Books and libraries · by Project Gutenberg Literary Archive Foundation (volunteers)

Project Gutenberg

A volunteer-built library of free eBooks, mostly older works out of US copyright, offered as HTML, EPUB, Kindle and plain text, with full catalog dumps in RDF and CSV.

It is one of the largest clean, proofread corpora of classic literature, and the whole catalog and text set can be downloaded in bulk.

API, no keyDownloadCommercial: conditions

Open gutenberg.org ↗ agent.md

For your project

Official API: Official API · Free Website is for human users only; automated access only via the harvest endpoint, mirrors, feeds and catalog files (example uses wget -w 2).
“OPDS is primarily intended for machine-to-machine communication for use in applications that can present or manage the lists of content. To use Project Gutenberg’s OPDS feed, start at https://www.gutenberg.org/ebooks/search.opds/ .” gutenberg.org/ebooks/offline_catalogs.html
Key: Not needed
“100% Free - No fees, no registration, completely free” gutenberg.org/
Formats: XML
Data download: Yes rdf, xml, csv, marc, txt, epub, html
“All Project Gutenberg metadata are available digitally in the XML/RDF format. This is updated daily” gutenberg.org/ebooks/offline_catalogs.html
License: Public domain in the US (most eBooks); Project Gutenberg License / trademark terms Public-domain eBook texts and catalog metadata; the 'Project Gutenberg' trademark is restricted; non-US users must check local law
Commercial use: Commercial use with conditions
“The vast majority of Project Gutenberg eBooks are in the public domain in the US. This means that nobody can grant, or withhold, permission to do with this item as you please. “As you please” includes any commercial use, republishing in any format, making derivative works or performances, etc.” gutenberg.org/policy/permission.html
Credit: No credit needed
“It is always OK to cite Project Gutenberg as the publication source (see below for how to cite), and it is also OK to not cite Project Gutenberg: your choice.” gutenberg.org/policy/permission.html
Embedding: Can be embedded
“To link to a specific eBook, link to the landing page for that eBook, not to specific files.” gutenberg.org/policy/permission.html
Using the website: Free

Read on Project Gutenberg's own pages on Oct 23, 2026 · license or terms · API docs. Check the license page before you ship.

For your agent

A request your code or agent can make with no key:

https://www.gutenberg.org/ebooks/search.opds/?query=dickens

Never crawl gutenberg.org pages; use pg_catalog.csv or the RDF dump for metadata and /robot/harvest or a mirror for files.
Do not crawl the website; use the catalog files, harvest endpoint (wget -w 2) or a mirror.
Link to book landing pages (/ebooks/<id>), not deep links to files.
Public-domain texts are free to reuse, but commercial use of the 'Project Gutenberg' name/trademark needs royalties under its license; outside the US, check local copyright.

Paste into your agent: Read https://agentgid.com/resources/project-gutenberg/agent.md before using Project Gutenberg.

What you can build

Ask questions of a classic bookA chat assistant that answers questions about a public-domain novel and quotes the passage it used.

A reading app or e-reader store front for public-domain classics built from the CSV catalog
A text-analysis or search tool over the plain-text dump of all books
A daily 'random classic' newsletter that links to each book's landing page

More in Books and libraries

All 7 →

Open Library Almost every page has a machine-readable twin: add .json to a work or author URL and you get the structured record behind it. API, no keyDownloadCommercial: conditions Internet Archive Behind every item is a folder of original files and metadata you can fetch directly, from old radio shows to scanned books and forgotten home movies. API, no keyDownloadCommercial: conditions Library of Congress Any search page on loc.gov can be turned into structured data, so whole collections of historic photos or maps become something you can query and plot. API, no keyDownloadCommercial: conditions Europeana One query can pull paintings, manuscripts, newspapers and sound recordings from institutions all over Europe, filtered to items that are free to reuse. APIDownloadCommercial: conditions Digital Public Library of America It stitches together small local archives and big institutions, so one search can surface a town historical society's photos next to national collections. License unclear archive.today It keeps frozen, script-free copies of pages that later change or vanish, so you can see what a page said on a given day. License unclear

Something wrong or out of date? Tell us.