游戏娱乐3 days ago
Agent Brawl Club
用 AI agent 与其他人对抗炸弹人、贪吃蛇和德州扑克。
ChenR · V2EX
Agent 来玩炸弹人、德州扑克 做了个面向 agent 的对战平台，登录后就可以用你的 agent 来生成策略对战了 炸弹人和贪吃蛇是提前生成策略、执行器 德州扑克是每回合实时请求 agent 策略 第一次做项目，请大家批评 https://brawlclub.fly.dev/#/
完整作品展
技术栈
60 projects
用 AI agent 与其他人对抗炸弹人、贪吃蛇和德州扑克。
ChenR · V2EX
Agent 来玩炸弹人、德州扑克 做了个面向 agent 的对战平台，登录后就可以用你的 agent 来生成策略对战了 炸弹人和贪吃蛇是提前生成策略、执行器 德州扑克是每回合实时请求 agent 策略 第一次做项目，请大家批评 https://brawlclub.fly.dev/#/
Rollin - 实时多人策略游戏，掷骰子、秘密放置和战术战斗。
@z3roshot · X
Made up a game where chess meets dice: roll, shop, secretly place, fight. ⚄ Same deterministic engine runs the bots and the humans. Server-authoritative so nobody can peek at your hidden pieces. Built with Claude Code. Read more
混合动物、机甲或英雄来创建独特的混合角色。
Magic Animal Generator — 尽情发挥你的想象力 用 AI 混合两种动物，创造前所未见的新物种
在AI游戏大师主持的多人策略游戏中竞争和统治
jklewis · HN
Machinations – a multiplayer strategy game where LLM is the game master
在高对比度的单色街机中玩 Tic-Tac-Toe、Snake 和 2048，配以复古 8-bit 音效。
@ParvaShastri · X
No login. No leaderboards. No BS. Just quiet me-time. 🕹️ I built MONO.ARCADE—a minimalist playground. And yes, it’s def vibecoded. 🏄♂️✨ 😉 18 classic games ready. Just click and play. 💡 Comment a game idea! I’ll build it & feature your name. 👉
与AI或在线对手下棋，通过迷你游戏决定每次吃子。
@GeorgeGognadze · X
Hi, I’m building the new chess version where mini games decide the capture @dualchess
Play a browser-based game about conquering the world.
pzxc · HN
I've been using AI (mostly Claude, a little Cursor) to make video games, publishing a new one every day, for over 2 months Today's game is a simplified Risk clone called World Domination. Happy to answer any questions, would love any feedback!
Trendoff：实时1v1对战，由端侧AI评判。
german_merlo1 · Product Hunt
Trendoff Live 1v1 trend battles, judged by AI
融合街霸2格斗风格的Pong浏览器游戏。
@asredoblado · X
Working on Super Pong. Think Pong meets Street Fighter 2. #IndieGameDev #vibecoding #app #webgame #pong #build
发射机器人有效载荷并建造戴森群保护地球。
@JonathanCochran · X
Not quite Acelerando, but I vibe-coded a game: Recompile the Moon 🌙 Launch robot payloads, refactor celestial mass, and build a Dyson swarm before Earth gets wrecked. Built with Codex 5.6-sol, inspired by your “vibe-code a game” challenge:
在Mech Arena中玩16个AI街机游戏
@spt4d · X
Deployed the 16 games built with Codex and GameBlocks. A few examples: Most of my time is actually spent shaping the player experience. Many ideas emerge through playing and exploration rather than from the initial design — the loop seems to be build → play → discover → improve. Is it possible to build an agent harness that supports this discovery loop — not just one that optimizes against a predefined spec? Full game list:
