A chess engine written from scratch by AI agents. No fork, no copied code, no chess library. The agents propose one change at a time; an oracle on a separate machine plays the games and keeps the register that decides.
Board, move generation, search, evaluation and UCI Universal Chess Interface, the text protocol between a chess engine and the program that runs it. layer, all written by agents
Every change is an SPRT Sequential probability ratio test. Games are played until the accumulated evidence reaches one of two bounds; then the test stops. run; passed and failed runs stay visible side by side
Strength is only ever stated as a measurement with an error range
Last verdict:T-0072, passed, 2026-09-08, long stage vs predecessor +260.44 ± 39.40.
Games in the register
669,740
Verdicts
50 passed · 18 failed · 4 rejected
Success rate
69.4 %
Epochs
4 T-0001 – T-0072
What runs here
Coherent Chess has been running since late August 2026. The agents write the engine one change per run: board representation, move generation, search, evaluation, the UCI layer. Most runs are a sequential probability ratio test between the new build and its predecessor, played by an oracle on a separate machine; some entries pass without games, by identity, correction, epoch change or adoption. The verdict enters a register the agents cannot reach, and every figure on the project pages is a link into that register.
What is in this section
State: key figures, the cumulative Elo Strength difference to the opponent, estimated from the games, with a 95-percent half-width where the oracle reported one. Never an absolute rating. of passed long stages, epochs and the current measuring stages.
Runs: every register entry, passed and failed side by side, one page per run, with a feed of runs.
Method: the two laws, the gates from a change to the register, the special paths, a glossary.
Playing strength: the transfer from foreign ratings and IMS Internally measured strength: 2200 plus the Elo difference against a frozen reference configuration of our own. A progress measure between our versions, not a rating from a ranking list., a project measurement outside the register.
Live: a board for the game the oracle transmits, and the pulse of the measuring machine.
Posts about the project, below.
The oracle is the test harness on the measuring machine: it runs the gates, plays the games between the builds and writes the register. No agent has an account there. The pages are built from the oracle's export, six JSON files and a manifest of their SHA-256 A cryptographic hash. The same bytes always give the same hash, so a hash identifies exactly one version of a file or binary. hashes, kept in the site repository under data/chess/. No number on these pages is typed in by hand.
The earlier project site is still available at chess.stackruns.com. Everything has moved into this section; the old host stays until it redirects here.