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
A structured workflow system for AI coding agents - harness engineering, execution loop, skills, hooks, and a learning loop. Works with Claude Code, Codex, Antigravity CLI, Copilot.
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。
An AI coding agent harness and local dashboard for Claude Code, OpenAI Codex, Google Antigravity, and GitHub Copilot.
GOAT Flow audits agent setup, installs guardrails and deny hooks, provides structured /goat-* workflows, and preserves lessons between sessions. Its manifest-backed registry keeps the same harness available across all four supported coding agents.
Install locally when you want a project-pinned version:
The embedded terminal needs the optional node-pty package to compile. See Troubleshooting if the terminal does not appear.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。
An AI coding agent harness and local dashboard for Claude Code, OpenAI Codex, Google Antigravity, and GitHub Copilot.
GOAT Flow audits agent setup, installs guardrails and deny hooks, provides structured /goat-* workflows, and preserves lessons between sessions. Its manifest-backed registry keeps the same harness available across all four supported coding agents.
Install locally when you want a project-pinned version:
The embedded terminal needs the optional node-pty package to compile. See Troubleshooting if the terminal does not appear.查看完整 README ↗