Observed arrival · 2026-10-08
Chessglance reads chess positions from images and video
A browser-based chess-board recognizer turns screenshots, book diagrams, and video frames into positions that can be checked and exported.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Chess players, book readers, and chess-tool developers
- Worth noticing
- The page reports 65% exact across 844 held-out diagrams from 11 books, versus 100% on 1,000 lichess boards.
Field notes
For browser scans, a model downloaded once runs locally; the page says those images are not uploaded. It evaluates all 64 squares, applies chess-legality checks, and flags low-confidence squares for correction before FEN export or opening in Lichess. Results vary by evaluation set: the page reports 84.1% exact on 107 1920s-book boards and 65% on 844 held-out diagrams from 11 books.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
$PaidCommerce or pricing visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue