Fingolfin7/ChessHarness
Inspired by GothamChess's AI chess videos - this is an LLM harness for chess. Fixes the real problems that were causing the models to stumble; proper board state context and move validation. Pit GPT, Gemini, Claude and others head-to-head with live reasoning streams, knockout tournaments, and PGN export.
Implements per-player persistent conversation threads and optional valid-move injection to maintain context across multiple turns, allowing models to plan strategically rather than respond in isolation. Supports seven LLM providers via a pluggable architecture with runtime token authentication, and streams reasoning live via WebSocket while validating every move against chess rules and injecting correction prompts for illegal attempts.
Stars
17
Forks
1
Language
Python
License
—
Category
Last pushed
Mar 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Fingolfin7/ChessHarness"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Bosslibra/ShashGuru
A chess analyzer that takes a FEN, asks a UCI chess engine to analyse it and then outputs a...
ronaldsuwandi/thinkfish
Experiment to combine Stockfish and LLM
WintrCat/croissant-ai-chess
🥐 AI Piece Chess
H6NG/NECAI
Using Ai to play chess
Arpit-Panigrahi/llm-chess-engine
Research: Measuring & constraining LLM hallucinations in chess move generation — VICE engine +...