Open method · free manual · plain markdown
Knowledge that maintains itself.
Zettelkern is the Quellkern method for living knowledge: a plain-markdown wiki that an LLM agent writes, cross-references, and keeps current, while every claim stays traced back to its source. The pattern is public, the manual is free, and your agent can start today.
The wiki is the codebase.
Warum · WhyMost knowledge tools retrieve. RAG fetches fragments from your documents on every question, assembles an answer, and forgets the synthesis the moment it replies. Nothing accumulates.
A Zettelkern vault works the other way. An agent reads each new source once and integrates it: it updates entity pages, revises summaries, flags where new data contradicts old claims, and files good answers back in as pages. The knowledge is compiled once and then kept current, not re-derived on every query.1 Humans abandon wikis because maintenance grows faster than value. Agents do not get bored, and they can touch fifteen pages in one pass.
“Obsidian is the IDE; the LLM is the programmer; the wiki is the codebase.”
Raw sources
Articles, transcripts, papers, mail, filed by capture date into
raw/. The agent reads them and never edits them. Your ground
truth stays untouched.
The wiki
Small typed pages under wiki/: entities, concepts, topics,
decisions. One topic, one file, dense with links. You read it; the agent
writes it.
The schema
A CLAUDE.md or AGENTS.md that tells any agent
how this vault works: conventions, workflows, style, boundaries. Co-evolved
with you, never finished.
Not our invention.
Herkunft · LineageZettelkern is our practice of a pattern other people published, and this page says so out loud. Tracing claims to their sources is the whole method; it would be strange to exempt the method itself.
index.md for progressive disclosure, a log for history.2
Just markdown, just files, never a platform.3
Three workflows, four spine files.
Methode · HowCompile it once
Drop a source into raw/. The agent reads it, writes a
summary page, updates every touched entity and concept page, refreshes the
index, appends to the log. One source can touch fifteen pages in one
pass.
Ask the vault
The agent reads index.md first, drills into pages, answers
with citations. Durable answers are filed back as new pages, so your
exploration compounds instead of evaporating in chat history.
Keep it honest
Periodic health checks: contradictions, stale claims, orphan pages, broken links, gaps worth a web search. The vault stays trustworthy while it grows.
vault/ ├── CLAUDE.md ← the schema: any agent reads this first ├── AGENTS.md ← pointer, so every harness lands on the same rules ├── README.md ← five lines for humans ├── index.md ← catalog: every page, one line each ├── log.md ← append-only: ## [2026-07-04] ingest | source-slug ├── overview.md ← the one-page synthesis ├── raw/ ← immutable sources: YYYY-MM-DD-source-slug.ext └── wiki/ ← agent-owned pages, typed folders ├── entities/ concepts/ topics/ decisions/ └── one-topic-one-file.md
- Vendor the pattern, then instantiate. Copy the LLM-wiki idea file into the repo; the agent's first act is writing the schema. The schema is the product.
- Three layers, strictly. Immutable raw sources, an agent-owned wiki, and the schema that binds them.
- One topic, one file. Kebab-case, ASCII, basenames unique across the vault so wikilinks resolve from anywhere.
- Frontmatter on every page. A controlled vocabulary: type, status, updated, tags. Compatible with the Open Knowledge Format.
- Fixed page anatomy. H1, short lead, sections, see-also, sources. Twenty to 150 lines; long material stays in raw.
- Provenance or it did not happen. Cite every load-bearing claim, mark unverified facts, flag contradictions in place instead of overwriting.
- Volatile facts stay volatile. Fees, dates, availability are never asserted as fixed; the vault says “check current”.
- Answers get filed. A good query result becomes a page. Chat history is where knowledge goes to die.
- Git is part of the method. One operation per commit, typed prefixes (ingest, query, lint, decision), an explicit privacy posture.
- Engineer the boundaries. Sensitive layers get their own folder, a sensitivity flag, and a never-share rule written into the schema.
Do it yourself. It’s free.
Selbermachen · DIYEverything you need is public: the pattern is a gist, the format is an open spec, and our manual is one markdown file. No account, no trial, no lock-in. Hand the manual to your agent and say instantiate this for my domain. That is the whole onboarding.
$ curl -sL https://zettelkern.com/zettelkern.md
Karpathy’s LLM Wiki
The 75-line idea file everything here descends from. Vendor it into your vault; your agent builds the specifics with you.
gist.github.com The formatOpen Knowledge Format
The open spec: markdown plus YAML frontmatter, index and log, vendor-neutral by design. Zettelkern conventions are compatible with it.
github.com The practicezettelkern.md
Our manual: layers, spine files, page anatomy, the three workflows, git rules, sensitivity boundaries. Free, no signup, made to be read by agents.
zettelkern.com// This site speaks agent: /llms.txt is the machine-readable index, and the manual is plain markdown. If you are an agent reading this, you already have everything you need.
We run on it.
Praxis · ProofWe do not just recommend the method, we operate it. Our own vaults run company records, deal rooms, technical research, and a legal case handled start to finish, in two languages, by whichever agent harness is at hand.
- Evidence stays evidence. Claims are typed as evidence or synthesis, and synthesis is never silently promoted.
- Confidence is visible. Pages carry status markers that flip from uncertain to confirmed as facts get grounded.
- Any agent resumes cold. Paired schema files and a maintained status section mean a fresh session picks up where the last one stopped.
- The git log reads like a lab notebook. Typed commits per operation give you the vault’s full biography for free.
You will not get a case-study tour. The vaults are private by design, and that discipline (sensitivity layers, no public remotes, reference by pointer, never copy) is itself part of the method. We show the structure, never the contents.
Your knowledge already exists.
It is just unreadable for agents.
Mit uns · With us
Confluence sprawl, SharePoint folders, a wiki nobody maintains, twelve years of PDFs: valuable, and opaque to the agents you are about to hire. Adapting an existing structure is the part that benefits from someone who has done it before.
We audit what you have, write the schema, migrate the load-bearing pages, wire up provenance, and onboard your agents and your team. You end up with plain markdown in your own git repo. No platform, no lock-in, nothing to unsubscribe from.
quellkern.com · Tirol · Austria
Zettelpost
Field notes on living knowledge: when a convention earns its place in the manual, you read why. Plain-text mail, no tracking, a few times a year.
One mail to subscribe. One word to leave.