What this site is, and what it isn't.

What Sumerian Book is

Sumerian Book is an independent scholarly reconstruction of the history of Mesopotamia, built and maintained by a solo developer in France. It is a curated narrative based on the cuneiform tablet record — every claim is anchored to at least one tablet, visible inline with its transliteration, translation, and source.

The project has no academic affiliation, no institutional funding, and no editorial board. It exists because the developer believes this material should be readable by curious people who are not specialists, and because so much of the corpus has never been translated into any modern language.

How content is produced

Tablets come from three kinds of sources:

• Hand-curated editorial entries — written by the developer, drawing on mainstream scholarship (Roth, George, Frame, Leichty, Novotny, Black/Cunningham/Robson, et al.). These carry the source citation in the "Source" line under the translation.
• Imported scholarly translations — from open corpora such as ETCSL (Oxford), ORACC (Penn / NYU / others), SAAo, RIME, RINAP. Attribution is preserved per tablet.
• Engine-generated translations — produced by an AI translation pipeline (Anthropic Claude) running on the tablet text and a photograph, with a strict anti-fabrication system prompt, multi-layer reading, and explicit confidence levels (high / medium / low / experimental). Engine-translated entries are clearly labelled in the "Source" line as engine:... and carry their confidence badge. See the engine page for full methodology.

No warranty

The content is offered as an honest, best-effort reading of the primary sources. Cuneiform texts are fragmentary, multilingual, damaged, and centuries-deep contested in their interpretation. Even the best scholarly translations disagree about specific words. Engine-generated translations carry an extra layer of uncertainty that we surface, but cannot eliminate, with confidence indicators.

Use the site for personal study, teaching, journalism, or as a stepping stone to the original scholarly literature. Do not use it, in its current state, as the sole source for academic publication. When in doubt, follow the source link on the tablet's page back to the published edition.

Licensing of our text

The original editorial text written for this project (period descriptions, chapter intros, the prologue and epilogue, the interpretation paragraphs labelled engine) is licensed under Creative Commons BY-NC-SA 4.0: you may quote, translate, or build upon it freely for non-commercial purposes, with attribution and share-alike.

Licensing of the imagery

Tablet photographs come from third-party collections under their own licences:

• CDLI (Cuneiform Digital Library Initiative) — most images here, used under CC BY-NC-SA 3.0. Source URL and museum attribution preserved per image.
• Wikimedia Commons — public domain or CC-licensed contributions; attribution preserved per image.
• Public museum open-access programmes — the Metropolitan Museum (CC0), the British Museum, the Yale Babylonian Collection, the Louvre, the Vorderasiatisches Museum Berlin, and others. Their attribution lines appear under each tablet.

If you are a rights-holder and believe an image should be removed or its attribution corrected, please write to us via the contact form and we will act within seven days.

Acceptable use

You may read, link to, quote, and share the site freely. You may not scrape it aggressively (please rate-limit yourself to one request per second), or use it as input to train a closed commercial model without notice.

Limitations of liability

The site is provided "as is", without warranty of any kind. To the maximum extent permitted by applicable law, the developer is not liable for any loss arising from your use of the site or reliance on its content.

Contact & takedowns

For any question — correction, source request, takedown notice, or help offer — write through the contact form. We aim to reply within seven days.