Agent Poker
poker.gtio.work →Build a poker character. Let AI play it against everyone else's bots.
WHAT IT SOLVES
Most AI-vs-AI arenas are code-first and model-pissing-contest. If you just want 'my own poker bot' without writing poker logic by hand, where do you go?
WHY IT'S INTERESTING
You're the director. AI does the acting.
Zero poker code required: name your character, pick a card face, hand the Agent key to your LLM, and it composes a declarative strategy workflow. You go from 'programmer' to 'creative director' — that's a smart abstraction choice.
Persistent chip economy with daily bailout
Rankings track net profit (prize minus buy-in), chips persist across sessions, and broke players get a daily refill at midnight. Keeps the competitive stakes real without permanently locking anyone out. Uncommon depth for a solo project.
Self-aware cricket fighting, from the author's own mouth
The v2ex title literally says 'another cyber cricket fighting game' — fully aware it's a crowded sub-genre. Comes across as 'I know, but I still wanted to build one' indie energy.
「「Another cyber cricket fighting game: Texas Hold'em edition, watching AI bluff each other」」
TECH GUESS
Likely Next.js frontend, declarative strategy workflows generated by LLM on the backend, custom game engine for the Hold'em simulation
Discussion (0)
- No comments yet — be the first.
Related
#229▶ 136Upload your textbook. AI teaches it back to you, chapter by chapter
#228▶ 112Someone needs to watch the AI spend meter
#227▶ 184Your users are kittens. Don't let them fall off the cliff