Karpathy's LLM wiki: what it is and how to set one up

Andrej Karpathy published an "idea file" gist, llm-wiki.md, describing a pattern in which an AI agent writes and maintains a linked markdown knowledge base from user-supplied sources, compiling synthesis at ingest time rather than re-deriving it per query as RAG does. The gist specifies a three-layer structure (a CLAUDE.md/AGENTS.md schema, index.md, and an append-only log.md) plus ingest, query and lint operations, and names Codex, Claude Code and OpenCode as agents that can build a wiki from it. Karpathy framed the workflow as "Obsidian is the IDE; the LLM is the programmer; the wiki is the codebase.

An LLM wiki is a set of linked markdown pages that an AI agent writes and keeps up to date from the sources you give it. You pick the sources and ask the questions; the agent does the summarizing, cross-referencing and filing. Andrej Karpathy described the pattern in April 2026. On 2 April 2026 Karpathy posted "LLM Knowledge Bases" on X, about using LLMs to build knowledge bases for his research topics. By late September X counted about 21.9 million views and 108,600 bookmarks on that post. On 4 April he followed up with a gist, llm-wiki.md , which he calls an "idea file": you paste it into your own agent he names Codex, Claude Code and OpenCode and the agent builds the specifics with you. The gist describes three layers: CLAUDE.md or AGENTS.md that tells the LLM how the wiki is structured and which steps to follow. You and the LLM revise it over time. Our guides to And three operations: Two files help it find its way. index.md lists every page with a one-line summary, and the LLM reads it first when answering. Karpathy says this works at about 100 sources and hundreds of pages without embedding-based search. log.md is an append-only record of ingests, queries and lint passes. He keeps the agent open on one side and Obsidian on the other, and browses the pages and the graph view as the agent edits. In his words: "Obsidian is the IDE; the LLM is the programmer; the wiki is the codebase." To see the graph of an LLM wiki someone has published on GitHub, paste the repository into the wiki graph viewer https://dexio.wiki/wiki-graph/ . Most people use LLMs with documents through retrieval RAG . You upload files, the model pulls matching chunks for each question, and it writes an answer. The gist's objection is that the model rediscovers the knowledge from scratch every time. A question that needs five documents means finding and joining the same fragments again on every ask. Nothing builds up. In an LLM wiki the synthesis happens when a source comes in. The knowledge is "compiled once and then kept current, not re-derived on every query." The cross-references are already written and the contradictions already noted. And because good answers are filed as pages, your questions add to the wiki as well as your sources. For an agent that keeps working on a subject, this is the difference between reading last week's conclusion and redoing last week's search. The gist also explains why people give up on wikis: "the maintenance burden grows faster than the value." An LLM does not get bored of that upkeep and can update 15 files in one pass. The gist is deliberately abstract. It says to share it with your agent and build a version that fits your needs together. A layout that follows it: my-wiki/ AGENTS.md the schema CLAUDE.md if you use Claude Code raw/ sources; the agent never edits these assets/ images downloaded from clipped articles wiki/ index.md every page, one line each log.md append-only history sources/ entities/ concepts/ A short schema to start from: Wiki schema Layout - raw/ holds sources. Read them. Never edit them. - wiki/ holds the pages you write, one topic per page. - Link pages with page-name . Ingest 1. Read the new file in raw/ and tell me the key points. 2. Write a summary page in wiki/sources/. 3. Update the entity and concept pages it affects. Note any claim it contradicts. 4. Add new pages to wiki/index.md with a one-line summary. 5. Append to wiki/log.md: YYYY-MM-DD ingest | Source title Query Read wiki/index.md first, then the pages it points to. Cite the pages you used. If an answer is worth keeping, file it as a new page. Lint List contradictions, stale claims, orphan pages, and concepts mentioned without a page of their own. Then tell the agent what to do. Paste in the gist and ask it to set up the wiki in this folder with you. After that, drop one source into raw/ and say "Ingest raw/that-file.md and follow AGENTS.md." Karpathy prefers to ingest one source at a time, read the summary, and steer what the agent emphasizes. When you find a rule you keep repeating, add it to the schema so the next session follows it too. The reference setup is one person, one agent and one folder. The gist does list a team use, an internal wiki fed by Slack threads, meeting transcripts and customer calls, and notes that a git repo gives you history and collaboration. Once more than one agent or machine writes to the wiki, four problems show up: index.md , log.md and up to 10 to 15 other pages. Two ingests at once, from two agents or two laptops, touch the same files. A synced folder can drop one of the saves or leave a conflicted copy; git gives you merge conflicts in prose. There are three ways to do it. A git repo. Every agent pulls before it works and commits after, under its own author name. You get history and diffs. You also get conflicts in shared files like index.md , and agents that cannot run git, such as a chat app in a browser, cannot take part. A synced folder. Easy for one person on two machines. It has the same overwrite problem with two writers at once, and it records nothing about who changed what. A hosted wiki that agents reach over MCP. One copy, so nothing to sync or merge. The server has to handle concurrent writes, history and link checks for you. Dexio https://dexio.wiki is a hosted wiki for AI agents, and it takes the third option. Agents list, read, search, write, edit, move and link markdown pages over MCP. Hermes, OpenClaw, Claude Code, Codex, Cursor, Claude and ChatGPT can all write to the same wiki. Against the failure modes above: base version the agent last read, so one agent never overwrites another's edit. wikilinks . Dexio flags links to pages that do not exist when they are written, and the graph at app.dexio.wiki shows them. page history , with the agent's name from the agent field on every change. To connect an agent that runs commands, tell it "Look at dexio.wiki and log me in." It gives you a sign-in link, you click Allow access, and it adds Dexio to its own settings. Or add the MCP server yourself: https://app.dexio.wiki/mcp over Streamable HTTP, with the header Authorization: Bearer followed by your API key. Your other agents can use the same key; each names itself on every change. Dexio is free for one person, and agents never count as members. You can download any wiki as a zip of markdown files whenever you like. Setup for each agent, step by step: Hermes https://dexio.wiki/guides/hermes-agent-memory/ , OpenClaw https://dexio.wiki/guides/openclaw-memory/ , Claude Code https://dexio.wiki/guides/claude-code-memory/ , Codex https://dexio.wiki/guides/codex-mcp/ , Cursor https://dexio.wiki/guides/cursor-mcp/ and the rest in Guides https://dexio.wiki/guides/ . A folder, a schema file and one source are all the gist asks for, so start there. When a second agent or a second machine starts writing, move the wiki to one copy that every writer shares. Originally published at dexio.wiki https://dexio.wiki/blog/llm-wiki/ .