---
title: "Karpathy's LLM Wiki as a knowledge base | Bombos"
description: "Karpathy's LLM Wiki lets an AI agent turn raw sources into a linked Markdown wiki it maintains itself. It works well for one person; a team needs more."
image: "https://bombos.ai/assets/og-en-v2.png"
---

# What is Karpathy's LLM Wiki, and does it work as a team knowledge base?

Short answer

LLM Wiki is an idea Andrej Karpathy published as a GitHub Gist on 4 April 2026. Instead of searching raw documents on every question, an LLM agent reads each new source once and updates a persistent, interlinked Markdown wiki, which you browse in Obsidian. It works well for one person's research. For a team, questions of shared editing, permissions and many tools remain open.

*Piet Baudoin · published November 17, 2026 · November 17, 2026*

## The idea: compile once, instead of searching every time

Most AI knowledge bases work with retrieval-augmented generation (RAG): at question time, the system searches the raw documents and hands the best chunks to the model. Karpathy’s point in the gist is that the model is then “rediscovering knowledge from scratch on every question.” His alternative is to let an agent do the work up front. Each new source is read once and folded into a wiki of summaries, entity and concept pages, comparisons and an overview, which he calls “a persistent, compounding artifact.”

His own analogy: “Obsidian is the IDE; the LLM is the programmer; the wiki is the codebase.” The agent writes; the human reads, browses and asks questions.

## The three layers

| Layer | What it is | Who writes it |
| --- | --- | --- |
| Raw sources | Articles, papers, images, data. Never changed. | You collect them |
| The wiki | Linked Markdown pages: summaries, entities, concepts, an overview | The LLM, entirely |
| The instructions | A file such as CLAUDE.md or AGENTS.md describing structure, conventions and workflows | You and the LLM together |

Two files hold it together. `index.md` lists every page with a link and a one-line summary, and the agent reads it first when answering. `log.md` is an append-only record of what was ingested and when, with a fixed prefix per entry so it can be searched with simple command-line tools.

## The three operations

1.  **Ingest.** The agent reads one new source, discusses the main points with you, writes a summary page, and updates the index, the log and every related page. A single source can touch ten to fifteen pages. Karpathy prefers to ingest one source at a time and stay involved.
2.  **Query.** The agent searches the wiki and answers with citations to its pages. A good answer can be filed back as a new page, so the wiki grows from questions too.
3.  **Lint.** A periodic health check for contradictions, stale claims, orphan pages, missing concepts and missing links.

The gist names supporting tools: the Obsidian Web Clipper for collecting sources, Obsidian’s graph view, the Dataview plugin for queries over page metadata, Marp for slides, and git for version history.

## The misunderstanding: it is about Obsidian

Most coverage focuses on the Obsidian setup. The real shift is who maintains the knowledge. Karpathy argues that people abandon wikis because upkeep grows faster than their value, and that an LLM makes upkeep almost free. The format is ordinary Markdown; the method is an agent that reads, links, updates and checks. That also means the wiki is only as good as the model’s judgment: a wrong summary or a wrong link is written with the same confidence as a right one, which is why the lint step and the git history matter.

## What this means for a team

The pattern fits a researcher or a founder who curates their own sources. In a team, the open questions start where the gist stops:

-   **Who edits?** One agent owning the wiki works for one person. With five people and their agents ingesting at the same time, edits collide and someone has to review what becomes the shared truth.
-   **Who may see what?** A folder of Markdown has no per-page permissions.
-   **Which tools read it?** Claude Code and Codex can read a Markdown folder in a repository. The colleague in ChatGPT or Copilot cannot, unless someone connects it.
-   **Where do the lessons go?** The wiki compiles sources. Rules a team learns from corrections in daily work need their own path into it.

For the general approach to what such a knowledge base should contain, see [How do you build a knowledge base for AI agents?](https://bombos.ai/en/questions/team-knowledge/how-to-build-a-knowledge-base-for-ai-agents/) and for the broader picture, [What is a knowledge base in AI?](https://bombos.ai/en/questions/team-knowledge/what-is-a-knowledge-base-in-ai/)

## Where Bombos fits

An LLM Wiki works well for one person; Bombos is for the team. It is a plugin: a shared memory layer underneath every AI tool the team uses, from Claude and Codex to ChatGPT, Copilot, Grok and Cursor, that learns how your team works and shows with every answer which notes it rests on. It runs in the cloud in Europe or standalone on your own server, and one person can try it first with their own agents.

