dotnet

ai-samples: Build AI Features in .NET Applications

.NET AI Samples is a collection of C# examples for adding AI capabilities to .NET applications, centered on Microsoft.Extensions.AI and its provider integrations. It is archived, so use it as a reference and follow the current .NET AI documentation for maintained guidance.

View on GitHub Compare
Stars
878
Forks
184
Stars, last 30 days
-2
Last commit
4 months ago
Contributors
19

Our take

Archivedarchived by its owners on GitHub, read-only

Health score

32/100

How it is scored
Activity
19
Community
69
Issues
21
Pull requests
20

-2 stars in the last 30 days

This is a useful, broad .NET AI reference, but its archived, read-only status makes it unsuitable as a maintained foundation for a new application.

Good fit if

  • You want to learn from C# examples built around Microsoft.Extensions.AI and its integrations.
  • You are exploring the included chat, summary, function-calling, or evaluation scenarios.
  • You can treat the code as a reference and verify it against current .NET AI guidance.

Look elsewhere if

  • You need an actively maintained repository or ongoing issue and pull-request handling.
  • You need a current implementation baseline rather than archived examples.
  • You need a single documented setup path: the repository contains multiple sample areas rather than one shared install workflow.
All health signals
Last commit2026-06-15 (4 months ago)
Commits, last 90 days0
Releases, last 12 months0
Contributors19 (top contributor: 23% of commits)
Issues closed, last 90 days0
Pull requests merged, last 90 days0
Project age2 years

Checked on 2026-10-15 with the GitHub API.

Project history

Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.

Selected snapshot

Stars

876

Forks

184

Change since Nov 16, 2026: 0 stars·0 forks

Overview

AI Samples for .NET is a collection of C# examples built on .NET and Microsoft.Extensions.AI, Microsoft's shared set of abstractions for connecting .NET applications to AI services. It helps developers explore ways to add language-model and embedding capabilities without tying every example to a single provider.

The repository also includes quickstarts and application examples, including samples using Azure OpenAI, OpenAI, Semantic Kernel, and other listed integrations. It is archived and read-only, so it is best treated as a learning resource rather than a maintained starting point for new projects.

Key Features

  • Examples of Microsoft.Extensions.AI abstraction implementations and provider integrations.
  • Samples for Azure OpenAI, OpenAI, Azure AI Inference, and Ollama.
  • Microsoft.Extensions.AI.Evaluation API usage examples for assessing LLM response quality.
  • OpenAI and Azure OpenAI quickstarts covering text summaries, chat apps, and function calling.
  • A customer-support chat sample.
  • Build 2024 tutorial projects demonstrating Semantic Kernel chat history, function calling, logging, plugins, and dependency injection.

Use Cases

  • .NET developers comparing provider integrations while learning the Microsoft.Extensions.AI abstractions.
  • Developers building a first AI-powered .NET chat or summarization feature who want a sample to study.
  • Teams exploring function calling or Semantic Kernel patterns through the included tutorial projects.
  • Developers investigating how to evaluate the quality of LLM responses in a .NET application.

What you need

Detected in the repository

  • C# (main language on GitHub)
  • Automated checks on GitHub Actions

License in plain words

MITpermissive

  • Commercial use: yes
  • Modify and redistribute: yes
  • You must keep: the copyright and license notice
  • Share your changes: no

A summary, not legal advice: the LICENSE file is what applies.

Getting Started

Browse the repository README and follow the link for the sample that matches your scenario. The repository points readers to the current .NET AI documentation for maintained guidance.

Considerations

The repository is archived and read-only, with no recent commits or releases recorded in the health data. Although it has contributions from multiple people, there is no ongoing maintenance or recent issue and pull-request activity to rely on. The README does not provide a single runtime or setup specification for the collection, so check the instructions for each sample and confirm its dependencies before using it. The project is licensed under MIT; review that license when incorporating code into another project.

Found this useful?

Share it with someone who would like ai-samples.