WhyVault
Sign indeStart for free

LLM Wiki

The LLM wiki: an encyclopedia your AI keeps for you.

Andrej Karpathy made a simple idea popular: instead of letting an AI search from scratch every time you ask, let it write a wiki from your sources and keep it up to date. Here’s why that works so well, where the DIY version gets painful, and how to start one in ten minutes.

Reading time: 9 minutesUpdated:

01

The idea: the AI writes the wiki, you read it

Picture two ways of handing your knowledge to an AI. In the first, you throw every document onto one big pile. Each time you ask something, the AI rummages through it, pulls out a few paragraphs that look relevant and builds an answer. Tomorrow, with the next question, it starts over. That’s RAG, the usual technique behind “chat with your documents”.

In the second, the AI reads each source once, carefully, and works it into a wiki: one page per source, one page per concept, links in between. When a new article arrives, it updates the pages it touches and notes where it disagrees with older sources. That’s the LLM wiki as Andrej Karpathy described it.

The roles are clear: the AI writes, you read. Your raw sources stay untouched. The wiki next to them is plain Markdown you can browse, in Obsidian for example. And one file of rules – in Claude Code that would be a CLAUDE.md – tells the agent how the wiki is organised and how to write its pages.

02

RAG or LLM wiki?

Both give an AI access to what you know. The difference is when the thinking happens.

–RAG: search on every questionLLM wiki: work it in once, keep it current
When the work happensOn every question, again and againOnce, when new material arrives
What the AI readsSnippets from raw documentsMaintained pages with a summary, sources and links
Connections across sourcesRebuilt from scratch every timeAlready on the page
ContradictionsRarely noticedWritten down while working a source in
What you can read yourselfAn index made for machinesA wiki you can browse
Best forHuge piles of documents nobody curatesYour own knowledge and topics you go deep on
When the work happens
RAG: search on every questionOn every question, again and again
LLM wiki: work it in once, keep it currentOnce, when new material arrives
What the AI reads
RAG: search on every questionSnippets from raw documents
LLM wiki: work it in once, keep it currentMaintained pages with a summary, sources and links
Connections across sources
RAG: search on every questionRebuilt from scratch every time
LLM wiki: work it in once, keep it currentAlready on the page
Contradictions
RAG: search on every questionRarely noticed
LLM wiki: work it in once, keep it currentWritten down while working a source in
What you can read yourself
RAG: search on every questionAn index made for machines
LLM wiki: work it in once, keep it currentA wiki you can browse
Best for
RAG: search on every questionHuge piles of documents nobody curates
LLM wiki: work it in once, keep it currentYour own knowledge and topics you go deep on

A well-kept wiki doesn’t need fancy retrieval. WhyVault uses full-text search – because the pages are clearly named and linked, that’s enough for the agent to find what it needs.

03

Why it works so well

Keeping a wiki was always a good idea. What’s new is that someone else does the tedious half.

  • Knowledge compounds

    Every new source makes existing pages better instead of adding one more file to the pile. After a few weeks, one page holds more than any single document.

  • The agent does the upkeep

    Summarising, linking, updating cross-references: exactly the maintenance where every second brain eventually stalls. An AI doesn’t get bored of it.

  • Better answers

    Reading a curated page beats piecing together snippets. That’s true for people, and it’s true for agents.

  • Your Markdown

    The wiki is plain .md files with [[wikilinks]]. No vendor format, no database you can’t get out of.

04

Where the DIY version gets hard

The home-built setup is quick to describe: a folder on your laptop, Obsidian for reading, Claude Code or another agent in the terminal, and a CLAUDE.md with the rules. It works – for one person on one machine.

Then it gets tricky. Claude on your phone and ChatGPT in the browser can’t reach that folder. Every tool wants its own rules file, so you keep CLAUDE.md, AGENTS.md and your Cursor rules in sync by hand. What the agent changed across twelve pages yesterday, you only see if you committed to Git first. And nothing stops it from overwriting or deleting a page.

Then come the little scripts that collect sources, rename them and file them in the right folder. With every script, your AI second brain turns a little more into a project you have to maintain.

05

An LLM wiki in WhyVault, already set up

The folders of the WhyVault template map almost one to one onto Karpathy’s setup. You don’t build anything – you just write one rules note.

0_Inbox/                     raw sources: articles, notes, transcripts
1_Knowledge/                 the wiki – flat, shared, kept by the agent
  Maps/
    Learning.md              the index: what exists, what’s missing
  Notes/
    Spaced repetition.md
    Retrieval practice.md
  Sources/
    Talk – How memory works.md
  People/
9_System/
  Identity/                  USER.md, SOUL.md, IDENTITY.md, CONTEXTS.md
  Wiki rules.md              the schema: your CLAUDE.md for every agent
0_Inbox/
Your raw sources land here. The agent reads them but doesn’t change them – and since agents can’t delete anything over MCP, every original stays put until you tidy up.
1_Knowledge/
The wiki itself. Flat and shared: one idea gets exactly one page, whichever source it came from. Sources/ holds one page per source, Notes/ one per concept.
1_Knowledge/Maps/
A map is the entry point to a topic: which pages exist and what’s still missing. It’s the index the agent reads first.
9_System/Wiki rules.md
Everything in 9_System is handed to every connected agent at the start via vault_overview. So a rules note here works like a CLAUDE.md template – except Claude, ChatGPT and Cursor all read it. More on the structure

06

How to start your LLM wiki

From an empty vault to your first source worked in, without writing any code:

  1. 1

    Create a vault and connect your agent

    Sign up, pick the WhyVault template and connect your agent using the address https://mcp.whyvault.io. Guides for every agent

  2. 2

    Write your wiki rules

    Create a note in 9_System that describes how your wiki works. Short beats complete – you can sharpen it any time.

