# loop-everything

**Repository Path**: perrylink/loop-everything

## Basic Information

- **Project Name**: loop-everything
- **Description**: Loop Engineering ecosystem hub: documentation, selection guides, and architecture overviews for 12 autonomous coding loop engines. The entry point to closed-loop autonomous development.
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-08-22
- **Last Updated**: 2026-08-22

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Loop Engineering
[![Gitee](https://img.shields.io/badge/Gitee-mirror-c71d23?logo=gitee)](https://gitee.com/perrylink/loop-everything)

*The [**Loop Engineering**](https://github.com/PerryLink/loop-everything) ecosystem hub — index and entry point for all autonomous coding loop engines.*

> 11 autonomous AI coding loop engines — from a single goal statement to production code, without human intervention.
>
> 11 个自主 AI 编程循环引擎 —— 从单一目标声明到生产级代码，无需人工干预。

[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE)
[![Version](https://img.shields.io/badge/version-0.1.0-blue)]()

[English](#english) | [中文](#chinese)



---

## English

### 🎯 What is Loop Engineering?

Loop Engineering is a methodology for **autonomous AI coding**. Instead of chatting with an AI assistant turn-by-turn, you give it a **goal** and it executes a structured multi-phase workflow:

1. **Part 1 — Design Bubble** (phases 1.1→1.2→1.3): Requirements → Direction → Solution
2. **Routing Gate**: Decide next action (implement / redesign / complete / pause / fail)
3. **Part 2 — Implementation Chain** (phases 2.1→2.8): Plan → Implement → Review → Test Strategy → Test Plan → Test Execution → Audit → Hard Verification
4. **Convergence**: Auto-detect completion and terminate

All 11 engines share this architecture, each wrapping a different AI tool.

---

### 🌐 Project Navigation

| # | Project | Wrapped Tool | Language | Description |
|:--:|------|------|:--:|------|
| ⭐ | **loop-everything** | Meta-repo | — | Ecosystem hub — you are here |
| 1 | [loop-aider](https://github.com/PerryLink/loop-aider) | Aider CLI | Python | 11-phase state machine, 10-point PhaseGuard, atomic write |
| 2 | [loop-superpowers](https://github.com/PerryLink/loop-superpowers) | Claude Code Skills | YAML/MD | 7-skill autonomous mini-loop, Phase Contract DSL |
| 3 | [loop-ollama](https://github.com/PerryLink/loop-ollama) | Ollama | Python | ReAct loop, 3-tier fault tolerance, fully local/air-gapped |
| 4 | [loop-hermes](https://github.com/PerryLink/loop-hermes) | Hermes SDK | Python | 24 modules, 6 gates, provider fallback, parallel delegation |
| 5 | [loop-antigravity](https://github.com/PerryLink/loop-antigravity) | Gemini API | Python | Circuit breaker, multimodal handler, billing tracker |
| 6 | [loop-codex](https://github.com/PerryLink/loop-codex) | Codex Desktop (CDP) | TypeScript | CDP+JSON-RPC dual-channel, CDPGuard L0/L1/L2 |
| 7 | [loop-copilot](https://github.com/PerryLink/loop-copilot) | GitHub Copilot SDK | TypeScript | Think-Act-Observe, watchdog, session hooks |
| 8 | [loop-cursor](https://github.com/PerryLink/loop-cursor) | Cursor SDK | TypeScript | 3-package monorepo, 22-step engine, 27-model registry |
| 9 | [loop-opencode](https://github.com/PerryLink/loop-opencode) | OpenCode CLI | TypeScript | 8 safety gates, 3-layer architecture |
| 10 | [loop-openclaw](https://github.com/PerryLink/loop-openclaw) | OpenClaw Gateway | Python | 15 Jinja2 templates, dual-engine rendering, 3 topologies |
| 11 | [loop-deepseek](https://github.com/PerryLink/loop-deepseek) | DeepSeek API | TypeScript | ReAct loop, reasoning_content caching (40-60% token savings) |
| 📋 | [loop-claudecode](https://github.com/PerryLink/loop-claudecode) | Claude Code | Bash/Skill | Reference implementation, G1/G2/G3 OS-level gates |

