# microsoft/ai-dev-gallery

An open-source project for Windows developers to learn how to add AI with local models and APIs to Windows apps.

Repository: https://github.com/microsoft/ai-dev-gallery
Canonical: https://ross.abutalabs.com/products/ai-dev-gallery
Language: C#
License: MIT
License Family: permissive
Topics: directml, dotnet, genai, npu, onnx, phi3, qnn, stable-diffusion, windows, winui3, ai, onnxruntime, onnxruntime-genai, visual-studio, winappsdk, developer-tools, mistral, whisper, wpf, csharp
Last push: 2026-08-20T04:21:58+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 35, longevity 47
- inputs: {"age_days": 665, "days_push": 13, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1497, forks 221 (observed 2026-08-28T04:04:53.925297+00:00)

## What it is
AI Dev Gallery is a Windows application from Microsoft that lets developers explore over 25 interactive samples powered by local AI models running via ONNX Runtime, DirectML, and NPUs. It allows browsing and downloading models from Hugging Face and GitHub, viewing C# source code, and exporting standalone Visual Studio projects with one click.

## Use cases
- add local AI features to my Windows app
- run Phi-3 or Mistral locally on Windows with C#
- learn how to use ONNX Runtime Generative AI in WinUI apps
- try Stable Diffusion locally on Windows with DirectML
- run Whisper speech recognition offline on Windows
- export a working Visual Studio project with AI model integration
- test AI models on NPU on Copilot+ PCs

## When to choose
- you are a Windows developer building WinUI3/WPF apps with C#
- you want to run AI models locally without cloud APIs
- you want copy-paste sample code and exportable projects for AI integration
- you target NPUs or GPUs on Windows 10/11

## When to avoid
- you develop for macOS, Linux, or mobile platforms
- you need cloud-based AI APIs rather than local models
- your machine lacks the recommended 16GB RAM and GPU VRAM
- you need a production-ready AI library rather than a learning gallery

## Facets
- artifact type: application
- maturity: active
- function: machine-learning, llm-inference, image-processing, speech-recognition, developer-tools, sdk
- domain: artificial-intelligence, large-language-models, developer-tools, windows, machine-learning
- platform: windows, dotnet, cpp
- tags: winui3, onnx, onnxruntime, directml, npu, local-models, hugging-face, sample-gallery, csharp, windows-app-sdk, stable-diffusion, whisper, phi3

## Member repositories
- microsoft/ai-dev-gallery (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:53.925297+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:33:09.387637+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/ai-dev-gallery (fetched 2026-08-28T04:04:53.925297+00:00, sha 61adc5f328dc)
- Data as of 2026-08-30T08:39:29.467469+00:00.