AI DevOps Framework

aidevops.sh — Unleash your AI assistant's true potential with specialist DevOps agents, designed to manage all your infrastructure and services with security and reliability guidance on every decision.

"List all my servers and websites, and check each for theme and plugin update needs, SEO and page loading performance scores, and give me a list of recommended priorities" - One conversation, complete infrastructure management.

Why This Framework?

Beyond Single-Repo Limitations: VS Code and Web UIs work on one repo at a time. CLI AI assistants can manage your entire infrastructure when given the right tools, access, and guidance.

DevOps Superpowers for AI:

GitHub Actions Quality Gate Status CodeFactor Maintainability Codacy Badge CodeRabbit

License: MIT Copyright

GitHub stars GitHub forks GitHub watchers

GitHub release (latest by date) GitHub Release Date GitHub commits since latest release

Version GitHub repo size Lines of code GitHub language count GitHub top language

GitHub issues GitHub closed issues GitHub pull requests GitHub contributors

Services Supported AGENTS.md AI Optimized MCP Servers API Integrations

Enterprise-Grade Quality & Security

Comprehensive DevOps framework with tried & tested services integrations, popular and trusted MCP servers, and enterprise-grade infrastructure quality assurance code monitoring and recommendations.

Security Notice

This framework provides agentic AI assistants with powerful infrastructure access. Use responsibly.

Capabilities: Execute commands, access credentials, modify infrastructure, interact with APIs Your responsibility: Use trusted AI providers, rotate credentials regularly, monitor activity

Quick Start

One-liner install (fresh install or update):

bash <(curl -fsSL https://raw.githubusercontent.com/marcusquinn/aidevops/main/setup.sh)

Or manually:

git clone https://github.com/marcusquinn/aidevops.git ~/Git/aidevops
~/Git/aidevops/setup.sh

That's it! The setup script will:

After installation, use the CLI:

aidevops status     # Check what's installed
aidevops update     # Update to latest version
aidevops uninstall  # Remove aidevops

Your AI assistant now has agentic access to 30+ service integrations.

Supported AI Assistants: (OpenCode & Zed are our daily drivers and preferred tools, so will have the most continual testing. All 18 assistants below have MCP configuration support.)

Preferred:

IDE-Based:

Claude Family:

Enterprise & Professional:

Specialized:

Terminal & CLI:

Core Capabilities

AI-First Infrastructure Management:

Unified Interface:

Quality Control & Monitoring:

Requirements

# Install dependencies (auto-detected by setup.sh)
brew install sshpass jq curl mkcert dnsmasq  # macOS
sudo apt-get install sshpass jq curl dnsmasq  # Ubuntu/Debian

# Generate SSH key
ssh-keygen -t ed25519 -C "[email protected]"

Comprehensive Service Coverage

Infrastructure & Hosting

Domain & DNS

Development & Git Platforms with CLI Integration

WordPress Development

Git CLI Enhancement Features:

Security & Code Quality

AI Prompt Optimization

Performance & Monitoring

AI & Documentation

MCP Integrations

Model Context Protocol servers for real-time AI assistant integration. The framework helps configure these MCPs for 18 AI assistants including OpenCode (preferred), Cursor, Claude Code/Desktop, Windsurf, Continue.dev, Cody, Zed, GitHub Copilot, Kilo Code, Kiro, AntiGravity, Gemini CLI, Droid, Warp AI, Aider, and Qwen.

All Supported MCPs

MCP Purpose API Key Required
Ahrefs SEO analysis & backlinks Yes
Augment Context Engine Semantic codebase retrieval Yes (Augment account)
Chrome DevTools Browser debugging & automation No
Cloudflare Browser Server-side rendering Yes (Cloudflare)
Context7 Library documentation lookup No
Crawl4AI Web crawling & scraping No
Google Search Console Search performance data Yes (Google API)
Grep by Vercel GitHub code search No
LocalWP WordPress database access No (local)
Next.js DevTools React/Next.js assistance No
Outscraper Google Maps & business data extraction Yes
PageSpeed Insights Performance auditing Yes (Google API)
Perplexity AI-powered research Yes
Playwright Cross-browser testing No
Repomix Codebase packing for AI context No
Snyk Security vulnerability scanning Yes
Stagehand (JS) AI browser automation Optional (Browserbase)
Stagehand (Python) AI browser automation Optional (Browserbase)

By Category

Context & Codebase:

Browser Automation:

SEO & Research:

Data Extraction:

Performance & Security:

WordPress & Development:

Quick Setup

# Install all MCP integrations
bash .agent/scripts/setup-mcp-integrations.sh all

# Install specific integration
bash .agent/scripts/setup-mcp-integrations.sh stagehand          # JavaScript version
bash .agent/scripts/setup-mcp-integrations.sh stagehand-python   # Python version
bash .agent/scripts/setup-mcp-integrations.sh stagehand-both     # Both versions
bash .agent/scripts/setup-mcp-integrations.sh chrome-devtools

Repomix - AI Context Generation

Repomix packages your codebase into AI-friendly formats for sharing with AI assistants. This framework includes optimized Repomix configuration for consistent context generation.

Why Repomix?

Use Case Tool When to Use
Interactive coding Augment Context Engine Real-time semantic search during development
Share with external AI Repomix Self-contained snapshot for ChatGPT, Claude web, etc.
Architecture review Repomix (compress) 80% token reduction, structure only
CI/CD integration GitHub Action Automated context in releases

Quick Usage

# Pack current repo with configured defaults
npx repomix

# Compress mode (~80% smaller, structure only)
npx repomix --compress

# Or use the helper script
.agent/scripts/context-builder-helper.sh pack      # Full context
.agent/scripts/context-builder-helper.sh compress  # Compressed

Configuration Files

File Purpose
repomix.config.json Default settings (style, includes, security)
.repomixignore Additional exclusions beyond .gitignore
repomix-instruction.md Custom AI instructions included in output

Key Design Decisions

MCP Integration

Repomix runs as an MCP server for direct AI assistant integration:

{
  "repomix": {
    "type": "local",
    "command": ["npx", "-y", "repomix@latest", "--mcp"],
    "enabled": true
  }
}

See .agent/tools/context/context-builder.md for complete documentation.

Augment Context Engine - Semantic Codebase Search

Augment Context Engine provides semantic codebase retrieval - understanding your code at a deeper level than simple text search. It's the recommended tool for real-time interactive coding sessions.

Why Augment Context Engine?

Feature grep/glob Augment Context Engine
Text matching Exact patterns Semantic understanding
Cross-file context Manual Automatic
Code relationships None Understands dependencies
Natural language No Yes

Use it to:

Quick Setup

# 1. Install Auggie CLI (requires Node.js 22+)
npm install -g @augmentcode/auggie@prerelease

# 2. Authenticate (opens browser)
auggie login

# 3. Verify installation
auggie token print

MCP Integration

Add to your AI assistant's MCP configuration:

OpenCode (~/.config/opencode/opencode.json):

{
  "mcp": {
    "augment-context-engine": {
      "type": "local",
      "command": ["auggie", "--mcp"],
      "enabled": true
    }
  }
}

Claude Code:

claude mcp add-json auggie-mcp --scope user '{"type":"stdio","command":"auggie","args":["--mcp"]}'

Cursor: Settings → Tools & MCP → New MCP Server:

{
  "mcpServers": {
    "augment-context-engine": {
      "command": "bash",
      "args": ["-c", "auggie --mcp -m default -w \"${WORKSPACE_FOLDER_PATHS%%,*}\""]
    }
  }
}

Verification

Test with this prompt:

What is this project? Please use codebase retrieval tool to get the answer.

The AI should provide a semantic understanding of your project architecture.

Repomix vs Augment Context Engine

Use Case Tool When to Use
Interactive coding Augment Context Engine Real-time semantic search during development
Share with external AI Repomix Self-contained snapshot for ChatGPT, Claude web, etc.
Architecture review Repomix (compress) 80% token reduction, structure only
CI/CD integration Repomix GitHub Action Automated context in releases

See .agent/tools/context/augment-context-engine.md for complete documentation including configurations for Zed, GitHub Copilot, Kilo Code, Kiro, AntiGravity, Gemini CLI, and Factory.AI Droid.

osgrep - Local Alternative (Experimental)

osgrep provides 100% local semantic search with no cloud dependency:

npm install -g osgrep && osgrep setup
osgrep "where is authentication handled?"
Feature osgrep Augment
Privacy 100% local Cloud-based
Auth None required Account + login
Node.js 18+ 22+

⚠️ Status: Currently experiencing indexing issues (v0.4.x). See .agent/tools/context/osgrep.md for details and GitHub issues #58, #26 for progress.

AI Agents & Subagents

Agents are specialized AI personas with focused knowledge and tool access. Instead of giving your AI assistant access to everything at once (which wastes context tokens), agents provide targeted capabilities for specific tasks.

Call them in your AI assistant conversation with a simple @mention

How Agents Work

Concept Description
Main Agent Domain-focused assistant (e.g., WordPress, SEO, DevOps)
Subagent Specialized assistant for specific services (invoked with @mention)
MCP Tools Only loaded when relevant agent is invoked (saves tokens)

Main Agents

Ordered as they appear in OpenCode Tab selector and other AI assistants (14 total):

Name File Purpose MCPs Enabled
Plan+ plan-plus.md Read-only planning with semantic codebase search context7, augment, repomix
Build+ build-plus.md Enhanced Build with context tools context7, augment, repomix
Build-Agent build-agent.md Design and improve AI agents context7, augment, repomix
Build-MCP build-mcp.md Build MCP servers with TS+Bun+ElysiaJS context7, augment, repomix
Accounting accounting.md Financial operations quickfile, augment
AI-DevOps aidevops.md Framework operations, meta-agents, setup context7, augment, repomix
Content content.md Content creation workflows augment
Health health.md Health and wellness guidance augment
Legal legal.md Legal compliance and documentation augment
Marketing marketing.md Marketing strategy and automation augment
Research research.md Research and analysis tasks context7, augment
Sales sales.md Sales operations and CRM augment
SEO seo.md SEO optimization, Search Console, keyword research gsc, ahrefs, augment
WordPress wordpress.md WordPress ecosystem (dev, admin, MainWP, LocalWP) localwp, context7, augment

Example Subagents with MCP Integration

These are examples of subagents that have supporting MCPs enabled. See .agent/ for the full list of 80+ subagents organized by domain.

Agent Purpose MCPs Enabled
@hostinger Hosting, WordPress, DNS, domains hostinger-api
@hetzner Cloud servers, firewalls, volumes hetzner-* (multi-account)
@wordpress Local dev, MainWP management localwp, context7
@seo Search Console, keyword research gsc, ahrefs
@code-standards Quality standards reference, compliance checking context7
@browser-automation Testing, scraping, DevTools chrome-devtools, context7
@git-platforms GitHub, GitLab, Gitea gh_grep, context7
@agent-review Session analysis, agent improvement (under build-agent/) (read/write only)

Setup for OpenCode

# Install aidevops agents for OpenCode
.agent/scripts/generate-opencode-agents.sh

# Check status
.agent/scripts/generate-opencode-agents.sh  # Shows status after generation

Setup for Other AI Assistants

Add to your AI assistant's system prompt:

Before any DevOps operations, read ~/git/aidevops/AGENTS.md for authoritative guidance.

When working with specific services, read the corresponding .agent/[service].md file
for focused guidance. Available services: hostinger, hetzner, wordpress, seo,
code-quality, browser-automation, git-platforms.

Continuous Improvement with @agent-review

End every session by calling @agent-review to analyze what worked and what didn't:

@agent-review analyze this session and suggest improvements to the agents used

The review agent will:

  1. Identify which agents were used
  2. Evaluate missing, incorrect, or excessive information
  3. Suggest specific improvements to agent files
  4. Generate ready-to-apply edits
  5. Optionally compose a PR to contribute improvements back to aidevops

This creates a feedback loop:

Session → @agent-review → Improvements → Better Agents → Better Sessions
                ↓
         PR to aidevops repo (optional)

Contributing improvements:

@agent-review create a PR for improvement #2

The agent will create a branch, apply changes, and submit a PR to marcusquinn/aidevops with a structured description. Your real-world usage helps improve the framework for everyone.

Code quality learning loop:

The @code-quality agent also learns from issues. After fixing violations from SonarCloud, Codacy, ShellCheck, etc., it analyzes patterns and updates framework guidance to prevent recurrence:

Quality Issue → Fix Applied → Pattern Identified → Framework Updated → Issue Prevented

Slash Commands (OpenCode)

Slash commands provide quick access to common workflows directly from the OpenCode prompt. Type / to see available commands.

Available Commands

Development Workflow (typical order):

Command Purpose
/context Build AI context with Repomix for complex tasks
/feature Start a new feature branch workflow
/bugfix Start a bugfix branch workflow
/hotfix Start an urgent hotfix workflow
/linters-local Run local linting (ShellCheck, secretlint)
/code-audit-remote Run remote auditing (CodeRabbit, Codacy, SonarCloud)
/code-standards Check against documented quality standards
/pr Unified PR workflow (orchestrates all checks)

Release Workflow (in order):

Command Purpose
/preflight Run quality checks before release
/changelog Update CHANGELOG.md with recent changes
/version-bump Bump version following semver
/release Full release workflow (bump, tag, GitHub release)
/postflight Verify release health after deployment

Meta/Improvement:

Command Purpose
/agent-review Analyze session and suggest agent improvements

Installation

Slash commands are automatically installed by setup.sh:

# Commands are deployed to:
~/.config/opencode/commands/

# Regenerate commands manually:
.agent/scripts/generate-opencode-commands.sh

Usage

In OpenCode, type the command at the prompt:

/preflight
/release minor
/feature add-user-authentication

Commands invoke the corresponding workflow subagent with appropriate context.

Creating Custom Agents

Create a markdown file in ~/.config/opencode/agent/ (OpenCode) or reference in your AI's system prompt:

---
description: Short description of what this agent does
mode: subagent
temperature: 0.2
tools:
  bash: true
  specific-mcp_*: true
---

# Agent Name

Detailed instructions for the agent...

See .agent/opencode-integration.md for complete documentation.

Usage Examples

Server Management

# List all servers across providers
./.agent/scripts/servers-helper.sh list

# Connect to specific servers
./.agent/scripts/hostinger-helper.sh connect example.com
./.agent/scripts/hetzner-helper.sh connect main web-server

# Execute commands remotely
./.agent/scripts/hostinger-helper.sh exec example.com "uptime"

Monitoring & Uptime (Updown.io)

# List all monitors
./.agent/scripts/updown-helper.sh list

# Add a new website check
./.agent/scripts/updown-helper.sh add https://example.com "My Website"

Domain & DNS Management

# Purchase and configure domain
./.agent/scripts/spaceship-helper.sh purchase example.com
./.agent/scripts/dns-helper.sh cloudflare add-record example.com A 192.168.1.1

# Check domain availability
./.agent/scripts/101domains-helper.sh check-availability example.com

Quality Control & Performance

# Run quality analysis with auto-fixes
bash .agent/scripts/qlty-cli.sh check 10
bash .agent/scripts/qlty-cli.sh fix

# Run chunked Codacy analysis for large repositories
bash .agent/scripts/codacy-cli-chunked.sh quick    # Fast analysis
bash .agent/scripts/codacy-cli-chunked.sh chunked # Full analysis

# AI coding assistance
bash .agent/scripts/ampcode-cli.sh scan ./src
bash .agent/scripts/continue-cli.sh review

# Audit website performance
./.agent/scripts/pagespeed-helper.sh wordpress https://example.com

Documentation & Resources

Wiki Guides:

Agent Guides (in .agent/):

Provider-Specific Guides: Hostinger, Hetzner, Cloudflare, WordPress, Git platforms, Vercel CLI, Coolify CLI, and more in .agent/

Architecture

aidevops/
├── setup.sh                       # Main setup script
├── AGENTS.md                      # AI agent guidance
├── .agent/scripts/                # Automation & setup scripts
├── .agent/scripts/                     # Service helper scripts
├── configs/                       # Configuration templates
├── .agent/                          # Comprehensive documentation
├── .agent/                        # AI agent development tools
├── ssh/                           # SSH key management
└── templates/                     # Reusable templates and examples

Configuration & Setup

# 1. Copy and customize configuration templates
cp configs/hostinger-config.json.txt configs/hostinger-config.json
cp configs/hetzner-config.json.txt configs/hetzner-config.json
# Edit with your actual credentials

# 2. Test connections
./.agent/scripts/servers-helper.sh list

# 3. Install MCP integrations (optional)
bash .agent/scripts/setup-mcp-integrations.sh all

Security & Best Practices

Credential Management:

Quality Assurance:

Contributing & License

Contributing:

  1. Fork the repository
  2. Create feature branch
  3. Add provider support or improvements
  4. Test with your infrastructure
  5. Submit pull request

License: MIT License - see LICENSE file for details Created by Marcus Quinn - Copyright © 2025

What This Framework Achieves

For You:

For Your AI Assistant:

Get Started:

bash <(curl -fsSL https://raw.githubusercontent.com/marcusquinn/aidevops/main/setup.sh)

Or: git clone https://github.com/marcusquinn/aidevops.git ~/Git/aidevops && ~/Git/aidevops/setup.sh

Transform your AI assistant into a powerful infrastructure management tool with seamless access to all your servers and services.

Back to top