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
Is your AI coding spend delivering? Offline-first analytics for Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI and Cline — $/100 AI lines per project, every verdict carrying its own confidence, a self-contained dashboard, exec plugins in any language, and a self-hosted team server. No telemetry; prompts are never read.
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。
Vendor-neutral evidence for AI-assisted software engineering.
Measure cost, usage and code-producing activity from local coding-agent logs today;
connect that evidence to review, CI and durable outcomes next. Offline-first, reproducible
and designed to measure systems rather than rank people.
AI coding vendors now provide useful usage dashboards of their own. They are the right
place for plan limits and vendor-specific administration. assaio is for the questions
that cross those boundaries: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。
Vendor-neutral evidence for AI-assisted software engineering.
Measure cost, usage and code-producing activity from local coding-agent logs today;
connect that evidence to review, CI and durable outcomes next. Offline-first, reproducible
and designed to measure systems rather than rank people.
AI coding vendors now provide useful usage dashboards of their own. They are the right
place for plan limits and vendor-specific administration. assaio is for the questions
that cross those boundaries:查看完整 README ↗