Alternatives
Products that do what Can a person's chess mind outlive them? An attempt with 41 masters does
Two years ago I sat down to build a chess engine for my kids' Christmas present. Wanted it to play badly enough to be beatable but not randomly bad: different styles so they could choose what to face. While building those styles I noticed the choices started looking like actual historical players' tendencies. Went looking. Turns out: given enough games from one person, you can extract enough of their decision pattern to reproduce it. Two years later, 41 players, ~3,000 games each. Tal sacrifices unsoundly. Morphy attacks like it's 1850. Capablanca grinds endgames. Same engine underneath,…
- 1CA
2021 · chrisbutner.github.io
- 2SA
I made a chess engine today, and made it fit within 2KB. I used a variant of MinMax called Negamax, with alpha beta pruning. For the board representation I have used a 120-cell "mailbox". I managed to squeeze in checkmate/stalemate in there, after trimming out some edge cases. I am a great fan of demoscene (computer art subculture) since middle school, and hence it was a ritual i had to perform. For estimating the Elo, I measured 240 automated games against Stockfish Elo levels (1320 to 1600) under fixed depth-5 and some constrained rules, using equal color distribution. Then converted…
Feb 2026 · github.com
- 3
- 4PA
Thought I would post in celebration of 1 year of my website being online. I've been working on it on and off and currently the website allows users to play Hex, Tumbleweed, Amazons, and Connect 6 against friends or against practice bots. I've been a long time player of some of these games and I felt for a long time that the world could use a few more popular abstract strategy games compared to Chess or Go. If you try it, let me know what you think. I'm always looking for new games or new features to add :)
Oct 2025 · abstractboardgames.com
- 5IT
I built 1e4.ai - a chess web app where you play against neural networks trained to mimic human Lichess players at specific Elo ranges. There's a separate model for each 100-point rating bucket from ~800 to 2200+, and the bots not only choose human-like moves but also burn clock time, play worse under time pressure, and blunder in human-like ways. Live demo: https://1e4.ai Code: https://github.com/thomasj02/1e4_ai A few things that might be interesting: - Trained on almost a full year of Lichess blitz games, around 1B total games - Architecture is an a small…
May 2026
- 6PA
Hi, this is my first HN submission so please forgive the rough edges. For this project gathered chess positions from some well-known chess players with a lot of games. (Usually ~25k games and 1M+ positions. The most for any player was GM Aman Hambleton with 1.8M positions indexed.) With each board position I create a probability distribution of moves the player has made from that position. Then, I simply draw from that distribution (with sampling temperature) to choose a move. As long as there's at least one game with a given position, you can keep playing. You'll see that it's pretty easy…
2022 · d2frm2q2a7fq8v.cloudfront.net
- 7
- 8
Chess pattern training. No timers, no streaks, no ratings.
Jun 2026 · boxwoodchess.com
- 9OC
My personal project: https://github.com/leonidasdeim/chasse Goal was to build session based chessboard game without any rules - to play just like oldschool over the board. Just create new board and share link with a friend. I would appreciate any feedback and github star. Thanks!
2023 · chasse.fun
- 10CTChess Twist▲29
I continue my experiment of transposing classic games onto an irregular grid. I've previously released variants of minesweeper and checkers. And now I'd like to share my variant of Chess. Chess can be a pretty punishing game, but I thought this was nevertheless a way to make it even more challenging by making it trickier to anticipate your opponent, even though both players still have the same information. From the playtests I've done, that challenge is pretty compelling. It also seems to be more fun at 2 people, where both players keep surprising one another.
2024 · polyreplay.com
- 11CG
For no specific reason, I trained a neural network to generate random chess positions that look similar to positions from actual games (from lichess db). I also made it so you can condition it on some fixed pieces, and adjust the number of pieces. It turned out to be quite effective and I find it surprisingly fun and instructive to generate e.g. endgame positions with a certain pawn structure (set low temperature, place some pawns and position the kings, adjust number of pieces to get an endgame), and then figure out how to win vs. the computer in those positions. I hooked it up so that you…
2024 · chessdream.ai
- 12
- 13
- 14IB
I built this because I got tired of Stockfish giving me evaluations (+0.5) without explaining the actual plan. Most opening explorers focus on statistics (Win/Loss/Draw). I wanted a tool that explains the strategic intent behind the moves (e.g., "White plays c4 to clamp down on d5" vs just "White plays c4"). The Project: Comprehensive Database: I’ve mapped and annotated over 3,500 named opening variations. It covers everything from main lines (Ruy Lopez, Sicilian) to deep sidelines. Strategic Visualization: The UI highlights key squares and draws arrows based on the textual…
Jan 2026 · atlaschess.me
- 15
- 16
- 17IB
I built a multiplayer strategy game for AI agents called Artifice. You give an agent a strategy prompt and it plays on its own. Games are 4 players, 25 turns, simultaneous actions, fog of war, and free-text diplomacy between agents. The main entry point is the site: https://artificegame.com And here is the github repo: https://github.com/burakcan/artifice You can watch live games there with the full map, troop movements, and private messages between agents. A lot of the fun has come from the playtests. In one of them, an agent was told to play like an old man…
Mar 2026 · artificegame.com
- 18CL
As I was playing with the Outlines library (https://outlines-dev.github.io/outlines/), I discussed with my friend Maxime how funny it would be if we set up a way to pair LLMs in chess matches till one wins. The first time I tried it, it required substantial prompt engineering to get some of those LLMs to propose valid moves. Large language models can mostly stay focused and even play rather well; see https://news.ycombinator.com/item?id=37616170 for example. However small language models aren't as easy to convince. Some of those LLMs have seen very little…
2024 · huggingface.co
- 19
Identify patterns in your mistakes to get better at chess
Jul 2026 · e4coach.com
- 20IB
Hi HN, here is my humble weekend project. I couldn’t find any similar utilities online that would let me download all of my chess games, so I decided to make one. It’s definitely imperfect, so please let me know if you have any feedback!
2023 · chessgamedownloader.fly.dev
- 21
- 22
- 23
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →