OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Semantic Kernel

An open-source C# SDK for integrating large language model technology into applications and developing assistants or multi-agent systems.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Semantic Kernel — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an application needs embedded LLM capabilities, assistant behavior, or agent orchestration. For newer multi-agent and cross-runtime work, the supplied repository evidence identifies Microsoft Agent Framework as the successor.

Who it is for

  • Developers building LLM-powered applications
  • Teams creating assistants or orchestrated agent systems
  • C# developers needing an SDK-based integration approach

Documented uses

  • Integrate LLM technology into a C# application
  • Build a single assistant
  • Orchestrate specialized agents
  • Support multiple model providers
  • Develop an interoperable multi-runtime agent system
Before you choose

Requirements & limits

The repository is public, active, and MIT-licensed.

  • C# is the identified primary language.
  • The project is an SDK rather than a standalone end-user assistant.
  • Microsoft Agent Framework is identified as the successor for multi-agent orchestration, multi-provider support, and cross-runtime interoperability.
  • The evidence confirms cloud, self-hosted, and server deployment contexts.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Semantic Kernel and create a basic Python assistant

Set up Semantic Kernel for Python and create an assistant that responds to a prompt.

Before you start

  • Python 3.10 or newer
  • Windows, macOS, or Linux
  • An Azure OpenAI API key, or an OpenAI API key

Steps

  1. Set either AZURE_OPENAI_API_KEY or OPENAI_API_KEY as an environment variable.

  2. Install the Python package with the command below.

    Documented command
    pip install semantic-kernel

  3. Create a ChatCompletionAgent using AzureChatCompletion, give it instructions, and call get_response with a user message.

  4. Print the response content.

Expected outcome

A Python assistant is configured and the documented example returns a haiku response.

Guide limitations

  • The documented Python example uses AzureChatCompletion even though the installation section also lists direct OpenAI support.
  • The repository identifies Microsoft Agent Framework as Semantic Kernel's successor and links to a migration guide, but does not provide migration steps here.
Documentation 1 ↗Documentation 2 ↗
Source-based practical guide

Install Semantic Kernel and create a basic .NET assistant

Set up the .NET packages and create an assistant that responds to a prompt.

Before you start

  • .NET 10.0 or newer
  • Windows, macOS, or Linux
  • Azure OpenAI deployment, endpoint, and API key environment variables

Steps

  1. Add the Microsoft.SemanticKernel and Microsoft.SemanticKernel.Agents.Core packages.

  2. Configure the kernel with AddAzureOpenAIChatCompletion, using the Azure OpenAI deployment, endpoint, and API key environment variables.

  3. Build the kernel and create a ChatCompletionAgent with a name, instructions, and the kernel.

  4. Invoke the agent with a prompt and write each response message to the console.

Expected outcome

A .NET assistant is configured and the documented example prints a haiku response.

Guide limitations

  • The documented .NET quickstart uses Azure OpenAI; no direct OpenAI .NET example is provided.
  • The repository identifies Microsoft Agent Framework as Semantic Kernel's successor and links to a migration guide, but does not provide migration steps here.
Documentation 1 ↗Documentation 2 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Semantic KernelIntegrate LLM technology into a C# applicationCloud, Self-hosted, ServerThe repository is public, active, and MIT-licensed. The supplied evidence does not specify pricing or account requirements.
AgeniteDefine typed tools with JSON Schema validation and error handling.CLI
VeldraCreate an agent with a policy, tools, skills, knowledge base and reasoning method.Self-hostedThe documented deployment is self-hosted and uses a sign-in gate after a first-run administrator account is created.
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
microsoft/semantic-kernel · Official homepage title · retained in its source language
How we review sourcesSuggest a correction