patrickfrank1/chesspos

Embedding based chess position search and embedding learning for chess positions

57
/ 100
Established

This tool helps chess enthusiasts and analysts find similar chess positions by converting them into numerical 'embeddings'. You input a collection of chess positions, train a neural network to understand their strategic relationships, and then use the resulting embeddings to search for positions that are strategically alike. This is ideal for chess coaches, content creators, or advanced players looking to study specific tactical themes or opening variations across many games.

Available on PyPI.

Use this if you need to efficiently search through large databases of chess games to find positions that share strategic characteristics or tactical patterns, beyond simple board state matching.

Not ideal if you are looking for a simple chess engine or a tool to analyze individual game moves, as its primary purpose is position similarity search rather than game play or single-game analysis.

chess-analysis game-study position-search tactical-pattern-recognition opening-exploration
Maintenance 10 / 25
Adoption 6 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

16

Forks

6

Language

Jupyter Notebook

License

AGPL-3.0

Last pushed

Mar 12, 2026

Commits (30d)

0

Dependencies

11

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/patrickfrank1/chesspos"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.