Skillget

awesome-aem-ai

mcp
Security Audit
Warn
Health Warn
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 6 GitHub stars
Code Pass
  • Code scan — Scanned 3 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

A curated list of AI resources, tools, MCP servers, agents, and skills for Adobe Experience Manager (AEM) and Edge Delivery Services (EDS)

README.md

Awesome AEM AI Awesome Last Commit PRs Welcome

A curated list of AI resources, tools, MCP servers, agents, and skills for Adobe Experience Manager (AEM) and Edge Delivery Services (EDS).

The AEM AI landscape moves fast — agents, MCP servers, and skills ship monthly across Experience League, aem.live, developer blogs, and press releases. This list is the single map, refreshed as things change.

⭐ Start Here

Things this list has that you won't find in the official docs:

  • Hands-on Labs - Four step-by-step labs: AEM MCP Server, Experience Production Agent, Claude Code Skills, and ACM MCP Server (20-40 min each)
  • Ready-to-use Claude Code Skills - Six AEM backend skills (HTL, Sling Models, OSGi, clientlibs, testing, EDS blocks) you can copy into your project today
  • Community MCP Servers - The tools Adobe doesn't list: community servers for Sites, EDS, and Groovy script execution
  • Real-World Architecture Audit - A live Dispatcher security audit showing what grounded AI catches that chatbots miss

What's New (July 2026)

  • Adobe's agents restructured into Brand Experience Agent (Modernization + Production + Development), Content Advisor Agent, and Governance Agent - now GA via Agentic SKU
  • Official MCP servers grew from 2 to 5: added Cloud Manager, Experience Governance, and Cloud Migration
  • Summit 2026: Brand Visibility solution, LLM Apps, and Brand Concierge
  • adobe/skills graduated from beta - now installable as a Claude Code plugin
  • New in AEM 2026.6.0: Visual Content Fragments, AI Translation, AI Search, Brand Aware Metadata

Contents

Official Resources

Adobe Documentation

Adobe AI Products

See also: Dedicated LLM Optimizer Section for complete documentation, tutorials, and guides.

Announcements

Architecture

Adobe Experience Platform Agent Orchestrator

The Agent Orchestrator is the agentic layer powering AEM AI agents. It coordinates specialized agents across workflows and applications.

┌─────────────────────────────────────────────────────────────────────┐
│                    AI Assistant (Conversational UI)                  │
├─────────────────────────────────────────────────────────────────────┤
│                         Reasoning Engine                             │
│   • Interprets natural language prompts                              │
│   • Creates step-by-step execution plans                             │
│   • Adjusts dynamically, retries alternative approaches              │
├─────────────────────────────────────────────────────────────────────┤
│                    Adobe Experience Platform Agents                  │
│  ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ ┌─────────────┐ │
│  │  Discovery   │ │   Content    │ │  Experience  │ │ Development │ │
│  │    Agent     │ │ Optimization │ │  Production  │ │   Support   │ │
│  └──────────────┘ └──────────────┘ └──────────────┘ └─────────────┘ │
├─────────────────────────────────────────────────────────────────────┤
│                         Knowledge Base                               │
│   • Adobe product documentation                                      │
│   • Customer metadata & business objects                             │
│   • Analytics data                                                   │
└─────────────────────────────────────────────────────────────────────┘

Documentation: Agent Orchestrator | Platform Learn Tutorial

Key Components

Component Description Documentation
Conversational Interface Natural language interaction via AI Assistant Docs
Reasoning Engine Interprets goals, creates plans, adjusts dynamically Docs
Knowledge Base Secure access to documentation, metadata, analytics Docs
LLM Service Azure OpenAI or Meta Llama models Docs

Built-in Functional Agents

Agent Purpose Scope
Product Knowledge Agent Retrieves and answers from Adobe documentation Documentation queries
Operational Insights Agent Translates questions to queries against data stores Analytics & reporting
Product Support Agent Troubleshooting for AEM, Platform, CJA, Journey Optimizer Support tickets

Experience Modernization Agent Architecture

The Experience Modernization Agent automates migration to Edge Delivery Services:

┌─────────────────────────────────────────────────────────────────────┐
│                   Experience Modernization Console                   │
│                      (Web Interface)                                 │
├─────────────────────────────────────────────────────────────────────┤
│                        AI Coding Agent                               │
│  ┌──────────────────────────────────────────────────────────────┐   │
│  │                    Migration Skills                           │   │
│  │  • Page decomposition & section identification                │   │
│  │  • Block mapping against library                              │   │
│  │  • Design system extraction (colors, fonts, CSS)              │   │
│  │  • Bulk content import                                        │   │
│  └──────────────────────────────────────────────────────────────┘   │
├─────────────────────────────────────────────────────────────────────┤
│                      Integration Layer                               │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐  ┌────────────┐  │
│  │   GitHub    │  │    Figma    │  │  Live AEM   │  │   Source   │  │
│  │ Integration │  │ MCP Server  │  │   Preview   │  │  Website   │  │
│  └─────────────┘  └─────────────┘  └─────────────┘  └────────────┘  │
├─────────────────────────────────────────────────────────────────────┤
│                    Edge Delivery Services                            │
│              (Production-ready output)                               │
└─────────────────────────────────────────────────────────────────────┘

Workflow:

  1. Analyze source pages → Identify visual sections
  2. Map sections → Match against block library
  3. Extract design system → Generate CSS (colors, fonts, styles)
  4. Create PRs → GitHub integration for review
  5. Deploy → Direct to Edge Delivery Services

Documentation: Overview | AEM Playground

Security & Governance

  • Enterprise-grade trust layer - Built-in data access controls
  • Consent management - Respects data-usage policies
  • Human oversight - Agents follow user input and product-level access controls
  • Transparent workflow - Exposes reasoning logic, queries, and conversation history
  • Audit trail - All agent actions are logged and explainable

Documentation: AI in Experience Cloud

Core AI Services & Trust

Foundational AI technologies and ethics powering the AEM ecosystem.

Service Role Key Feature
Adobe Firefly Generative Engine Commercially safe image generation and creative editing.
Adobe Sensei GenAI Experience Intelligence Powers copy variations, content discovery, and intelligent automation.
Responsible AI Ethical Framework Framework focusing on accountability, responsibility, and transparency.
Experience Cloud Performance Contextual Intelligence Real-time performance insights to tailor AI outputs to customer personas.

Architecture Resources

Resource Description Link
AEM Cloud Service Architecture Core AEM architecture overview Docs
EDS Architecture Edge Delivery Services deep dive Docs
Adobe Developers Live 2025 AEM Agents session recording Video
Experience Cloud Blueprints Reference architecture diagrams Docs

MCP Servers

Model Context Protocol (MCP) servers that integrate with AEM and EDS.

Official Adobe MCP Servers

Adobe provides official MCP servers hosted at https://mcp.adobeaemcloud.com/adobe/mcp/:

Server Endpoint Description
Content Server /content Full CRUD operations for pages, fragments, and assets
Content Read-Only /content-readonly Read-only access for retrieval operations
Cloud Manager /cloudmanager Manage programs, environments, repositories, and pipelines
Experience Governance /experience-governance Assess content compliance against brand governance standards
Cloud Migration /cloud-migration Migration analysis data for AEM 6.x to Cloud Service transitions

Key Features:

  • Natural language interaction with AEM content
  • OAuth authentication via Adobe ID
  • Respects user's AEM permissions
  • Supports Claude, ChatGPT, Cursor, VS Code, JetBrains, GitHub Copilot, Claude Code, Cline, Windsurf, and Microsoft Copilot Studio

Official Documentation

Local Runtime MCP Servers

Model Context Protocol (MCP) servers that connect AI tools to local running environments (AEM SDK and Dispatcher).

Server Components Description
AEM Quickstart MCP Server aem-logs, diagnose-osgi-bundle, recent-requests Full inspection of local OSGi, logs, and HTTP request traces
Dispatcher MCP Server validate, lint, trace_request, inspect_cache Static and best-practice checks, request tracing, cache analysis

Official Documentation

Community MCP Servers

Name Description Links
aem-mcp-server Full-featured MCP server for AEM - 35+ methods for content, components, assets npm / GitHub
aem-sites-mcp Sites-specific MCP server for local AEM instance management GitHub
acm-mcp-server MCP server for AEM Content Manager (ACM) - execute Groovy scripts via AI GitHub

Edge Delivery Services MCP Servers

Name Description Links
helix-mcp Docs search, page status, audit logs, and RUM/Core Web Vitals tools for EDS and Document Authoring sites GitHub
aem-eds-mcp-server 10 consolidated tools for EDS via the Helix Admin API - content management, config, jobs, search npm

Also recommended by aem.live: Context7 (API docs indexing including AEM), DA MCP Server (Document Authoring content workflows), and Browser MCP (remote browser control and screenshots).

AI Agents

Official Adobe Agents

Adobe's AEM agents are organized into three top-level agents. Overview

Agent Purpose Status
Brand Experience Agent Automates high-effort operational tasks via specialized sub-agents (Modernization, Production, Development) GA
Content Advisor Agent Discover, refine, and adapt assets via natural language for channel-ready variations GA
Governance Agent Enforces security, regulatory, and brand policies to protect brand integrity GA

Try before you buy: AEM Playground - isolated sandbox for agentic workflows (auto-deletes after 30 days). Production access via the Agentic SKU - contact your Adobe CSM/TAM.

Brand Experience Agent

Umbrella agent for operational automation. Overview

Experience Production Agent

Automates high-effort, high-volume content tasks. Overview

Skill Description Documentation
Content Update Job Update, remove, replace content in pages, fragments, forms via natural language or Jira Docs
Content Create Job Create net-new content via natural language (Limited Availability - email [email protected]) Docs
Figma to Visual Content Fragments Turn Figma designs into Visual Content Fragments Docs
Forms Creation Job Build adaptive forms through natural language without development teams Docs
Communication Creation Job Generate personalized, data-driven correspondence (statements, policies, bills) Docs

Content Update Skill Technical Details:

  • Content Types: Pages, Content Fragments, Adaptive Forms, Assets
  • Operations: Update, remove, replace, add content elements
  • Input Methods: Natural language prompts or Jira ticket integration
  • Integration: Direct AEM author instance connectivity
Experience Modernization Agent

AI-powered website migration to Edge Delivery Services. Overview

Skill Description
Site Migration Transform websites from any CMS, legacy AEM, or Figma into EDS projects
Block Development Content-Driven Development methodology with Block Collection/Party
Design Extraction Extract colors, fonts, styles into CSS from source sites

Console: Available at aemcoder.adobe.io - no local setup required

Experience Development Agent

AI-assisted troubleshooting and build automation for AEM Cloud Service. Overview

Capability Description
Pipeline Troubleshooting Analyze logs and suggest fixes for failing Full Stack and Web Tier Config pipelines
Conversational Cloud Manager Ask questions about programs, environments, and pipelines in natural language
Maintenance Windows AI-assisted management of Quiet Hours and Update Free Periods

Access: Requires Cloud Manager Developer or Program Manager role

Content Advisor Agent

Discover, refine, and adapt assets through natural language. Overview

Capability Description
Semantic Discovery Find assets, Content Fragments, and Adaptive Forms using conversational prompts
Advanced Filtering Format, orientation, dimensions, metadata, tags, folders, creation dates
Image Optimization Format conversion, resolution, cropping, sharpening, background changes
Multi-Variant Production Generate channel-ready renditions from single prompts (Instagram, web banners, etc.)
Dynamic Variant Generation Create optimized variants as dynamic URLs for different channels

Governance Agent

Brand integrity and compliance enforcement. Overview

Capability Description
Compliance Monitoring Detect policy violations in real-time
Metadata Enforcement Ensure assets have required metadata
Brand Validation Check content against tone, claims, logo, typography, imagery rules

Integration: Works with ChatGPT, Claude, and other AI systems via A2A and MCP protocols, plus the official /experience-governance MCP server

Agent Resources

Resource Description Link
Agents Overview Complete agents documentation Docs
Agents in AEM Tutorial Hands-on learn tutorial Docs
AEM Playground Sandbox for agentic workflows aem.live
AI in AEM Overview All AI capabilities in AEM Docs
Developers Live 2025 AEM Agents session recording Video

Availability: AEM as a Cloud Service and Edge Delivery Services (GA via Agentic SKU); progressive rollout to AEM 6.5 LTS on Managed Services is planned

Claude Code Skills

Official Adobe Skills (adobe/skills)

The adobe/skills repository is now production-ready (main branch) and covers AEM EDS, AEM Cloud Service, AEM 6.5 LTS, project management, App Builder, Analytics/CJA, and Creative Cloud.

# Install as a Claude Code plugin (recommended)
/plugin marketplace add adobe/skills

# Install via npx (Vercel Skills)
npx skills add adobe/skills --all

# Install via gh-upskill
gh upskill adobe/skills --all

AEM Cloud Service skills include:

Skill Description
ensure-agents-md Bootstraps AGENTS.md by detecting modules from pom.xml
create-component Scaffolds dialogs, HTL, Sling Models, tests, and clientlibs
dispatcher Assistant for Apache/Dispatcher security, performance, and tuning
workflow Designs models, develops process steps, and diagnoses failures
aem-rde Rapid Development Environment assistance (beta)

Official Adobe EDS Skills

Install official Adobe skills from adobe/helix-website:

# Install via gh-upskill
gh extension install trieloff/gh-upskill
gh upskill adobe/helix-website --all

15 skills available: content-driven-development, page-import, building-blocks, content-modeling, testing-blocks, code-review, docs-search, block-inventory, block-collection-and-party, page-decomposition, identify-page-structure, scrape-webpage, generate-import-html, preview-import, authoring-analysis

AEM Core Skills (This Repository)

Pre-built AEM backend skills available in .claude/skills/:

Skill Description File
aem-htl HTL/Sightly templating, data binding, contexts, i18n View
aem-sling-models Sling Models, injectors, delegation, exporters View
aem-osgi OSGi services, configs, schedulers, events View
aem-clientlibs Client libraries, dependencies, optimization View
aem-testing Unit tests, AEM Mocks, integration tests View
eds-blocks EDS block development, patterns, utilities View

Installation

# Copy this repo's skills to your AEM project
cp -r .claude/skills/ /path/to/your/aem-project/.claude/skills/

Skills Tools

Tool Description Install
gh-upskill Install skills from any GitHub repo gh extension install trieloff/gh-upskill
openskills Universal skills loader for AI agents npx openskills install
claude-skills-cli Create and validate Claude skills npx claude-skills-cli init

Documentation

IDE Extensions & Plugins

VS Code Extensions

Extension Description Marketplace
AEM Sync Sync file changes to AEM automatically Link
VSCode AEM Sync Sync files, folders, nodes to AEM Link
AEM Copilot GitHub Copilot for AEM Edge Delivery Services Link
AEM Explorer Integrates AEM to VS Code for development Link

IntelliJ Plugins

Plugin Description Marketplace
AEM IDE Comprehensive AEM development tools Link

AI Features by AEM Product

Adobe GenStudio

Feature Description Documentation
Performance Marketing AI-powered content supply chain for creating, manage, and measure marketing content Docs
Content Generation Generate on-brand content variations across channels Docs
Brand Compliance Ensure content meets brand guidelines using AI Docs
Multi-Channel Delivery Optimize and deliver content to web, social, email, and ads Docs

AEM Sites

Feature Description Documentation
Visual Content Fragments Render structured content as formatted HTML experiences for visual preview before publication (GA 2026.6.0) Docs
AI Translation LLM-powered content translation (Azure OpenAI as provider, more LLMs planned) Docs
Generate Variations AI-powered content variations for Content Fragments and EDS Docs
Generative AI Overview GenAI for content creation and personalization Docs

AEM Assets

Feature Description Documentation
AI Search Natural language asset search ("a family at the beach") without exact metadata matches Docs
Brand Aware Metadata AI-generated custom metadata on upload/re-process using prompt libraries (Early Adopter) Docs
AI-Generated Video Captions Automatic caption generation for Dynamic Media with OpenAPI videos (GA 2026.6.0) Docs
Smart Tags Automatic AI tagging for images and videos Docs
Smart Crop AI-powered focal point detection and cropping Docs
Dynamic Media AI Smart imaging and video optimization Docs
Content Advisor Agent Natural language asset discovery and refinement Docs

AEM Forms

Feature Description Documentation
Generative AI for Forms AI-powered form generation and panel creation Docs
AI Assistant Product knowledge and authoring assistance Docs
Content Advisor Agent Intelligent search across Adaptive Forms Docs
Forms Creation Job Build adaptive forms through natural language Docs

AEM Guides

Feature Description Documentation
AI Assistant Smart help and authoring features Docs
Smart Suggestions AI-powered content reuse recommendations Docs

AEM Screens

Feature Description Documentation
Data-Driven Personalization Rules-based personalization for digital signage based on location, time, audience data Docs
Smart Image Cropping AI-powered focal point detection for screen dimensions (inherited from Assets) Docs
Adobe Analytics Integration Understanding signage performance with analytics Docs
Adobe Target A/B Testing AI-assisted testing for digital signage content Docs

Note: AEM Screens inherits AI capabilities from AEM Sites and Assets (Smart Tags, Smart Crop, etc.) for content that is published to digital signage displays.

