-
Notifications
You must be signed in to change notification settings - Fork 1
Home
Saiki77 edited this page May 16, 2026
·
4 revisions
A Python framework for building AI bots for Hexagonal Tic-Tac-Toe (Connect-6 on an infinite hex grid). Fast C game engine, multiple neural network architectures, AlphaZero training pipeline, and a live training dashboard.
Home of the Orca bot.
| Page | What you'll get |
|---|---|
| Quickstart | 5 minutes from pip install to a bot playing |
| Game Rules | The rules of Hex Connect-6 in 60 seconds |
| Concepts | MCTS, AlphaZero, policy/value, ELO explained briefly |
| Bot Approaches | Six complete bot designs with code |
| Examples | Ten ready-to-run scripts in the examples/ folder |
| FAQ | Common pitfalls and questions |
| Page | What it covers |
|---|---|
| Getting Started | Full HexGame API, coordinates, search |
| Bot Approaches | Hand-tuned, minimax, MCTS, neural, hybrid |
| Plugin System | Register custom bots and networks |
| Examples | Annotated tour of the examples/ folder |
| API Reference | All public function signatures |
| Page | What it covers |
|---|---|
| Training Guide | Self-play pipeline, curriculum, distributed |
| SFT Guide | Warm-start from game collections |
| Train Dashboard | Web UI for monitoring training |
| Configuration | Every tunable parameter |
| Benchmarking | Compare hardware and profile bottlenecks |
| Orca Bot | Architectures, loading, fine-tuning |
| Page | What it covers |
|---|---|
| Evaluation and Sharing | Arena, Leaderboard, Model Zoo |
| Playing Online | Run your bot on hexo.did.science under your account |
| Dashboard Guide | REST + WebSocket API for live game data |
| Advanced | Solver, opening book, ensemble, MCTS tricks |
pip install hexbotSee the README for development-install instructions.
Built something cool with this? Open an issue or get in touch, and it'll be featured on the README.
Home · Quickstart · Concepts · FAQ · API Reference · GitHub · PyPI
hexbot · MIT licensed · Built for the Hexagonal Tic-Tac-Toe community
Learn
Build
Train
Evaluate & Share
Reference