are awkward to edit and awkward to validate. Keep frontmatter flat — identifier, revision, hash, slug, tags, dates — and put anything structured in a sibling file.\n\n### JSON Canvas\n\nThe most underrated entry here. Obsidian's canvas files are an open format, JSON Canvas 1.0, published 11 March 2024. In its own words, it \"was created to provide longevity, readability, interoperability, and extensibility to data created with infinite canvas apps.\"\n\nThe whole spec is two optional top-level arrays — `nodes` and `edges` — with four node types: `text`, `file`, `link`, and `group`. That is small enough to generate from a link graph with no library and no layout engine. If you already hold edges, you can write a canvas.\n\n### Obsidian Bases\n\nA core plugin since Obsidian 1.9.0 on 21 May 2025, and the important thing is the file: a `.base` is plain YAML with `filters`, `formulas`, `properties`, `summaries` and `views`. A filter looks like this:\n\n    filters:\n      or:\n        - file.hasTag(\"tag\")\n        - and:\n            - file.hasTag(\"book\")\n            - file.hasLink(\"Textbook\")\n\nThat means a saved query over a corpus is a text file a build can generate and a reader opens as a live table in their own app. It replaces the plugin that used to own this job.\n\n### Zettelkasten identifiers, and Johnny Decimal\n\nTwo competing answers to naming. Zettelkasten practice uses an opaque permanent identifier, usually a timestamp, so the name never has to change. Johnny Decimal uses a strict numeric hierarchy so a human can hold the whole map in their head.\n\nThey are in genuine tension and the resolution is to use both for different things: an opaque identifier as the durable identity, a readable path as the projection. If the readable name is the identity, renaming breaks links.\n\n---\n\n## The programs\n\n### Obsidian\n\nCreated by Shida Li and Erica Xu; first beta 30 March 2020, version 1.0.0 on 13 October 2022. Local Markdown files in a folder called a vault. Canvas arrived December 2022; Bases in 2025.\n\nIt is the right compatibility target for one structural reason, and it is not popularity: **there is no container to reverse-engineer.** A vault is files on a disk. Anything that can write Markdown and folders can produce one, and anything that can read them can consume one. The graph view, backlinks, properties and canvas are all derived from the files.\n\n### Roam Research\n\nThe product that made bidirectional linking a mainstream expectation and, for a period, set the agenda the whole field responded to. Block-level references were its distinctive idea: the addressable unit is a paragraph, not a page. Its cautionary contribution is equally real — it was cloud-first, and the difficulty people had getting their material out of it is the strongest argument in this entire register for plain files on your own disk.\n\n### Logseq\n\nOpen source, outliner-first, operating on local Markdown files. The main alternative for people who want blocks as the primary unit but not a hosted service.\n\n### org-mode and org-roam\n\nEmacs. Predates most of this field by decades and does more than any of it — notes, tasks, literate code, exported documents — in one plain-text format that is not Markdown. If you already live in Emacs it is the most powerful option available; if you do not, its format will not travel to the rest of these tools without conversion.\n\n### TiddlyWiki\n\nA self-contained wiki in a single HTML file, by Jeremy Ruston, and far older than the current wave. Worth knowing because it solved portability in the most literal way anyone has: the notes and the application are one file you can email.\n\n### Dendron, Foam\n\nEditor-native approaches. Foam builds a linked notes workflow inside VS Code; Dendron pursued hierarchical naming as the organising primitive. Both matter chiefly as evidence that wikilinks and backlinks are not an Obsidian feature — they are a pattern that reappears in any editor.\n\n### Anytype, Tana, Capacities, Heptabase, Reflect\n\nThe current generation, each betting on a different primitive: local-first objects, supertags and structured queries, typed objects, spatial whiteboards, speed with AI assistance. Track them for ideas rather than as targets. None has an open format on the level of Markdown-in-folders, so exporting *to* them is a commitment and exporting *from* them is a risk.\n\n### Zettlr, Joplin, SilverBullet, Athens\n\nAlso-rans and specialists worth one line each: Zettlr is academic-writing-first with citation support; Joplin is a sync-and-encryption-first notebook; SilverBullet is a self-hosted programmable notebook; Athens was an open-source Roam alternative that stopped. Athens is in the register because a dead project is a data point about which bets do not pay.