    # Wiki rules

- Raw sources live in 0_Inbox. Never change them.
- For every new source, create a page in 1_Knowledge/Sources.
- Every concept gets a page in 1_Knowledge/Notes.
  If it already exists, extend it instead of creating a second one.
- Every claim links its source with [[Title]].
- Write contradictions under “Where they disagree”.
- The map 1_Knowledge/Maps/Learning.md is the index. Keep it current.
- Don’t move anything. Tell me which sources you’ve processed.
  3. 3

    Drop sources into the inbox

    Paste articles, meeting notes or transcripts as notes in 0_Inbox. Or tell your agent in the chat: “Save this text as a note in the inbox.”

  4. 4

    Ask the agent to work them in

    Ask your agent to process the inbox. It reads your rules first, then the sources, and creates new pages or extends existing ones.

    Read the wiki rules and work the new notes in the inbox into the wiki. Then tell me which pages you created or updated.
  5. 5

    Check the history

    Every change shows up in the history with the agent’s name, as a diff against the previous version. If something’s off, undo it with one click. More on history

  6. 6

    Ask questions

    Now your agent answers from maintained pages instead of snippets. And when an answer is good, have it saved as a page of its own – that way your questions grow the wiki too.

1_Knowledge/Notes/Spaced repetition.md
---type: notesources:  - "[[Talk – How memory works]]"  - "[[Podcast – Learning with flashcards]]"updated: 2026-09-28---# Spaced repetitionIf you review something at intervals, you keep it longer than after one long session. The gaps can grow as it sticks.## What the sources say- Each recall just before you’d forget strengthens the memory. [[Talk – How memory works]]- In daily life, that means: few cards, every day, keep it short. [[Podcast – Learning with flashcards]]## Where they disagree- The podcast relies on an app that schedules each card. The talk says a simple plan works just as well. Open.## Related- [[Retrieval practice]] – works best when you actively recall instead of rereading.- [[Learning]]

07

What a wiki page looks like

A concept page after the agent has worked in two sources:

  1. Answer first: the opening two sentences say what it’s about. Read only those and you know enough.

  2. Every claim has a source. The link leads to the source page, and from there to the original in the inbox.

  3. Contradictions stay visible. The agent doesn’t smooth them over, it writes them down. That’s exactly where your own thinking starts.

  4. Links make the web. Through [[Retrieval practice]] and the map [[Learning]], the next agent finds the connection without having to search.

08

What it feels like

After a talk, with your notes already in the inbox:

Claude

  1. You: I put my notes from the memory talk in the inbox. Work them into the wiki.

  2. Tool: vault_overview

    Claude: I’ve read your wiki rules. The notes are mostly about spaced repetition and retrieval practice – there are already pages for both.

  3. Tool: create_note · “Talk – How memory works”

    Claude: Source page created, with the three points the talk put the most weight on.

  4. Tool: update_section · “What the sources say”

    Claude: I’ve extended “Spaced repetition”. One thing stood out: the talk disagrees with the podcast about fixed intervals. That’s now under “Where they disagree”.

  5. You: So what’s the difference between spacing and retrieval?

  6. Tool: read_note · “Retrieval practice”

    Claude: Spacing is about when you study: at intervals. Retrieval is about how: from memory instead of from the page. The two pages link to each other. Want me to save that distinction as a page of its own?

Every step shows up in the history as “Claude” – and can be undone with one click.

09

Once a month: the tidy-up pass

Even a good wiki grows wild. Every now and then, ask your agent to look through it and tell you:

  • which pages link to nothing and nothing links to (that’s what get_backlinks is for),
  • where two pages contradict each other without it being noted,
  • which concepts come up often but don’t have a page yet,
  • which claims have no source,
  • whether the maps still show what exists,
  • which sources in the inbox are already processed. You do the tidying – agents can’t move or delete anything.

Don’t ask the whole library every time. Have someone write the encyclopedia.

?

Frequently asked questions

What is an LLM wiki?

A wiki of Markdown pages that an AI writes from your sources and keeps up to date. You collect material and read; the agent summarises, links and extends existing pages when something new comes in.

What does Andrej Karpathy have to do with it?

Karpathy described the pattern and made it popular: raw sources, an AI-maintained wiki next to them, and a rules file that explains the setup to the agent. WhyVault isn’t an official implementation – it’s a place where exactly that setup works without your own scripts.

Do I need Obsidian for this?

No. You read and edit your wiki in the WhyVault app. If you like Obsidian: the export is a zip that Obsidian opens directly as a vault. Obsidian and WhyVault

Does WhyVault maintain the wiki automatically in the background?

No. Your agent does the work when you ask it to – in Claude, ChatGPT, Cursor or Claude Code. If you set up scheduled tasks there, it can do it regularly; WhyVault itself has no built-in AI.

Isn’t this just RAG?

Not quite. RAG searches raw documents on every question; an LLM wiki works knowledge in once and maintains it. WhyVault doesn’t use vector search, it uses full-text search – and with a well-kept wiki of clear pages, that works well.

How much does it cost?

WhyVault is free up to 20 notes – enough to try the idea with a few sources. A growing wiki needs Pro at €9.99 a month or €99 a year, with no limit. Reading and exporting always work, even without a subscription.

All guides

Your wiki, organised from day one.

Create your vault, write your wiki rules and let Claude work in your first source. Free, no credit card.

Start for free