# microsoft/semantic-kernel

Integrate cutting-edge LLM technology quickly and easily into your apps

Repository: https://github.com/microsoft/semantic-kernel
Canonical: https://ross.abutalabs.com/products/semantic-kernel
Homepage: https://aka.ms/semantic-kernel
Language: C#
License: MIT
License Family: permissive
Topics: ai, artificial-intelligence, llm, openai, sdk
Last push: 2026-08-26T16:41:58+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 91
- inputs: {"age_days": 1283, "days_push": 7, "days_rel": 15, "gap_med": 3.0, "n_releases_24m": 145}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 28504, forks 4739 (observed 2026-08-28T04:11:48.347037+00:00)

## What it is
Semantic Kernel is a model-agnostic SDK and orchestration framework from Microsoft for building AI agents and multi-agent systems in .NET, Python, and Java. It provides LLM connectivity, plugins, memory, planning, and vector database integrations, and is now succeeded by Microsoft Agent Framework.

## Use cases
- build ai agents in .net
- orchestrate multi-agent workflows
- integrate llm into my app
- connect openai to my c# application
- build a chatbot with plugins and memory
- add rag with vector database search
- use mcp tools with llm agents

## When to choose
- you need an enterprise-grade agent framework in .NET, Python, or Java
- you want multi-provider LLM support with plugins, memory, and planning
- you need multi-agent orchestration with vector database integrations

## When to avoid
- you are starting a brand-new project - Microsoft recommends its successor, Microsoft Agent Framework
- you need a lightweight single-purpose LLM client rather than a full orchestration framework

## Facets
- artifact type: framework
- maturity: maintenance
- function: agent-framework, llm-inference, rag, mcp, chatbot, sdk
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: cross-platform, windows, python, dotnet, jvm
- tags: llm-orchestration, multi-agent, openai, azure-openai, plugins, semantic-kernel, microsoft, ai-agents, retrieval-augmented-generation, macos, linux

## Member repositories
- microsoft/semantic-kernel (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:48.347037+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:54:22.600839+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/semantic-kernel (fetched 2026-08-28T04:11:48.347037+00:00, sha 361d6a8a39c8)
- Data as of 2026-08-30T08:39:29.467469+00:00.