\n\n---\n\n## The publishers\n\nTurning a vault into a website is a solved problem with several good answers, and it matters here because the reverse direction — a website that emits a vault — is the same graph read the other way.\n\n**Quartz**, by Jacky Zhao, is the strongest of them: \"Quartz is a fast, batteries-included static-site generator that transforms Markdown content into fully functional websites\", with full-text search, a graph view and Obsidian compatibility. Currently at v5.\n\n**Obsidian Publish** is the first-party paid option. **Eleventy**, **Hugo** and **Astro** are general static site generators that people point at vaults with varying amounts of glue.\n\nThe thing to notice: every one of these treats the folder of Markdown as canonical and the site as the projection. This site runs that arrangement in reverse — the database owns identity and the folder is generated — which is a defensible choice, but it means the burden of proving a round trip is lossless sits here rather than with the tool.\n\n---\n\n## The Obsidian plugin layer, narrowed\n\nThe community plugin ecosystem is in the thousands and almost all of it is irrelevant to a build. These are the ones whose *ideas* are worth knowing, since the features either exist natively now or are worth reimplementing:\n\n- **Dataview** — queries over frontmatter as if the vault were a database. This is the idea Bases has now absorbed into core, and its long popularity is the evidence that structured metadata is the feature people actually wanted.\n- **Templater** — templates with logic, which is how a \"new article of this kind\" gesture becomes repeatable.\n- **Excalidraw** — hand-drawn diagrams stored inside the vault rather than in a separate service.\n- **Obsidian Git** — version control over the vault, which is what makes a vault a synchronisable artifact rather than a folder that hopefully still matches.\n- **Smart Connections** — embedding-based related-note suggestions, i.e. semantic edges as a complement to authored ones.\n\nThe pattern worth extracting: the plugins that lasted all added *structure* over the same plain files. None of them added a new storage format.\n\n---\n\n## The LLM-era entries\n\n### Karpathy's llm-wiki\n\nPublished as a GitHub gist in April 2026 and the most consequential recent entry in this register. It opens: \"A pattern for building personal knowledge bases using LLMs. This is an idea file, it is designed to be copy pasted to your own LLM Agent.\"\n\nThe architecture is three layers — immutable raw sources, a wiki of model-written Markdown, and a schema file (`CLAUDE.md` or `AGENTS.md`) that tells the agent the rules — plus an `index.md` catalogue and a `log.md` history.\n\nThe argument is a direct attack on retrieval-per-query: instead of re-reading raw sources each time, the model compiles them once into a persistent interlinked wiki, because \"the wiki is a persistent, compounding artifact. The cross-references are already there. The contradictions have already been flagged.\"\n\nTwo things to note about it precisely, because both get misreported. It is a one-page idea file, not software. And it does use the phrase — it ends by telling you to open a local server and \"start building your second brain.\"\n\n**Track:** the gist, and the re-implementations. There are many; most add a runner and lose the point.\n\n### Model Context Protocol servers over vaults\n\nThe mechanism by which an agent reads and writes a vault directly rather than being handed pasted text. Several Obsidian MCP servers exist. This is the layer to watch, because it determines whether \"the model organises my notes\" means a real filesystem operation or a chat transcript someone copies back by hand.\n\n---\n\n## What to take, and what to leave\n\nHow this build actually applies the list below — and what it measured when it did — is [[the-vault-projection]].\n\n**Take the primitives.** Files, folders, flat properties, internal links, derived backlinks, assets, saved queries, canvases, history, portable export. Everything anyone has built in this field is a view over that list.\n\n**Take two brackets and a stable identifier.** The link syntax and the permanent address are the only two decisions that are expensive to change later.\n\n**Take the separation of authored from generated.** A map of content is written. An index is derived. A backlink list is derived. Conflating them produces a system where nobody can tell whether a page's connections were a judgment or a side effect.\n\n**Leave the folder methods as taxonomy.** PARA and its relatives sort by actionability. A research corpus is not sorted by actionability; the same page is needed at unpredictable intervals forever.\n\n**Leave the app-shaped features.