# aidevops — AI DevOps Framework with Agent Playbooks

> aidevops is an OpenCode plugin and Git-first AI ops framework with agent playbooks, quality gates, and security checks for multi-agent projects.

## Install

Save the content below to `.claude/skills/` or append to your `CLAUDE.md`:

## Quick Use

```bash
npm install -g aidevops && aidevops update

# Start in any repo
aidevops init

# Run the built-in security/quality surface
aidevops security status
```

## Intro

aidevops is an AI operations framework and OpenCode plugin that turns broad projects into agent playbooks with Git-first quality gates and security checks. The GitHub repo is verified at 234★ and documents a global install + update flow.

**Best for:** teams running multi-agent delivery who want Git-first structure, quality gates, and repeatable playbooks

**Works with:** OpenCode; CLI on macOS/Linux; Git worktrees/PR workflows; optional MCP integrations

**Setup time:** 15–30 minutes

### Key facts (verified)

- README calls out an autonomous supervisor loop that runs on a cadence (every 2 minutes) to dispatch work.
- README quick reference lists install as `npm install -g aidevops && aidevops update`.
- README describes 11 primary agents plus many on-demand subagents (framework scope).
- GitHub: 234 stars · 44 forks; pushed 2026-05-12 (GitHub API verified).

## Main

Treat aidevops like an operating system for agent work:

- Start by using its Git-first structure (worktrees, PR gates) so autonomous work is reviewable.
- Pick 1–2 high-value commands (onboarding, security scan, update flow) and make them part of your daily loop.
- For teams, standardize the install/update path and define which operations require second-model verification.

Because it is powerful, adopt it incrementally: measure reliability and cost on one project before scaling.

### README excerpt (verbatim)

<!-- SPDX-License-Identifier: MIT -->
<!-- SPDX-FileCopyrightText: 2025-2026 Marcus Quinn -->

# AI DevOps Framework

**[aidevops.sh](https://aidevops.sh)** — An [OpenCode](https://opencode.ai/) plugin and AI operations platform for launching and managing development, business, marketing, and creative projects. 11 primary agents handle automatable work across every domain so your time is preserved for real-world discovery and decisions that AI cannot yet reach.

> **Recommended setup:** [OpenCode](https://opencode.ai/) + OpenAI models. GPT-5.5 is the preferred high-capability model for complex agent work; GPT-5.4 mini is the preferred fast, lower-cost model for triage and routine implementation. Claude models (Anthropic) remain fully supported, and other model providers are evaluated from time to time as their quality, latency, and cost profiles change.

*"Scope a mission to redesign the landing pages — break it into milestones, dispatch workers in parallel, validate each milestone, and track budget across the whole project"*

**One conversation, autonomous project delivery — with enterprise-level security & quality-control.**

Founded by [Marcus Quinn](https://github.com/marcusquinn) on 9th November 2025 to help anyone level-up their AI & Open-Source game.

## **The Philosophy**

**Maximum value for your time and money.** **[aidevops](https://aidevops.sh)** is built on these principles:

- **Autonomous orchestration** - An AI supervisor runs every 2 minutes, dispatching parallel workers, merging PRs, detecting stuck processes, and advancing multi-day missions — no human babysitting required
- **Multi-domain agents** - 11 primary agents covering code, automation, product, SEO, marketing/sales, content/video/social, legal, research, business/accounts, health, and framework operations with 900+ subagents loaded on demand
- **Multi-model safety** - High-stakes operations (force push, production deploy, data migration) are verified by a second cross-provider model before execution — different providers have different failure modes, so correlated hallucinations are rare
- **Resource efficiency** - Cost-aware model routing across OpenAI, Anthropic, Gemini, Cursor, and local models; project-type bundles auto-configure quality gates and model tiers, with budget tracking and burn-rate analysis
- **Self-healing** - When something breaks, diagnose the root cause, create tasks, and fix it. Every error is a live test case for a permanent solution

### FAQ

**Q: Is aidevops just a CLI?**
A: It is a CLI plus an OpenCode plugin and an operations framework with agent playbooks and quality gates (per README).

**Q: How do I install it?**
A: README recommends `npm install -g aidevops && aidevops update` (Homebrew and source installs also exist).

**Q: What is it best for?**
A: Multi-agent delivery where you need repeatable workflows, security checks, and Git-first review structure.

## Source & Thanks

> Source: https://github.com/marcusquinn/aidevops
> License: MIT
> GitHub stars: 234 · forks: 44

---

<!-- ZH -->

## 快速使用

```bash
npm install -g aidevops && aidevops update

# 在任意仓库初始化
aidevops init

# 运行安全/质量检查入口
aidevops security status
```

## 简介

aidevops 是 AI 运维框架与 OpenCode 插件，把大项目落成可执行的 agent playbook，并配套 Git-first 的质量门禁与安全检查。仓库 GitHub 已验证 234★，并提供全局安装与更新流程。

**最适合：** 希望用 Git-first 结构化方式运行多 agent 交付、并内建质量门禁的团队

**适配：** OpenCode；macOS/Linux CLI；Git worktree/PR 流程；可选 MCP 集成

**配置时间：** 15–30 分钟

### 关键事实（已验证）

- README 提到自动监督循环按固定节奏运行（every 2 minutes），用于调度任务。
- README Quick Reference 给出安装方式：`npm install -g aidevops && aidevops update`。
- README 描述 11 个 primary agents，并按需加载大量子 agent。
- GitHub：234 stars · 44 forks；最近更新 2026-05-12（GitHub API 验证）。

## 正文

把 aidevops 当作“agent 工作的操作系统”：

- 先落地 Git-first 结构（worktree、PR、门禁），让自动化工作可 review、可回滚。
- 先选 1–2 个高价值入口（onboarding、安全扫描、更新流程）塞进日常循环。
- 团队场景建议统一安装/更新路径，并明确哪些高风险操作需要第二模型复核。

由于能力很强，建议从单个项目渐进采用：先度量可靠性与成本，再扩展到更多任务。

### README 原文节选（verbatim）

<!-- SPDX-License-Identifier: MIT -->
<!-- SPDX-FileCopyrightText: 2025-2026 Marcus Quinn -->

# AI DevOps Framework

**[aidevops.sh](https://aidevops.sh)** — An [OpenCode](https://opencode.ai/) plugin and AI operations platform for launching and managing development, business, marketing, and creative projects. 11 primary agents handle automatable work across every domain so your time is preserved for real-world discovery and decisions that AI cannot yet reach.

> **Recommended setup:** [OpenCode](https://opencode.ai/) + OpenAI models. GPT-5.5 is the preferred high-capability model for complex agent work; GPT-5.4 mini is the preferred fast, lower-cost model for triage and routine implementation. Claude models (Anthropic) remain fully supported, and other model providers are evaluated from time to time as their quality, latency, and cost profiles change.

*"Scope a mission to redesign the landing pages — break it into milestones, dispatch workers in parallel, validate each milestone, and track budget across the whole project"*

**One conversation, autonomous project delivery — with enterprise-level security & quality-control.**

Founded by [Marcus Quinn](https://github.com/marcusquinn) on 9th November 2025 to help anyone level-up their AI & Open-Source game.

## **The Philosophy**

**Maximum value for your time and money.** **[aidevops](https://aidevops.sh)** is built on these principles:

- **Autonomous orchestration** - An AI supervisor runs every 2 minutes, dispatching parallel workers, merging PRs, detecting stuck processes, and advancing multi-day missions — no human babysitting required
- **Multi-domain agents** - 11 primary agents covering code, automation, product, SEO, marketing/sales, content/video/social, legal, research, business/accounts, health, and framework operations with 900+ subagents loaded on demand
- **Multi-model safety** - High-stakes operations (force push, production deploy, data migration) are verified by a second cross-provider model before execution — different providers have different failure modes, so correlated hallucinations are rare
- **Resource efficiency** - Cost-aware model routing across OpenAI, Anthropic, Gemini, Cursor, and local models; project-type bundles auto-configure quality gates and model tiers, with budget tracking and burn-rate analysis
- **Self-healing** - When something breaks, diagnose the root cause, create tasks, and fix it. Every error is a live test case for a permanent solution

### FAQ

**aidevops 只是一个 CLI 吗？**
答：不止：它同时是 OpenCode 插件与运维框架，包含 playbook 与质量门禁（见 README）。

**怎么安装？**
答：README 推荐 `npm install -g aidevops && aidevops update`（也提供 Homebrew/源码路径）。

**最适合什么场景？**
答：需要多 agent 并行交付、并要求流程可复用、可审计、可 review 的团队。

## 来源与感谢

> Source: https://github.com/marcusquinn/aidevops
> License: MIT
> GitHub stars: 234 · forks: 44


---
Source: https://tokrepo.com/en/workflows/aidevops-ai-devops-framework-with-agent-playbooks
Author: Script Depot