# edge-ai
**Repository Path**: mirrors_microsoft/edge-ai
## Basic Information
- **Project Name**: edge-ai
- **Description**: Edge AI Accelerator
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-09-09
- **Last Updated**: 2025-09-11
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
# Edge AI Accelerator
[](https://dev.azure.com/ai-at-the-edge-flagship-accelerator/edge-ai/_build/latest?definitionId=12&branchName=main)
[](LICENSE.md)
[](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://dev.azure.com/ai-at-the-edge-flagship-accelerator/_git/edge-ai)
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.
## π― 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
## π Get Started (Pick Your Adventure)
### β [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**
### β [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**
### β [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**
## πΊοΈ Your Learning and Deployment Journey
```mermaid
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 learning [PraxisWorx Learning Path]
Foundation[Foundation Katas
AI-Assisted Engineering
15-45 min each]
Skills[Core Skills
Task Planning
ADR Creation
Prompt Engineering]
Application[Applied Practice
Edge Deployment Labs
2-50+ hours]
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 --> Foundation
Foundation --> Skills
Skills --> Application
Application --> QuickDeploy
Intermediate --> QuickDeploy
Intermediate --> CustomBuild
Advanced --> CustomBuild
Advanced --> NewFeatures
%% Learning enhances all paths
Foundation -.-> QuickDeploy
Skills -.-> CustomBuild
Application -.-> NewFeatures
QuickDeploy --> Production
CustomBuild --> Production
NewFeatures --> Production
Application --> Expertise
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 Foundation fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
style Skills fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
style Application fill:#f3e5f5,stroke:#7b1fa2,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
```
## οΏ½π Repository Tour
```text
π¦ edge-ai/
βββ π blueprints/ # Ready-to-deploy solution templates
βββ π docs/ # Complete documentation and guides
βββ ποΈ src/ # Reusable infrastructure components
βββ π§ͺ tests/ # Testing and validation
βββ π€ scripts/ # Automation and utilities
βββ π’ deploy/ # CI/CD pipelines and automation
```
### ποΈ 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)
### π Deployment Blueprints ([`blueprints/`](blueprints/))
Complete solution templates:
- **Single-node edge** deployments
- **Multi-node cluster** setups
- **Cloud-only** configurations
- **Minimal** proof-of-concept setups
### π Documentation ([`docs/`](docs/))
Everything you need to know:
- **Getting started** guides for different roles
- **Architecture** decisions and design patterns
- **Contributing** guidelines and development workflow
## π οΈ Quick Setup (Dev Container Recommended)
**Prerequisites:** Docker, VS Code, and GitHub Copilot (seriously, this repo is optimized for AI-assisted development)
```bash
# 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 π
```
**Alternative:** [Manual setup instructions](docs/getting-started/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.
## π¨ 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
## π PraxisWorx Learning Platform
**Empower your team to achieve proficiency in AI-assisted, hyper-velocity engineering** through hands-on training labs and focused practice exercises (Katas).
PraxisWorx (*where AI empowers every engineer to achieve more*) provides challenge-based learning for edge-to-cloud AI systems:
- **π₯ [Katas](praxisworx/katas/)** - Focused 15-45 minute practice exercises
- **π§ͺ [Training Labs](praxisworx/training-labs/)** - Comprehensive 2-8 hour hands-on experiences *(Coming Soon)*
- **π€ [AI Coaching](praxisworx/)** - Built-in coaching prompts for discovery-based learning
### π Start Your AI-Assisted Learning Path
**One-click training mode** - launch documentation with automatic navigation to PraxisWorx learning platform:
```bash
npm run docs:training
```
This command automatically:
- β
Builds the documentation
- β
Starts the local server
- β
Opens your browser directly to the PraxisWorx homepage
- β
Provides immediate access to all learning paths and resources
## π€ Contributing
We β€οΈ contributions! Whether you're fixing typos or adding new components:
1. Read our [Contributing Guide](docs/contributing/)
2. Check out [open issues](https://github.com/Microsoft/edge-ai/issues)
3. Join the [discussion](https://github.com/Microsoft/edge-ai/discussions)
## π Legal
This project is licensed under the [MIT License](./LICENSE).
**Security:** See [SECURITY.md](./SECURITY.md) for security policy and reporting vulnerabilities.
## Trademark Notice
> This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft
> trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in
> modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or
> logos are subject to those third-party's policies.
*π€ Crafted with precision by β¨Copilot following brilliant human instruction,
then carefully refined by our team of discerning human reviewers.*