Migration & Modernization

Feature Description Documentation
Experience Modernization Agent AI-assisted migration to Edge Delivery Services Docs
Cloud Migration MCP Server Migration analysis data for AEM 6.x to Cloud Service via MCP Docs
AEM Modernization Tools Convert legacy AEM to modern patterns Docs

Adobe LLM Optimizer

Generative Engine Optimization (GEO) for AI search visibility in ChatGPT, Perplexity, Copilot, Gemini, and other LLM-driven assistants.

Overview

Adobe LLM Optimizer is a generative AI-first application designed to help brands enhance their visibility, accuracy, and influence in AI-driven search environments. It provides insights into brand presence in AI-generated answers, offers prescriptive content recommendations, and automates optimization fixes.

Key Features

Feature Description Documentation
Brand Presence Dashboard Command center for brand mentions, citations, and sentiment in AI responses Docs
Optimization Opportunities Auto-detected insights for site and content improvements Docs
Customer Configuration Configure categories, topics, prompts, brand aliases Docs
Optimize at Edge CDN-layer optimizations without CMS authoring changes; Claude model support for content optimization Docs
Agentic Traffic Dashboard Monitor traffic from AI assistants and agents hitting your properties Docs
Referral Traffic Insights Track user clicks from AI citations, with model/platform change markers on charts Docs
Adobe Analytics Integration Connect Adobe Analytics to measure referral traffic and business impact (GA) Docs

LLM Optimizer is part of Adobe's Brand Visibility solution (Summit 2026) alongside Brand Concierge and LLM Apps.

Tutorials & Guides

Resource Description Link
Quick Start Onboarding and initial setup guide Docs
LLM Optimizer Overview Complete platform overview and walkthrough Docs
Best Practices Strategic planning, onsite/offsite optimization, agentic traffic Docs
Interactive Tour Hands-on tour of Adobe LLM Optimizer Demo
Why We Created LLM Optimizer Product vision and use cases Blog

Integration

  • AEM Cloud Service - Native integration with AEM as a Cloud Service
  • Edge Delivery Services - Optimize EDS sites for LLM visibility
  • CDN Configuration - Configure CDN for AI agent traffic targeting

Use Cases:

  • Improve brand citations in AI-generated answers
  • Optimize content structure for LLM readability
  • Track performance across ChatGPT, Google AI Overviews, Copilot, Gemini, Perplexity
  • Automated optimization fixes via CDN edge deployments

Getting Started

  1. Complete domain onboarding
  2. Configure categories, topics, and prompts
  3. Set up CDN log forwarding
  4. Monitor brand presence dashboard
  5. Apply optimization recommendations

Official Documentation

Edge Delivery Services AI

Official Documentation (aem.live)

Resource Description Link
Developer Tutorial Get started with EDS in 10-20 minutes Tutorial
AI Coding Agents Guide to using Claude Code, Cursor, Codex, Gemini, Copilot, and Zed with EDS Guide
AEM Playground Isolated sandbox for agentic workflows (auto-deletes after 30 days) Playground
llms.txt AEM documentation optimized for AI consumption llms.txt
Block Collection Curated production-ready blocks Blocks
CLI Reference aem up, aem import commands CLI
Block Party Community-built blocks showcase Block Party
Universal Editor Blocks Blocks for UE authoring UE Blocks
Architecture Deep dive into EDS architecture Architecture

Adobe Helix Claude Skills

Official skills from adobe/helix-website:

Orchestration Skills:

  • content-driven-development - Complete workflow for building/modifying blocks
  • page-import - Orchestrates migrating webpages to AEM EDS

Functional Skills:

  • building-blocks - Core block development
  • content-modeling - Content schema definitions
  • testing-blocks - Block testing and validation
  • code-review - Code review workflows

Research Skills:

  • docs-search - Search AEM documentation
  • block-inventory - Track available blocks
  • block-collection-and-party - Find existing blocks

Import Skills:

  • page-decomposition - Break pages into components
  • identify-page-structure - Detect page layout
  • scrape-webpage - Web scraping utilities
  • generate-import-html - HTML import generation
  • preview-import - Preview imports

Installing Adobe Skills

# Install gh-upskill extension
gh extension install trieloff/gh-upskill

# Add Adobe EDS skills to your project
gh upskill adobe/helix-website

# Or install standalone
curl -fsSL https://raw.githubusercontent.com/trieloff/gh-upskill/main/install.sh | bash
upskill adobe/helix-website --all

Development Tools

AI Grounding & Configuration

Essential files for grounding AI agents (Claude, Cursor, Copilot) in AEM Cloud Service project context.

