microsoft/edge-ai

microsoft/edge-ai

Description: Production-ready Infrastructure as Code, applications, pluggable components, and PlatformOps toolchains that empower organizations to achieve more with cloud and edge AI-powered solutions. Built by friendly geeks, for every team that needs edge solutions to achieve real production results.

Language: HCL

License: MIT

Stars: 87

Forks: 41

Open issues: 99

Created: 2025-03-19T23:33:05Z

Pushed: 2026-06-11T03:08:10Z

Default branch: main

Fork: no

Archived: no

README:

Edge AI Accelerator

  

Production-ready Infrastructure as Code that empowers organizations to achieve more with edge AI solutions. Built by friendly geeks, for every team that needs edge solutions to achieve real production results.

🎯 Who This Is For

• Platform Engineers building edge AI infrastructure at scale
• DevOps Teams deploying IoT and edge computing solutions
• Solution Architects designing hybrid cloud-edge systems
• Every organization that needs edge infrastructure solutions that actually deliver production results

🚀 Get Started (Pick Your Adventure)

→ [Just Want to Deploy Something?](docs/getting-started/general-user.md)

Start here if you want to achieve rapid deployment with existing blueprints to Azure. Time: 30-60 minutes

→ [Building Custom Solutions?](docs/getting-started/blueprint-developer.md)

Start here if you're combining components to achieve new deployment scenarios. Time: 2-4 hours

→ [Contributing New Features?](docs/getting-started/feature-developer.md)

Start here if you're developing new components to help others achieve more. Time: 1-2 days setup

🗺️ Your Deployment Journey

graph TD
Start([Target: Edge AI Solutions])

subgraph experience [Your Experience Level]
Beginner[New to Edge AI
Need to learn
fundamentals]
Intermediate[Some Experience
Want to deploy
quickly]
Advanced[Expert Level
Building custom
solutions]
end

subgraph deployment [Deployment Path]
QuickDeploy[Quick Deploy
Use existing
blueprints
30-60 minutes]
CustomBuild[Custom Solutions
Combine
components
2-4 hours]
NewFeatures[Feature Development
Create new
components
1-2 days]
end

subgraph outcomes [Outcomes]
Production[Production Systems
Reliable edge AI
solutions]
Expertise[Team Expertise
AI-assisted
engineering skills]
Community[Community Impact
Contributions &
improvements]
end

Start --> Beginner
Start --> Intermediate
Start --> Advanced

Beginner --> QuickDeploy

Intermediate --> QuickDeploy
Intermediate --> CustomBuild

Advanced --> CustomBuild
Advanced --> NewFeatures

QuickDeploy --> Production
CustomBuild --> Production
NewFeatures --> Production

NewFeatures --> Community

%% Enhanced color scheme for learning journey
style Start fill:#e1f5fe,stroke:#01579b,stroke-width:3px
style Beginner fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
style Intermediate fill:#fff3e0,stroke:#e65100,stroke-width:2px
style Advanced fill:#e8f5e8,stroke:#2e7d32,stroke-width:2px
style QuickDeploy fill:#e8f5e8,stroke:#2e7d32,stroke-width:2px
style CustomBuild fill:#fff3e0,stroke:#e65100,stroke-width:2px
style NewFeatures fill:#fff3e0,stroke:#e65100,stroke-width:2px
style Production fill:#cffafe,stroke:#059669,stroke-width:2px
style Expertise fill:#cffafe,stroke:#059669,stroke-width:2px
style Community fill:#cffafe,stroke:#059669,stroke-width:2px

�📁 Repository Tour

📦 edge-ai/
├── 📋 blueprints/ # Ready-to-deploy solution templates
├── 📚 docs/ # Complete documentation and guides
├── 🏗️ src/ # Reusable infrastructure components
├── 🧪 tests/ # Testing and validation
├── 🤖 scripts/ # Automation and utilities
└── 🚢 deploy/ # CI/CD pipelines and automation

🏗️ Infrastructure Components ([src/](src/))

Modular, reusable building blocks:

• Cloud services (identity, data, messaging, observability)
• Edge platforms (Kubernetes, Azure IoT Operations)
• Application frameworks (AI inference, telemetry)

📋 Deployment Blueprints ([blueprints/](blueprints/))

Complete solution templates:

• Single-node edge deployments
• Multi-node cluster setups
• Cloud-only configurations
• Minimal proof-of-concept setups

📚 Documentation ([docs/](docs/))

Everything you need to know:

• Getting started guides for different roles
• Architecture decisions and design patterns
• Contributing guidelines and development workflow

🛠️ Quick Setup (Dev Container Recommended)

Prerequisites: Docker, VS Code, GitHub Copilot, and the HVE Core extension (seriously, this repo is optimized for AI-assisted development)

# Clone and open in VS Code
git clone https://github.com/Microsoft/edge-ai.git
cd edge-ai
code .

# When prompted, "Reopen in Container"
# Everything gets installed automatically 🎉

Alternative: [Manual setup instructions](docs/contributing/development-environment.md) (for the brave)

> Note on Telemetry: If you wish to opt-out of sending telemetry data to Microsoft when deploying Azure resources with Terraform, you can set the environment variable ARM_DISABLE_TERRAFORM_PARTNER_ID=true before running any terraform commands.

🎨 What Makes This Project Different

• Actually works in production - empowering real deployments
• Modular design - enabling teams to build custom solutions that meet business needs
• AI-assisted development - optimized for GitHub Copilot to accelerate every engineer's productivity
• Multiple IaC frameworks - Terraform & Bicep
• Comprehensive testing - because empowering reliable edge infrastructure deployments is our mission

🔗 Want to Use Edge-AI Tools in Your Own Repository?

Share our AI instructions, custom agents, and prompts across your projects with a simple dev container setup:

Step 1: Clone both repositories into the same workspace

git clone…