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Agent library operator and stack readiness CLI/MCP for ~/.agents skills, profiles, and honest intelligence-stack health.
翻译准备中
取自仓库 README
正在加载完整 README。 以下为已保存的摘录。
Skill intelligence for agent harnesses. Minerva reads conversations and
tool calls from Claude Code, Codex, Cursor, OpenCode, Copilot, Gemini,
Hermes Agent, oh-my-pi (omp), and sonar — then proposes SKILL.md files and keeps the canonical
~/.agents/skills library in sync.
It is not a second agent runtime, not Cortex, and not a monitor for
companion CLIs.
Built with Go + Cobra + MCP stdio.
Override the library root with MINERVA_AGENTS_DIR. Override the home used
to find harness session files with MINERVA_HOME (tests should set both).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。
Skill intelligence for agent harnesses. Minerva reads conversations and
tool calls from Claude Code, Codex, Cursor, OpenCode, Copilot, Gemini,
Hermes Agent, oh-my-pi (omp), and sonar — then proposes SKILL.md files and keeps the canonical
~/.agents/skills library in sync.
It is not a second agent runtime, not Cortex, and not a monitor for
companion CLIs.
Built with Go + Cobra + MCP stdio.
Override the library root with MINERVA_AGENTS_DIR. Override the home used
to find harness session files with MINERVA_HOME (tests should set both).查看完整 README ↗