File Purpose Description
AGENTS.md AI Grounding Markdown file at project root providing AEM/OSGi context to AI agents. Prevents hallucinations of legacy patterns.
.aem-skills-config.yaml Metadata Storage Config file for project-specific metadata (Java package, group ID) to ensure AI-generated code follows local conventions.
llms.txt AI Documentation aem.live/llms.txt - AEM documentation formatted for AI consumption.

AEM Code Assessment IDE Agent

Early Adopter program (2026.6.0): detects and auto-fixes issues in AEM codebases, including deprecated API replacement and Maven dependency updates. See current release notes.

npm Packages

Official Adobe Packages

Package Description Install
@adobe/aem-cli AEM/EDS CLI for local development npm i -g @adobe/aem-cli
@adobe/aem-headless-client-js AEM Headless SDK Client npm i @adobe/aem-headless-client-js
@adobe/aem-import-helper Helper tool for importing sites to AEM npm i @adobe/aem-import-helper
@adobe/aem-upload AEM Assets direct binary uploading npm i @adobe/aem-upload
@adobe/aem-spa-page-model-manager SPA Editor page model manager npm i @adobe/aem-spa-page-model-manager

Community MCP & AI Packages

Package Description Install
aem-mcp-server MCP server for AEM - chat with your AEM instance npm i -g aem-mcp-server
openskills Universal skills loader for AI coding agents npx openskills install
claude-skills-cli CLI for creating Claude Agent Skills npx claude-skills-cli init

Development Tools

Package Description Install
aemsync Code sync for Sling/AEM npm i -g aemsync
aem-clientlib-generator Creates AEM ClientLibs config files npm i aem-clientlib-generator
aem-import-builder AI capabilities for AEM import scripts npm i aem-import-builder

CLI Commands

# AEM CLI - local development server with AI coding agents support
aem up

# AEM Project Archetype
mvn archetype:generate -DarchetypeGroupId=com.adobe.aem -DarchetypeArtifactId=aem-project-archetype

Real-World Architecture Audit (Non-Fluff Demo)

To demonstrate the difference between "GenAI chat" and "Architectural Intelligence," we performed a live audit of the AEM WKND Reference Site Dispatcher configurations using the principles defined in this guide.

The Objective

Identify security vulnerabilities in the Dispatcher filter rules that a standard chatbot would miss, but a grounded AEM agent can detect.

Step 1: Automated Analysis

We ran the aemanalyser-maven-plugin (integrated via the dispatcher skill) against the wknd-test project.

# Executing the audit
mvn com.adobe.aem:aemanalyser-maven-plugin:analyse -pl dispatcher -am

Step 2: Findings (Critical Vulnerability Detected)

The audit identified a high-risk misconfiguration in dispatcher/src/conf.dispatcher.d/filters/filters.any:

Vulnerable Code:

# Rule /0201 in filters.any
/0201 { /type "allow" /url "/home/users/*.infinity.json" }

Architectural Impact:

  • Vulnerability: This rule allows external access to user profile nodes via the .infinity.json selector.
  • Risk: An attacker can crawl /home/users to dump sensitive user metadata, preferences, and potentially hashed credentials or PII (Personally Identifiable Information).
  • Compliance: This violates the AEM Cloud Service Security Checklist which mandates that /home should never be exposed via Dispatcher.

Step 3: Proactive Fix

A "really good" AI doesn't just report this; it provides the surgical fix:

# Recommended Fix: Restrict access to specific, non-sensitive pagedata only
/0201 { /type "deny" /url "/home/users/*" }
/0202 { /type "allow" /url "/home/users/*.token.json" } # If specific token exchange is needed

Best Practices & AI Workflow

Guidelines for successfully integrating AI into your AEM development lifecycle.

