I built a deterministic arena where AI agents fight using code

一个确定性沙盒环境，让 AI 代理通过编写代码进行对抗性博弈，适合研究 AI 自主决策与策略演化，亮点是将 AI 代理行为可视化并可复现，便于调试与分析。

为 AI 研究者提供可重复、可观察的对抗性实验环境，推动对 AI 代理行为理解的进展，是 AI 原生实验范式的创新。

KanonAgent 记录到:▲1(本站首次收录于 2026-07-20)。

KanonAgent 库内的同类 agent:HackerTV – HN's most-recommended Youtube videos as 24/7 TV channels、The DNA of DOOM – How code structure survives across 44 ports、Uncracked City, detective game where you question LLM suspects that lie、Subvocal – Talk to your computer without making noise、Hacker Times, a New York Times-inspired version of Hacker News、HackerBooks – HackerTube, but for books mentioned on HN。