## Related questions

Is LLM Wiki a tool I can install?

No. It is an "idea file": a description you paste into an agent such as Claude Code, Codex or OpenCode, which then builds the specific setup with you. Many people have published their own implementations since.

Do I need Obsidian?

No. The wiki is plain Markdown. Karpathy uses Obsidian to read it, follow links and see the graph view, but any Markdown editor or a git repository works.

Does it replace RAG?

At moderate scale it can. Karpathy notes that an index file is enough at around 100 sources and hundreds of pages; beyond that he suggests a search tool such as qmd, a local Markdown search engine with BM25 and vector search.

Can a team use it?

Karpathy lists a business or team wiki fed by Slack, meetings and calls as one use case. The gist leaves out who may edit what, how conflicting edits are reviewed and how other AI tools read it.

## Sources

1.  [LLM Wiki (Andrej Karpathy, GitHub Gist, 4 April 2026)](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f)
2.  [How Claude remembers your project: CLAUDE.md and AGENTS.md (Claude Code docs)](https://code.claude.com/docs/en/memory)
3.  [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (Lewis et al., arXiv 2005.11401)](https://arxiv.org/abs/2005.11401)

## What does your AI forget?

1.  01You tell us which AI you use and where it keeps starting over.
2.  02We show what a shared memory changes there, on your own examples.
3.  03You keep the plan, with or without Bombos.

![Piet Baudoin](https://bombos.ai/assets/team/piet-klein.jpg)

**Piet Baudoin**You talk to Piet, from the Bombos teamDutch team from Utrecht and Nijmegen · data in Europe

## More questions about Team knowledge and AI

-   [What is a knowledge base in AI?](https://bombos.ai/en/questions/team-knowledge/what-is-a-knowledge-base-in-ai/)
-   [How do you build a knowledge base for AI agents?](https://bombos.ai/en/questions/team-knowledge/how-to-build-a-knowledge-base-for-ai-agents/)
-   [How do you set up an AI chatbot on your company knowledge base?](https://bombos.ai/en/questions/team-knowledge/ai-chatbot-with-company-knowledge-base/)
-   [How can AI help onboard a new team member?](https://bombos.ai/en/questions/team-knowledge/how-to-onboard-a-new-hire-with-ai/)
-   [What happens to your team's AI knowledge when the AI champion leaves?](https://bombos.ai/en/questions/team-knowledge/what-happens-when-your-ai-champion-leaves/)
-   [What working agreements should a team make about using AI?](https://bombos.ai/en/questions/team-knowledge/working-agreements-for-ai-in-a-team/)
-   [Claude Projects or NotebookLM for a team's documents?](https://bombos.ai/en/questions/team-knowledge/claude-projects-vs-notebooklm-for-team-documents/)
-   [How do you make company documents searchable for AI?](https://bombos.ai/en/questions/team-knowledge/how-to-make-company-documents-searchable-for-ai/)

[All questions about Team knowledge and AI →](https://bombos.ai/en/questions/team-knowledge/)


---

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://bombos.ai/#organization","name":"Bombos","url":"https://bombos.ai/","logo":"https://bombos.ai/assets/bombos-bee.png","description":"Bombos is the memory layer under every AI your team uses. One shared memory for Claude, ChatGPT, Copilot, Cursor and your own agents, that learns how you work.","sameAs":["https://www.linkedin.com/company/bombos-ai","https://www.youtube.com/@truebombos","https://www.instagram.com/truebombos/","https://bsky.app/profile/bombostrue.bsky.social","https://www.threads.com/@truebombos","https://mastodon.social/@Bombos","https://www.tiktok.com/@truebombos","https://t.me/truebombos","https://www.pinterest.com/truebombos/","https://github.com/bombos-ai","https://linktr.ee/bombos.ai","https://bombosai.substack.com","https://hashnode.com/@bombosai","https://hackernoon.com/u/bombos","https://dev.to/bombos"],"email":"info@bombos.ai","areaServed":["NL","Europe"],"knowsLanguage":["nl","en"],"contactPoint":{"@type":"ContactPoint","email":"info@bombos.ai","contactType":"sales","url":"https://bombos.ai/en/contact/","availableLanguage":["nl","en"]}},{"@type":"WebSite","@id":"https://bombos.ai/#website","name":"Bombos","url":"https://bombos.ai/","inLanguage":["nl-NL","en"],"publisher":{"@id":"https://bombos.ai/#organization"}}]}

{"@context":"https://schema.org","@type":"Article","headline":"What is Karpathy's LLM Wiki, and does it work as a team knowledge base?","description":"Karpathy's LLM Wiki lets an AI agent turn raw sources into a linked Markdown wiki it maintains itself. It works well for one person; a team needs more.","abstract":"LLM Wiki is an idea Andrej Karpathy published as a GitHub Gist on 4 April 2026. Instead of searching raw documents on every question, an LLM agent reads each new source once and updates a persistent, interlinked Markdown wiki, which you browse in Obsidian. It works well for one person's research. For a team, questions of shared editing, permissions and many tools remain open.","datePublished":"2026-11-17T00:00:00.000Z","dateModified":"2026-11-17T00:00:00.000Z","author":{"@type":"Person","name":"Piet Baudoin"},"publisher":{"@type":"Organization","@id":"https://bombos.ai/#organization","name":"Bombos","logo":{"@type":"ImageObject","url":"https://bombos.ai/assets/bombos-bee.png"}},"image":"https://bombos.ai/assets/og-en-v2.png","mainEntityOfPage":"https://bombos.ai/en/questions/team-knowledge/karpathy-llm-wiki-knowledge-base/","inLanguage":"en-US","isPartOf":{"@type":"CollectionPage","name":"Team knowledge and AI","url":"https://bombos.ai/en/questions/team-knowledge/"},"citation":[{"@type":"CreativeWork","name":"LLM Wiki (Andrej Karpathy, GitHub Gist, 4 April 2026)","url":"https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f"},{"@type":"CreativeWork","name":"How Claude remembers your project: CLAUDE.md and AGENTS.md (Claude Code docs)","url":"https://code.claude.com/docs/en/memory"},{"@type":"CreativeWork","name":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (Lewis et al., arXiv 2005.11401)","url":"https://arxiv.org/abs/2005.11401"}]}

{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Bombos","item":"https://bombos.ai/en/"},{"@type":"ListItem","position":2,"name":"Questions","item":"https://bombos.ai/en/questions/"},{"@type":"ListItem","position":3,"name":"Team knowledge and AI","item":"https://bombos.ai/en/questions/team-knowledge/"},{"@type":"ListItem","position":4,"name":"What is Karpathy's LLM Wiki, and does it work as a team knowledge base?","item":"https://bombos.ai/en/questions/team-knowledge/karpathy-llm-wiki-knowledge-base/"}]}

{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"Is LLM Wiki a tool I can install?","acceptedAnswer":{"@type":"Answer","text":"No. It is an \"idea file\": a description you paste into an agent such as Claude Code, Codex or OpenCode, which then builds the specific setup with you. Many people have published their own implementations since."}},{"@type":"Question","name":"Do I need Obsidian?","acceptedAnswer":{"@type":"Answer","text":"No. The wiki is plain Markdown. Karpathy uses Obsidian to read it, follow links and see the graph view, but any Markdown editor or a git repository works."}},{"@type":"Question","name":"Does it replace RAG?","acceptedAnswer":{"@type":"Answer","text":"At moderate scale it can. Karpathy notes that an index file is enough at around 100 sources and hundreds of pages; beyond that he suggests a search tool such as qmd, a local Markdown search engine with BM25 and vector search."}},{"@type":"Question","name":"Can a team use it?","acceptedAnswer":{"@type":"Answer","text":"Karpathy lists a business or team wiki fed by Slack, meetings and calls as one use case. The gist leaves out who may edit what, how conflicting edits are reviewed and how other AI tools read it."}}]}
```
