Life is too short to answer all the "What is the anime?" questions. Let computers do that for you. is a test-of-concept prototype search engine that helps users trace back the original anime by screenshot. It searches over 22300 hours of anime and find the best matching scene. It tells you what anime it is, from which episode and the time that scene appears. Since the search result may not be accurate, it provides a few seconds of preview for verification.

There has been a lot of anime screencaps and GIFs spreading around the internet, but very few of them mention the source. While those online platforms are gaining popularity, respects the original producers and staffs by showing interested anime fans what the original source is. This search engine encourages users to give credits to the original creators / owners before they share stuff online.

This website is non-profit making. There is no pro/premium features at all. This website is not intended for watching anime. The server has effective measures to forbid users to access the original video beyond the preview limit. I would like to redirect users to somewhere they can watch that anime legally, if possible.

Most Anime since 2000 are indexed, but some are excluded (see FAQ). No Doujin work, no derived art work are indexed. The system only analyzes officially published anime. If you wish to search artwork / wallpapers, try to use SauceNAO and

WebExtension available for Chrome, Firefox, or Opera to search.

Source code and user guide on Github:

Telegram Bot available @WhatAnimeBot

Source code and user guide on Github:

Official API Docs available at GitHub

WhatAnime by Andrée Torres

WhatAnime - 以图搜番 by Mystery0 (Simplified Chinese)

Go-talk presentation on 27 May 2016

Go-talk presentation on 4 Jun 2017

Go-talk presentation on 17 Jun 2018

System status page: (Powered by UptimeRobot)

Last Database Index update: 2 hours ago with 662 Million analyzed frames. (125 GB)

This database automatically index most airing anime in a few hours after broadcast.
You may subscribe to the updates on Telegram @whatanimeupdates

Full Database Dump 2019-04 (24.8GB)

If you have any feedback, suggestions or anything else, please email to [email protected].

You may also reach the author on Telegram @soruly or Discord.

Follow the development of and learn more about the underlying technologies on GitHub, Facebook Page or Patreon page.

Dr. Mathias Lux (LIRE Project)

Lux Mathias, Savvas A. Chatzichristofis. Lire: Lucene Image Retrieval – An Extensible Java CBIR Library. In proceedings of the 16th ACM International Conference on Multimedia, pp. 1085-1088, Vancouver, Canada, 2008 Visual Information Retrieval with Java and LIRE

Josh (Anilist) and Anilist team

Donate with PayPal or Become a Patron!

Former and Current Supporters:

And of cause, contributions and support from all anime lovers!