Skip to content
New this week26 prompts for Sora, Veo and Runway video workflows.
Explore video prompts→
AIPrompt123Prompt library

Search AIPrompt123

Search prompts, categories, platforms and repositories

LLM frameworksC#MIT

microsoft/semantic-kernel

Semantic Kernel provides abstractions for models, plugins, memory and planners across .NET, Python and Java. It is aimed at enterprise developers who want LLM capabilities inside existing applications with familiar language ecosystems and dependency injection.

26.0k stars4.1k forks540 contributors280 open issuesUpdated

What it does

  • Wraps model providers and prompt templates as reusable functions.
  • Connects native code as plugins the model can call.
  • Supports agents, memory and process orchestration.

Key features

  • C#, Python and Java SDKs.
  • Enterprise-friendly configuration and DI.
  • Plugin and function-calling abstractions.
  • Azure OpenAI integration.

How to install it

Commands are copied from the project documentation at the time of review. Check the repository for the current version.

.NET
dotnet add package Microsoft.SemanticKernel

Alternatives to consider

semantic-kernel is a strong default for llm frameworks, but the right choice depends on your stack, licence constraints and how much control you need. These are the projects we compare most often.

LangChainAutoGenDSPy

Prompts that pair with it

All prompts →
Verified Knowledge · FAQ

semantic-kernel FAQ

Adoption questions we hear most often about this project.

Related repositories

LLM frameworks · Python

A framework for composing LLM applications from models, tools, retrievers and memory.

118.0k19.2kMIT

LLM frameworks · Python

A framework for programming LLM pipelines and optimising prompts against a metric.

28.0k2.4kMIT

LLM frameworks · TypeScript

A TypeScript toolkit for building AI applications with streaming, tools and UI hooks.

18.0k2.9kApache-2.0