# gutenberg.org with an AI agent: 1 task measured

> A real task on gutenberg.org, each in a fresh Claude Code session: Playwright MCP used 257K tokens on average, Dejo 211K the first time and 79K on every run after. Steps, calls and right answers per tool.

Canonical: https://dejo.run/sites/gutenberg-org

> For AI agents: the index of this site is https://dejo.run/llms.txt, and every page is also served as markdown (add .md to its address, or send Accept: text/markdown).

gutenberg.org is Project Gutenberg, a library of free ebooks. Claude Code (Claude Sonnet 5) did this task there in brand-new sessions. Playwright MCP used 257K tokens per task on average; Dejo 211K the first time and 79K on every run after.

## Tasks

1. "search Project Gutenberg for the book "Realmah" by Arthur Helps and tell me its release date on the site"

## Tokens and calls per task

| task | Dejo, first run | Dejo, every run after | Playwright MCP | Playwright CLI |
|---|---|---|---|---|
| 1 | 211K | 79K, 1 call(s) | 257K, 4 calls | 443K, 7 calls |

## Learned and replayed with Dejo on 2026-11-13

Steps Dejo saved:

1. go https://www.gutenberg.org/
2. fill textbox "Search books" (by name)
3. press Enter
4. click link "Realmah Sir Arthur Helps 1369 downloads" (by name)
5. answer (by position)

Replay: 5 steps in 0.9 s, answer "Oct 20, 2026".

## FAQ

### How many tokens does an AI agent use on gutenberg.org?

In our test, Claude Code with Playwright MCP used 257K tokens per task on gutenberg.org on average. Dejo used 211K the first time and 79K on every run after, 69% fewer than Playwright MCP once the task was learned.

### Can Claude Code automate gutenberg.org?

Yes. In fresh Claude Code sessions on one task there, Dejo answered 1 of 1 right, Playwright MCP 1 and Playwright CLI 1. With Dejo, a task done once is replayed later without the model reading the pages again.

## Related

- [Dejo: browser automation MCP that remembers websites](https://dejo.run/)
- [Dejo MCP server setup: install in a minute](https://dejo.run/docs)
