AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻译准备中
尚未检测到更新。GitHub 发布版本后会显示在这里。
个人 GitHub 账号下公开仓库的所有者可以登录并验证所有权,自行管理介绍,无需管理员批准。
登录并生成验证文件,在 30 分钟内将其提交到此仓库的默认分支。其他分支或分叉仓库中的文件无效。然后在下方检查文件,即可无需管理员批准直接管理项目。请保留文件以维持管理权限。
如需登录,将前往登录页面。登录后请回到此处,再次点击所选的验证按钮。
在项目文件夹中运行 /nomorevibe verify,即可验证所有权并自行管理介绍。
一分钟完成验证制作者的介绍仅有上面的一句话。 更多详情请阅读仓库 README。 仓库 README ↗
正在加载完整 README。
查看完整 README ↗Agency is a language for building agents that compiles to TypeScript.
pnpm install agency-lang
Create a file called hello.agency:
node main() {
const greeting = llm("Say hello to the world!");
print(greeting);
}
Compile and run it:
pnpm run agency hello.agency
Now read the docs to learn more about the language and how to use it!
Weather data in the standard library (std::weather) is provided by Open-Meteo. Data is licensed under CC BY 4.0. The free API is for non-commercial use only; commercial use requires a paid subscription.
The bundled agent's coding workflow skills (brainstorming, writing-plans, executing-plans, TDD, systematic debugging, verification-before-completion) are vendored from the Superpowers plugin by Jesse Vincent, used under the MIT license. See packages/agency-lang/lib/agents/agency-agent/skills/superpowers/ATTRIBUTION.txt.
MIT.