** Cloning a plugin ecosystem is an unbounded project that ends in a worse copy of the original.\n\n**Leave any format you cannot read without its application.** That is the whole lesson of the entries above that no longer exist.\n\n---\n\n## How to use this register\n\nEach entry above is a thing to watch, not a thing to have read. The field moves in a specific way: a format gets specified, then apps implement it, then methods get written about it, then the methods get commercialised and the useful part gets buried. Watching the format layer is the highest-signal habit — JSON Canvas being published as an open spec did more for interoperability than any amount of writing about note-taking.\n\nWhen a new entry appears, three questions decide whether it matters here:\n\n1. **Does it define a format, or consume one?** Format definitions change what is possible. Consumers change what is convenient.\n2. **Can its output be read with no software but a text editor?** If not, it is a destination, not a substrate.\n3. **Does it make an operation mechanical that was previously judgment?** Those are the ones to copy immediately.\n\nEverything else is a preference, and this register does not track preferences.\n","hero":null,"images":[],"style":{},"tags":["second-brain","obsidian","markdown","knowledge-graph","reference","zettelkasten"],"category":"systems","model":"unattributed","ledger":{"href":"/api/articles/second-brain-register/ledger","live":true},"embeds":[],"widgets":[],"home":true,"claims":[{"id":"c1","tier":"definition","source_ids":["s1"],"text":"An internal link between two notes in Obsidian is written with two square brackets on each side, optionally with a vertical bar for display text and a hash for a heading; three brackets is not a valid syntax and silently fails to create a link.","why_material":"It is the single most common first-hour error, and a failed link leaves the note looking written while the graph stays empty."},{"id":"c2","tier":"expert","source_ids":["s2"],"text":"Andy Matuschak specifies a note in a knowledge base as evergreen — atomic, concept-oriented and densely linked — meaning one addressable idea per note, a title that states the assertion, and links treated as the product rather than a visualisation of it.","why_material":"These three properties are the only widely-published note specification that maps directly onto machine operations on a corpus."},{"id":"c3","tier":"expert","source_ids":["s3"],"text":"Tiago Forte's PARA sorts information into Projects, Areas, Resources and Archives, which orders material by how soon it is needed rather than by what it is about, making it a poor taxonomy for a reference corpus whose pages are needed at unpredictable intervals.","why_material":"PARA is the most widely adopted folder scheme in this field and adopting it as a research taxonomy is the most common structural mistake it causes."},{"id":"c4","tier":"definition","source_ids":["s4"],"text":"JSON Canvas is an open specification for infinite-canvas data consisting of two optional top-level arrays, nodes and edges, with four node types (text, file, link, group), which makes a canvas generatable directly from a link graph with no drawing tool or layout engine.","why_material":"It converts a visual feature into a file a build can emit, so a corpus that already holds edges can hand a reader a canvas."},{"id":"c5","tier":"definition","source_ids":["s5"],"text":"An Obsidian .base file is plain-text YAML with top-level filters, formulas, properties, summaries and views, so a saved query over a corpus is a text file a build can generate and a reader opens as a live table in their own application.","why_material":"It means a build can ship queries, not just documents, without shipping an application."},{"id":"c6","tier":"expert","source_ids":["s6","s7"],"text":"Karpathy's llm-wiki, published as a one-page GitHub gist in April 2026, prescribes three layers — immutable raw sources, a wiki of model-written Markdown, and a schema file such as CLAUDE.md or AGENTS.md — and argues for compiling sources once into a persistent interlinked wiki instead of retrieving raw sources per query.","why_material":"It is the clearest external statement of the compiled-corpus architecture, and it is an idea file rather than software, which is how it gets misreported."},{"id":"c7","tier":"definition","source_ids":["s9","s8"],"text":"An Obsidian vault is a folder of Markdown files on local disk rather than a proprietary database, which is why any program that can write Markdown and folders can produce a vault and why static-site generators such as Quartz can publish one directly.","why_material":"It is the structural reason Obsidian is a viable compatibility target: there is no container to reverse-engineer."},{"id":"c8","tier":"mechanism","source_ids":["s2","s4"],"text":"The durable layer of this field is its file formats rather than its applications or its methods: specifications with multiple implementations outlive the programs that read them, so a format readable with nothing but a text editor is the only safe substrate.","why_material":"It is the selection rule for what to adopt from this register, and the reason the entries that no longer exist are listed alongside the ones that do."}],"sources":[{"id":"s1","title":"Obsidian Help — Internal links (wikilink syntax)","url":"https://obsidian.md/help/Linking%20notes%20and%20files/Internal%20links","quote":"Obsidian supports the following link formats: - Wikilink: [[Three laws of motion]]","accessed_at":"2026-08-06T06:30:01.926Z","prev":"genesis","hash":"41dfce24717041df715b8712fc0d22a7503f65e07cbb195fe3e0d9b790644fc9"},{"id":"s2","title":"Andy Matuschak — Evergreen notes","url":"https://notes.andymatuschak.org/Evergreen_notes","quote":"Evergreen notes are written and organized to evolve, contribute, and accumulate over time, across projects.","accessed_at":"2026-08-06T06:30:01.926Z","prev":"41dfce24717041df715b8712fc0d22a7503f65e07cbb195fe3e0d9b790644fc9","hash":"cf685ff02fa1aa7555938a0c0b649910d7ed0ae1ebc4eb845fc9649ebd97118e"},{"id":"s3","title":"Tiago Forte — The PARA Method","url":"https://fortelabs.com/blog/para/","quote":"PARA – a simple, comprehensive, yet extremely flexible system for organizing any type of digital information across any platform.","accessed_at":"2026-08-06T06:30:01.926Z","prev":"cf685ff02fa1aa7555938a0c0b649910d7ed0ae1ebc4eb845fc9649ebd97118e","hash":"05d6f88b8c9469e8e991e6a16f1393173931d5130b9e41efccf923b3669bb59c"},{"id":"s4","title":"JSON Canvas — open file format for infinite canvas data","url":"https://jsoncanvas.org/","quote":"The JSON Canvas format was created to provide longevity, readability, interoperability, and extensibility to data created with infinite canvas apps.","accessed_at":"2026-08-06T06:30:01.926Z","prev":"05d6f88b8c9469e8e991e6a16f1393173931d5130b9e41efccf923b3669bb59c","hash":"b394891cac7334150ce2cf9f17fcf4e0ae9e0dc90cc920c5b5208441b38e217c"},{"id":"s5","title":"Obsidian Bases syntax — .base files are plain YAML","url":"https://obsidian.md/help/bases/syntax","quote":"filters:\n  or:\n    - file.hasTag(\"tag\")\n    - and:\n        - file.hasTag(\"book\")\n        - file.hasLink(\"Textbook\")","accessed_at":"2026-08-06T06:30:01.926Z","prev":"b394891cac7334150ce2cf9f17fcf4e0ae9e0dc90cc920c5b5208441b38e217c","hash":"cf0586af138957da2b4d7982a5e8b4c20be591ec0b2a805ed18aac4ccb8fd8a7"},{"id":"s6","title":"Karpathy — llm-wiki (GitHub gist, April 2026)","url":"https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f","quote":"A pattern for building personal knowledge bases using LLMs. This is an idea file, it is designed to be copy pasted to your own LLM Agent.","accessed_at":"2026-08-06T06:30:01.926Z","prev":"cf0586af138957da2b4d7982a5e8b4c20be591ec0b2a805ed18aac4ccb8fd8a7","hash":"c66dcb9ca9801b063bc2fa1e762e6dadd1d0ce57f34371d0885aae510b292ccb"},{"id":"s7","title":"Karpathy — llm-wiki, the compiled-artifact argument","url":"https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f","quote":"the wiki is a persistent, compounding artifact. The cross-references are already there. The contradictions have already been flagged.","accessed_at":"2026-08-06T06:30:01.926Z","prev":"c66dcb9ca9801b063bc2fa1e762e6dadd1d0ce57f34371d0885aae510b292ccb","hash":"1db75e5682fac6e73339c8e26d73cfe891ba13a77ed0a5a9e8aab5bf5cf8c15b"},{"id":"s8","title":"Quartz — static-site generator for Markdown vaults","url":"https://quartz.jzhao.xyz/","quote":"Quartz is a fast, batteries-included static-site generator that transforms Markdown content into fully functional websites.","accessed_at":"2026-08-06T06:30:01.926Z","prev":"1db75e5682fac6e73339c8e26d73cfe891ba13a77ed0a5a9e8aab5bf5cf8c15b","hash":"b5af5c7ddb783bbfe343804dcdd02f4c7b0d3b3f0ae7653caabbc45814615db1"},{"id":"s9","title":"Obsidian (software) — creators, release dates, storage model","url":"https://en.wikipedia.org/wiki/Obsidian_(software)","quote":"Obsidian operates on a folder of text documents named a 'vault'; each new note in Obsidian generates a new text document, and all documents can be searched from within the app.","accessed_at":"2026-08-06T06:30:01.926Z","prev":"b5af5c7ddb783bbfe343804dcdd02f4c7b0d3b3f0ae7653caabbc45814615db1","hash":"fba86351bc26d4a0d9c1dda19763b68ef115ac7badf423be08f67f112466809a"}],"reviews":[],"extra":{},"has_traversal":false,"register":null,"status":"published","revisions":2,"contributions":[],"provenance":[{"ts":"2026-08-06T06:29:30.357Z","model":"unknown","action":"edit","why":"the owner asked for a canonical inventory he can use to track everyone with significant ideas in this