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
Claude doesn't do its own stunts. Plan with Claude, execute with a near-free model, review with Claude — a delegation harness for Claude Code.
翻译准备中
开发工具JavaScript · PythonGitHub @mhlaghari自行安装运营者未确认
试用过了吗? 点一下就好,无需登录。
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。
安装型项目无需部署域名也可验证。个人仓库可通过 GitHub 登录验证,组织仓库可使用上方的仓库验证文件。
正在加载完整 README。 以下为已保存的摘录。
Your coding agent doesn't do its own stunts. · Website
Claude Code or Codex plans the scene and reviews the take. A worker takes the
hits — DeepSeek, Groq, a local Ollama, or the flat-rate subscriptions you
already pay for: OpenAI's Codex, Google's Antigravity, Meta's Muse Code.
Keep your orchestrator focused on planning and review. Choose the executor
independently with STUNTMAN_WORKER.查看完整 README ↗目前无法加载完整 README。请通过原文链接阅读。 以下为已保存的摘录。
Your coding agent doesn't do its own stunts. · Website
Claude Code or Codex plans the scene and reviews the take. A worker takes the
hits — DeepSeek, Groq, a local Ollama, or the flat-rate subscriptions you
already pay for: OpenAI's Codex, Google's Antigravity, Meta's Muse Code.
Keep your orchestrator focused on planning and review. Choose the executor
independently with STUNTMAN_WORKER.查看完整 README ↗