A hosted LLM wiki your agents maintain

Updated · By the Cozy team

An LLM wiki is a folder of Markdown pages that an AI agent writes and keeps current from your raw sources, instead of you. Cozy hosts that wiki for you. Every account gets a private workspace and one remote MCP endpoint, so any agent on any machine can ingest, query and lint the same pages without a local vault, tunnel or sync layer.

What the LLM wiki pattern is

In April 2026 Andrej Karpathy published the LLM Wiki idea file. It describes three layers and three operations:

His key observation is that people abandon wikis because the maintenance grows faster than the value. An agent can do the bookkeeping.

Why the local-vault version breaks down

Most tutorials build the pattern as an Obsidian vault on one laptop, plus Claude Code. That works for one person, one machine and one agent. It gets hard when:

How Cozy maps to the pattern

Karpathy's layer or operationIn Cozy
Raw sourcessources/ folder, filled by Connectors (Granola, Gmail, Google Drive, Notion, Slack, Linear and more), uploads, or the ingest API, with stable IDs, URLs and timestamps
The wikiwiki/ folder of plain Markdown with an index.md map, wikilinks, backlinks, aliases and typed relations
The schemaEditable SKILL.md files in skills/, served to agents as MCP prompts (organize, recall, maintain, dream)
Ingestcozy_ingest saves evidence; the agent then updates the pages it touches
Querycozy_context returns a page, its typed neighbors with excerpts, its evidence and warnings in one call
Lintcozy_health: broken links, duplicates, stale pages, conflicts, orphans, unsourced pages, a score and prioritized fixes
log.mdRevision history (last 50 revisions per file, restorable) and cozy_changes since any timestamp

What a hosted version adds

Cozy runs no model itself. You bring the agent, and the wiki stays plain files you can read and take with you.

Set it up

  1. Sign in at cozy.cloud. Your account gets My wiki automatically.
  2. Add https://cozy.cloud/mcp to Claude, Claude Code, Codex, ChatGPT or Cursor as a remote MCP server, then approve access on Cozy's consent page. See the Cozy MCP server guide.
  3. Ask the agent to call cozy_workspaces if you use more than one workspace. Tools use My wiki unless the agent passes a workspace.
  4. Connect a source or push some notes, then ask your agent to run the organize prompt and build wiki/index.md.

Frequently asked questions

What is an LLM wiki?

An LLM wiki is a collection of Markdown pages that an AI agent writes and maintains from your raw sources. You add sources and ask questions; the agent updates pages, links them and periodically lints the wiki for contradictions and stale claims. Andrej Karpathy described the pattern in April 2026.

Do I need Obsidian to run an LLM wiki?

No. Obsidian is a popular viewer for a local vault, but the pattern only needs Markdown files and an agent. Cozy hosts the files and exposes them over MCP, so you can use the wiki from any MCP client without a local vault.

How is an LLM wiki different from RAG?

RAG retrieves raw chunks at question time. An LLM wiki compiles sources into maintained pages ahead of time, so answers come from curated, linked, cited pages. Cozy uses lexical search over those pages and needs no embeddings.

Can several agents share one LLM wiki?

Yes. In Cozy every write includes the revision it was based on, so concurrent edits conflict instead of overwriting each other. Each agent signs in separately, with its own scopes, and can be disconnected on its own.

Give your agents a memory worth keeping

Cozy gives every account a private wiki that Claude, Codex, ChatGPT and other MCP clients can read and maintain.

Start your wiki