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).

dejo

gutenberg.org with an AI agent

The short answer: gutenberg.org is Project Gutenberg, a library of free ebooks. We gave Claude Code a real task there, each in a brand-new session. With Playwright MCP a task used 257K tokens on average. With Dejo it used 211K the first time and 79K on every run after, 69% fewer, because Dejo replays a learned task without the model reading the pages again.

The task

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

What each tool used

taskDejo, first runDejo, every run afterPlaywright MCPPlaywright CLI
1211K tokens, 21 s79K tokens, 1 call, 9 s, right257K tokens, 4 calls, 22 s, right443K tokens, 7 calls, right

Calls are browser tool calls the agent made. Right or wrong is checked against the answer read off the live site before any tool ran.

Learned and replayed with Dejo on 13 November 2026

We ran the task again with Dejo on 13 November 2026, so you can see what it saves today. These are the steps Dejo kept, exactly as it reported them. Each one carries a check that it landed, and a replay walks them in plain code.

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, with no page reading. Answer: “Oct 20, 2026” (right).

How we measured

Claude Sonnet 5 at medium effort, a brand-new Claude Code session per task and tool, @playwright/mcp 0.0.80, October 2026. The full method, and the sites that blocked every tool, are on the benchmark page. Raw data: benchmark-real-2026-10-21.json, benchmark-real-2026-10-23.json, benchmark-real-2026-10-23-fixes.json, benchmark-site-memory-2026-11-10.json.

Other websites we measured

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.