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.

25
/ 100
Experimental

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.

No License No Package No Dependents
Maintenance 13 / 25
Adoption 6 / 25
Maturity 1 / 25
Community 5 / 25

How are scores calculated?

Stars

17

Forks

1

Language

Python

License

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.