The Curator

You drop a PDF, an article or a markdown file into it. It reads the document and writes a wiki: one note per entity, one per concept, one summary per source, all linked to each other. Everything stays as plain markdown in a folder on your own machine, which means you can read it, edit it, back it up and take it somewhere else.

The part that matters is the other end. It runs a built-in MCP server, so a frontier model can search and read that wiki as a tool rather than being fed a wall of pasted text. You ask a question in Claude Desktop, it goes and looks things up in your notes, and it answers with your own material and citations back to the source.

Be clear about the dependency. It needs a Google Gemini or an Anthropic API key for ingestion and the health features. There is no version of this that runs on nothing. Gemini has a free tier that comfortably covers trying it out, and realistic ongoing cost is a few euros a month.

The corpus you are reading was built and is maintained in it. Every chapter here started as notes in that graph and was edited down by hand.

So ingesting this corpus is two things at once. It gives you a queryable version of everything I have worked out, and it is a genuine first run of the tool on real material rather than on a demo file. That is a better demonstration than anything I could write about it.

On macOS, one line:

curl -fsSL https://raw.githubusercontent.com/talirezun/the-curator/main/install.sh | bash

That script is readable at the URL above. Read it before you run it, the same as you would with anyone else's install script.

On Windows and Linux, it is a manual setup: Node 18 or newer, clone the repo,npm install, node src/server.js, then openlocalhost:3333. The canonical steps are in the repo:

Manual setup for Windows, Linux and Mac

If you already have Claude Code, Cursor, OpenCode, Augment or Cline running, hand it this and let it do the work. The canonical version of this prompt lives in the User Guide in the repo, and it is mirrored here so you do not have to leave the page.

Install The Curator on this machine.

Repo: https://github.com/talirezun/the-curator

Do this:
1. Clone the repo into a sensible directory and read its README before running anything.
2. Check I have Node 18 or newer. Tell me if I do not, and stop.
3. Install dependencies and start the server.
4. Tell me the local URL to open, and what the onboarding wizard will ask me for.

Do not add an API key yourself. Tell me where to paste mine and stop there.

User Guide §20, the canonical agent install prompt

Once the MCP bridge is connected, these go straight into Claude Desktop. They are written to be worth running rather than to look impressive.

Across the Field Notes corpus, what does the author say fails most often in phase two of a build, and which sources back that up? Quote the specific passages and name the chapter each one came from.

Read the whole Field Notes corpus and find places where the author contradicts himself, or where a later chapter revises a position taken in an earlier one. List each one with both passages.

Using only the Field Notes corpus, draft the first ninety days of an AI adoption plan for a 300-person European manufacturer with no in-house ML team. Flag every point where the corpus does not actually cover the question, rather than filling the gap yourself.

Take the strongest claim in the Field Notes corpus about agent memory and argue against it. Use only evidence from the corpus itself, and say clearly where the corpus gives you nothing to argue with.

It is free and MIT licensed and I maintain it in the open. A star is how these things get found.

⭐ Star The Curator on GitHub