---

### 🤔 Which One Should I Use?

| Your Scenario | Recommended Project |
|------|------|
| "I want the best overall quality" | **loop-aider** or **loop-ollama** |
| "I use Claude Code and want zero-dependency" | **loop-superpowers** |
| "I need fully offline / air-gapped operation" | **loop-ollama** |
| "I need production-grade safety with provider fallback" | **loop-hermes** |
| "I want Google Gemini with cost control" | **loop-antigravity** |
| "I need GUI automation (browser testing)" | **loop-codex** |
| "I use GitHub Copilot" | **loop-copilot** |
| "I use Cursor IDE" | **loop-cursor** |
| "I want DeepSeek's reasoning models" | **loop-deepseek** |
| "I need to generate agent workspace configs" | **loop-openclaw** |

---

### 🙋 FAQ

**Q: Isn't this just a wrapper around existing AI tools?**
A: No. Each engine adds a **structured state machine, safety gates, convergence detection, and autonomous multi-turn execution**. Without the loop wrapper, the underlying tools require manual turn-by-turn guidance. With it, you state a goal and the engine executes all phases autonomously.

**Q: Why 11 different engines instead of one?**
A: Each engine wraps a different AI tool with unique strengths. Ollama for local/offline, Hermes for production safety, Codex for browser GUI, DeepSeek for reasoning models. Pick the one that fits your stack.

**Q: Are these production-ready?**
A: Each engine implements a structured state machine with safety gates, convergence detection, and multi-phase execution. They are designed for autonomous operation, but we recommend testing in your own environment. See each project's README for detailed metrics and caveats.

**Q: How do I contribute or build my own engine?**
A: Start with [loop-claudecode](https://github.com/PerryLink/loop-claudecode) as the reference implementation, then adapt the architecture to wrap your preferred AI tool. See [CONTRIBUTING.md](CONTRIBUTING.md).

**Q: What's the difference between Part 1 (Design) and Part 2 (Implementation)?**
A: Part 1 (1.1→1.3) runs in a single continuous context for creative design thinking. Part 2 (2.1→2.8) runs as discrete checkpointed steps for reliable implementation. A routing gate between them decides whether to implement, redesign, or terminate.

---

### 📄 License

All projects in the Loop Engineering ecosystem are licensed under **Apache License 2.0**.

Copyright © 2026 Perry Link

---

## 中文

### Loop Engineering 是什么？

Loop Engineering 是一套**自主 AI 编程方法论**。不同于与 AI 助手逐轮聊天，你只需设定一个**目标**（goal），引擎会自动执行结构化的多阶段工作流：

1. **第一部分 — 设计气泡**（阶段 1.1→1.2→1.3）：需求 → 方向 → 方案
2. **路由闸门**：决定下一步动作（实施 / 重新设计 / 完成 / 暂停 / 失败）
3. **第二部分 — 实施链**（阶段 2.1→2.8）：规划 → 实施 → 审查 → 测试策略 → 测试计划 → 测试执行 → 审计 → 硬验证
4. **收敛检测**：自动检测完成并终止

