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
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The open source panel for a Zeroko runner: services, deployments, logs, data and tokens, and the skill your agents read to deploy. Self-hosted next to the runner.
翻译准备中
取自仓库 README
正在加载完整 README。
查看完整 README ↗The open source panel of Zeroko: a web app to manage one runner, and the skill agents read to deploy services on it. Self-hosted next to the runner.
cp .env.example .env # set the token and the password
docker compose up -d # then put a reverse proxy with TLS in front
Or in one container, the panel with the runner inside (panel:latest-aio):
cp .env.aio.example .env # set the password
docker compose -f docker-compose-aio.yml up -d
The docs are at zeroko.space/docs: installing, the panel, the runner and the API. What changed is in the changelog.
Run a runner, then put its token in .env.local
(ZEROKO_TOKEN, ZEROKO_PANEL_PASSWORD, ZEROKO_RUNNER_URL):
npm install
npm run dev # the panel at http://localhost:3000
npm run typecheck && npm run lint && npm run build
MIT licensed.