#1111th of 15 in Agent frameworks and SDKs

semantic-kernel

Microsoft SDK for building LLM agents and plugins in C#, Python and Java

Documentation ↗ Repository on GitHub ↗

Stars: 28.7k
License: MIT
Last commit: Oct 2026
Last release: Oct 2026
Language: C#

Stars, last 29 weeks+1,407

27,251 on 24 Mar 202628,658 on 13 Oct 2026

From GitHub's daily star counts.

Checked 14 Oct 2026 on GitHub.

Overview

Semantic Kernel is a model-agnostic SDK for building agents and multi-agent systems in .NET, Python and Java. It provides chat completion agents, plugins (native functions, prompt templates, OpenAPI, MCP), vector store connectors and a process framework for structured workflows. The README states it has been succeeded by Microsoft Agent Framework, which reached 1.0, and links a migration guide.

Who it is for: Developers building agents in .NET, Python or Java, or migrating to MAF

Strengths

Same agent and plugin model across Python, .NET and Java
Connectors for OpenAI, Azure OpenAI, Hugging Face, NVIDIA, Ollama, LMStudio and ONNX
Plugins can come from native code, prompt templates, OpenAPI specs or MCP
Vector store integrations include Azure AI Search, Elasticsearch and Chroma

Weaknesses

README says it is superseded by Microsoft Agent Framework 1.0
Java support lives in a separate repository with its own build steps
Requires .NET 10.0+ or Python 3.10+, which may exceed existing stacks
Library only: no UI, server or hosted deployment included

What it needs

no GPU
Needs OpenAI or Azure OpenAI API key, or a local model runtime
Models: OpenAI, Azure OpenAI, Hugging Face, NVIDIA NIM, Ollama

Also in Agent frameworks and SDKs

See all 15

Also in Agent frameworks and SDKs
Rank	Project	Score
1	langchainPython framework for building LLM agents and apps from interoperable components147.8k starsMIT	88 out of 100
2	browser-usePython library that lets an LLM agent control a web browser Live demo ↗ (opens in a new tab)117.9k starsMIT	88 out of 100
3	crewaiPython framework for multi-agent workflows with role-based Crews and event-driven Flows59.7k starsMIT	80 out of 100
#4	openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing30k starsMIT	77 out of 100
#5	agnoPython SDK and runtime for building and serving agents behind a REST API42.7k starsApache-2.0	76 out of 100

How to choose

Pick by language first (Python or TypeScript), then by how much the framework hides.
Check how it handles tool errors and retries; that is where agents break in production.
Look for tracing hooks so you can see each step later.

Health

Releases: 39 in the last 12 monthsLast one 8 days ago
Top contributor: 21% of commits63 of 302 in the last 12 months
Security advisories: 2 published ↗ (opens in a new tab)On GitHub, in the last 12 months; 2 critical or high
OpenSSF Scorecard: Not checked

Read from GitHub, deps.dev and OpenSSF on 14 Oct 2026. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

MIT Permissive

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes

Your part: Keep the copyright and license notice in copies you ship.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#11 of 15 in Agent frameworks and SDKs on Archestack, as of 14 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/microsoft/semantic-kernel.svg)](https://archestack.com/best-of-ai/projects/semantic-kernel/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-ai/semantic-kernel/" title="semantic-kernel on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Open-Source AI on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with semantic-kernel filled in.