全部 11 个引擎共享此架构，每个引擎封装不同的 AI 工具。

---

### 项目导航

| # | 项目 | 封装工具 | 语言 | 描述 |
|:--:|------|------|:--:|------|
| ⭐ | **loop-everything** | 元仓库 | — | 生态系统中心 — 你在这里 |
| 1 | [loop-aider](https://github.com/PerryLink/loop-aider) | Aider CLI | Python | 11 阶段状态机，10 点 PhaseGuard，原子写入 |
| 2 | [loop-superpowers](https://github.com/PerryLink/loop-superpowers) | Claude Code Skills | YAML/MD | 7 技能自主迷你循环，Phase Contract DSL |
| 3 | [loop-ollama](https://github.com/PerryLink/loop-ollama) | Ollama | Python | ReAct 循环，3 层容错，完全本地/气隙运行 |
| 4 | [loop-hermes](https://github.com/PerryLink/loop-hermes) | Hermes SDK | Python | 24 模块，6 道闸门，供应商回退，并行委托 |
| 5 | [loop-antigravity](https://github.com/PerryLink/loop-antigravity) | Gemini API | Python | 熔断器，多模态处理器，费用追踪 |
| 6 | [loop-codex](https://github.com/PerryLink/loop-codex) | Codex Desktop (CDP) | TypeScript | CDP+JSON-RPC 双通道，CDPGuard L0/L1/L2 |
| 7 | [loop-copilot](https://github.com/PerryLink/loop-copilot) | GitHub Copilot SDK | TypeScript | Think-Act-Observe，看门狗，会话钩子 |
| 8 | [loop-cursor](https://github.com/PerryLink/loop-cursor) | Cursor SDK | TypeScript | 3 包 monorepo，22 步引擎，27 模型注册表 |
| 9 | [loop-opencode](https://github.com/PerryLink/loop-opencode) | OpenCode CLI | TypeScript | 8 道安全闸门，3 层架构 |
| 10 | [loop-openclaw](https://github.com/PerryLink/loop-openclaw) | OpenClaw Gateway | Python | 15 个 Jinja2 模板，双引擎渲染，3 种拓扑 |
| 11 | [loop-deepseek](https://github.com/PerryLink/loop-deepseek) | DeepSeek API | TypeScript | ReAct 循环，reasoning_content 缓存（节省 40-60% token） |
| 📋 | [loop-claudecode](https://github.com/PerryLink/loop-claudecode) | Claude Code | Bash/Skill | 参考实现，G1/G2/G3 操作系统级闸门 |

---

### 该用哪个？

| 你的场景 | 推荐 |
|------|------|
| 追求最高质量 | **loop-aider** 或 **loop-ollama** |
| 使用 Claude Code，零依赖 | **loop-superpowers** |
| 完全离线 / 气隙环境 | **loop-ollama** |
| 生产级安全 + 供应商切换 | **loop-hermes** |
| Google Gemini + 成本控制 | **loop-antigravity** |
| GUI 浏览器自动化 | **loop-codex** |
| GitHub Copilot 用户 | **loop-copilot** |
| Cursor IDE 用户 | **loop-cursor** |
| DeepSeek 推理模型 | **loop-deepseek** |
| 生成 Agent 工作区配置 | **loop-openclaw** |

---

### 常见问题

**Q: 这不就是对现有 AI 工具的简单封装吗？**
A: 不是。每个引擎都添加了**结构化状态机、安全闸门、收敛检测和自主多轮执行**能力。没有循环封装时，底层工具需要人工逐轮引导。有了它，你只需设定目标，引擎就能自主执行所有阶段。

**Q: 为什么是 11 个不同的引擎，而不是一个？**
A: 每个引擎封装了不同的 AI 工具，各有独特优势。Ollama 适合本地/离线运行，Hermes 适合生产级安全，Codex 适合浏览器 GUI 自动化，DeepSeek 适合推理模型。选择适合你技术栈的那个。

**Q: 这些引擎可以用于生产环境吗？**
A: 每个引擎都实现了结构化状态机、安全闸门、收敛检测和多阶段执行。它们为自主运行而设计，但我们建议在你的环境中进行测试。详见各项目的 README。

**Q: 如何贡献或构建自己的引擎？**
A: 从 [loop-claudecode](https://github.com/PerryLink/loop-claudecode) 参考实现开始，然后调整架构以封装你偏好的 AI 工具。详见 [CONTRIBUTING.md](CONTRIBUTING.md)。

**Q: 第一部分（设计）和第二部分（实施）有什么区别？**
A: 第一部分（1.1→1.3）在单一连续上下文中运行，用于创造性设计思考。第二部分（2.1→2.8）以离散的检查点步骤运行，用于可靠的实施执行。两者之间的路由闸门决定是实施、重新设计还是终止。

---

### 许可证

Apache 2.0 © 2026 Perry Link