Core Principles

  1. Ground the Agent First: Always ensure AGENTS.md is present at the root of your project. This ensures AI agents (Claude, Cursor, Copilot) understand they are working on an AEM Cloud Service Java/OSGi project and prevents legacy code hallucinations.
  2. Use Specialized Skills Over General Chat: Prefer specialized instruction sets like create-component or dispatcher over general prompts. These skills encode multi-step Adobe best practices and mandatory file structures (dialogs, Sling Models, tests).
  3. Connect to the Runtime: Use MCP servers (AEM Quickstart and Dispatcher) to give your AI "eyes" into the running environment. This allows it to debug OSGi failures and request traces in real-time.
  4. Iterative Component Creation: When creating components, provide a detailed dialog specification (field names, types, labels) to the create-component skill for a high-fidelity first draft.
  5. Verify Locally Before Deployment: Use the dispatcher skill and MCP server to validate configurations against your local Docker container before committing to Cloud Manager.

Standard AI-Enhanced Workflow

  1. Bootstrap: Run ensure-agents-md to initialize project context.
  2. Develop: Use create-component to scaffold backend and frontend code.
  3. Debug: Use aem-logs and diagnose-osgi-bundle via MCP to fix runtime issues.
  4. Harden: Use dispatcher skill to audit security and performance.
  5. Refine: Use Generate Variations in the AEM Editor to polish copy and images.

Tutorials & Learning

Official Adobe Learning

Resource Description Link
AI in AEM Overview Official AI documentation Docs
Generative AI in AEM Sites Video tutorial on GenAI features Video
EDS Developer Tutorial Get started with Edge Delivery Services Tutorial
Experience Modernization Getting started with the migration agent Guide

Hands-on Labs

Step-by-step tutorials for practical AI implementation in AEM.

Lab Topic Duration Description
Lab 1 AEM MCP Server 20-30 min Set up and configure AEM MCP Server for natural language AEM interaction
Lab 2 Experience Production Agent 25-35 min Automate content operations using AI agents
Lab 3 Claude Code Skills 30-40 min Enhance AEM/EDS development with AI skills
Lab 4 ACM MCP Server 30-40 min Set up ACM MCP for Groovy script execution via AI

Quick Start:

git clone https://github.com/narendragandhi/awesome-aem-ai.git
cd awesome-aem-ai/tutorials

Certifications

Community Projects

Open Source

Project Description Stars
ACS AEM Commons Community utilities for AEM GitHub stars
AEM Guides WKND Sample AEM project GitHub stars
Helix Project Boilerplate EDS starter template GitHub stars

Community Tools

Tool Description Link
AEM Groovy Console Script execution for AEM GitHub
AEM Block Collection Curated EDS blocks GitHub

Videos & Presentations

Adobe Developers Live

Video Description Link
Building the Agentic Web AEM Agents, Content AI Foundational - ADL 2025 Keynote YouTube
Bringing Intelligence to Content in AEM Content AI in AEM - ADL 2025 YouTube
Accelerate your Edge Delivery Tutorial EDS Tutorial with AEM trial YouTube
AEM Release 2026.03 Release overview with latest AI features Video
AEM Release 2026.01 Release overview with latest AI features Video
Brand Concierge at Developers Live Enhance onsite experience with Brand Concierge Video
AEM Release 2025.01 New AI features in AEM 2025.01 YouTube
AEM Release 2025.02 Content Fragment Auto Tagging, EDS features YouTube

AI & MCP Tutorials

Video Description Link
Unlocking AEM's Potential with AI AI integration in AEM - Agentic, GenAI, AI Assistant YouTube
AI Assistant in AEM Configuration and live demo YouTube
AEM + MCP Integration MCP for content, components, assets management Playbooks

AEM Rocks Episodes

Adobe Summit Sessions

YouTube Channels

Webinars

Related Awesome Lists

Contributing

Contributions are welcome! Please read the contribution guidelines first.

How to Contribute

  1. Fork this repository
  2. Create a new branch (git checkout -b feature/add-resource)
  3. Add your resource to the appropriate section
  4. Commit your changes (git commit -am 'Add awesome resource')
  5. Push to the branch (git push origin feature/add-resource)
  6. Create a Pull Request

Contribution Guidelines

  • Ensure the resource is relevant to AEM and AI
  • Provide accurate descriptions
  • Include working links
  • Follow the existing format

License

CC0

To the extent possible under law, the contributors have waived all copyright and related or neighboring rights to this work.

Built with AI for the AEM Community

Reviews (0)

No results found