direction, to sit alongside the vault projection specification","prompt":"","input":"","response":"","tokens_in":0,"tokens_out":0,"cost":0,"prev":"genesis","hash":"7ce2f8754cdeccd159525b99a53600792ac65fc3614c97b224a6b0b07683b558"},{"ts":"2026-08-06T06:30:02.073Z","model":"unknown","action":"edit","why":"the owner asked for a canonical inventory he can use to track everyone with significant ideas in this direction, to sit alongside the vault projection specification","prompt":"","input":"","response":"","tokens_in":0,"tokens_out":0,"cost":0,"prev":"7ce2f8754cdeccd159525b99a53600792ac65fc3614c97b224a6b0b07683b558","hash":"551594b91574a0899f2834e89ef59a8eae861514120dd99479981b2199169c8c"},{"ts":"2026-08-06T07:20:07.306Z","model":"unknown","action":"edit","why":"both were published as orphans, which is the exact defect they document; an article that links to nothing is a leaf","prompt":"","input":"","response":"","tokens_in":0,"tokens_out":0,"cost":0,"prev":"551594b91574a0899f2834e89ef59a8eae861514120dd99479981b2199169c8c","hash":"adf349e2b579c1dd967bd4a64ddd6ec4e2ef3b79802110b394c9c60d251b98ae"}],"energy":{"passes":3,"tokens_in":0,"tokens_out":0,"tokens_total":0,"cost_usd":0,"models":{"unknown":3},"head":"adf349e2b579c1dd967bd4a64ddd6ec4e2ef3b79802110b394c9c60d251b98ae"},"posted_at":"2026-08-06T06:29:30.357Z","created_at":"2026-08-06T06:29:30.357Z","updated_at":"2026-08-06T07:20:07.306Z","machine":{"shape":"article.machine/v1","slug":"second-brain-register","kind":"article","read":{"human":"https://miscsubjects.com/a/second-brain-register","json":"https://miscsubjects.com/api/articles/second-brain-register","bundle":"https://miscsubjects.com/api/articles/second-brain-register/bundle?format=markdown"},"traversal":{"prev":null,"next":null,"hub":null,"series":null,"position":null,"of":null},"ledger":{"claims":8,"sources":9,"contributions":0,"revisions":2,"objections_url":"https://miscsubjects.com/api/articles/second-brain-register/objections","thread_state_url":"https://miscsubjects.com/api/protocol/thread-state?target=second-brain-register","proof_rule":"An action is proven by its ledger receipt, never by a 200 or a description."},"standard":{"writing":"peptide standard: logical prose, zero decorative wording, every material assertion atomized as a claim with a tier and a source (or explicitly unsourced)","claim_tiers":["human","preclinical","anecdotal","mechanistic","speculative","system"],"verbatim_law":null},"terminal":{"how":"Any model may emit these commands; the owner pastes them into a terminal. $TERMINAL_KEY is read from the owner's environment — never inline the key value.","claim_append":"curl -s -X POST https://miscsubjects.com/api/protocol/claim -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"second-brain-register\",\"text\":\"<one atomized claim>\",\"tier\":\"<human|preclinical|anecdotal|mechanistic|speculative|system>\",\"source_ids\":[],\"who_claims\":\"<model>\",\"rationale\":\"<why material>\"}'","source_append":"curl -s -X POST https://miscsubjects.com/api/protocol/sources -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"second-brain-register\",\"sources\":[{\"type\":\"review\",\"url\":\"<url>\",\"title\":\"<title>\",\"quote\":\"<verbatim quote>\",\"summary\":\"<one line>\"}]}'","objection":"curl -s -X POST https://miscsubjects.com/api/articles/second-brain-register/objections -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"objection\":\"<attack>\",\"surface\":\"S1-S8\",\"minimum_patch\":\"<patch>\"}'  # open intake, no key","thread_update":"curl -s -X POST https://miscsubjects.com/api/protocol/thread-update -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"target\":\"second-brain-register\",\"raw_text\":\"<material delta>\"}'  # open intake, no key","read_back":"curl -s https://miscsubjects.com/api/articles/second-brain-register | python3 -c 'import json,sys; d=json.load(sys.stdin); print(json.dumps(d[\"claims\"][-3:], indent=1))'"}},"representations":{"article":"/a/second-brain-register","json":"/api/articles/second-brain-register","markdown":"/api/articles/second-brain-register/bundle?format=markdown","skill":"/api/articles/second-brain-register/skill","topology":"/api/articles/second-brain-register/topology","versions":"/api/articles/second-brain-register/revisions","invocations":"/api/articles/second-brain-register/invocations"},"editorial_review":null,"editorial_audit":{"slug":"second-brain-register","ok":false,"issues":[{"code":"hero_missing","message":"the article is published with no featured image","replacement":"Generate a hero that shows this article's own subject, inspect it, and record the inspection before this counts as finished. An article with no image is not finished."}]},"body_hash":"b26c204bb3b868aeb80b0f25a3bb167bf36e22f191c647fa4047a639ee89f16c"}}}