Build planner-driven agent workflows with Microsoft Semantic Ker

Build planner-driven agent workflows with Microsoft Semantic Kernel

Compose prompts, plugins, memory, planners, and connectors into repeatable Python, .NET, or Java agent workflows with Microsoft Semantic Kernel.

Prerequisites

Microsoft Semantic Kernel; Python 3.10+, .NET 10.0+, or Java 17+ depending on runtime; LLM provider credentials as required by the chosen connector

Installation

Use the upstream install or setup path that matches your environment:

• pip install semantic-kernel

Requirements and caveats from upstream:

• 
• Python: 3.10+

• Python

Basic usage or getting-started notes:

• Local Deployment: Run with Ollama, LMStudio, or ONNX

• First, set the environment variable for your AI Services:

• Azure OpenAI:

• Source: https://github.com/microsoft/semantic-kernel

• Extracted from upstream docs: https://raw.githubusercontent.com/microsoft/semantic-kernel/HEAD/README.md

Documentation

• https://learn.microsoft.com/semantic-kernel/

Source

• Agent Skill Exchange