All directories
AgentEngineeringProduct

Semantic Kernel

microsoft/semantic-kernel

Microsoft’s enterprise-oriented agent/LLM app framework (.NET/Python). GitHub: microsoft/semantic-kernel (~28k stars).

00

GitHub repository

https://github.com/microsoft/semantic-kernel
01

Overview

Semantic Kernel (microsoft/semantic-kernel) is listed in LimeDock Directories as an AI agent resource. Microsoft’s enterprise-oriented agent/LLM app framework (.NET/Python). Group: multi-agent. Community size: ~28k GitHub stars. Repo (copy/paste): https://github.com/microsoft/semantic-kernel This page is a plain-English guide so searches for the GitHub project can land on how teams actually use it.

SaaSOther

Work with LimeDock

Using this skill? LimeDock can wire it into a durable automation you own.

Agents are a starting point. LimeDock turns the workflow into production automation your SaaS team owns — not another prompt library.

We sell owned automations for SaaS teams — live workflows that plug into Slack, CRM, and your internal platform — not just a skill list.

02

Link

https://github.com/microsoft/semantic-kernel
03

Installation guide

Open the GitHub repository, then follow the README for your stack.

Official GitHub repository: https://github.com/microsoft/semantic-kernel GitHub path: microsoft/semantic-kernel

How to open it: 1. Copy: https://github.com/microsoft/semantic-kernel 2. Clone or follow the README for your OS/stack. 3. Start with the smallest example before production use.

04

How to use it

**Simple example** You’re in a Microsoft stack and want a first-party agent framework.

1. Install Semantic Kernel for your language. 2. Create a plugin/tool. 3. Build a thin agent API with enterprise auth.

05

Example prompts

  • Create a Semantic Kernel plugin for our CRM lookup.
  • SK vs AutoGen for enterprise .NET?
  • Prompt + plan patterns in SK.
06

Use cases and examples

  • Evaluate microsoft/semantic-kernel as an AI agent building block
  • Pilot Semantic Kernel on one staging workflow
  • Compare against agents you already pay for
  • Document a team playbook after the pilot
07

Prerequisites

  • .NET or Python
  • Azure/OpenAI access common
08

Tips

  • Enterprise auth/identity early.
  • Keep plugins small and tested.