Semantic Kernel

Profile

Overview

The bottom line — what this framework is, who it's for, and when to walk away.

Bottom Line Up Front

Semantic Kernel is a lightweight, open-source development kit for building AI agents and integrating AI models into C#, Python, or Java codebases. It acts as middleware, translating AI model requests into calls to existing APIs and passing results back. Designed for enterprise use, it emphasizes flexibility, modularity, and future-proofing.

Best For

Building AI agents and integrating models to automate enterprise business processes.

Avoid If

no data

Strengths

  • +Lightweight and open-source development kit.
  • +Facilitates rapid integration of AI models and agent building.
  • +Acts as efficient middleware for enterprise-grade solutions.
  • +Flexible, modular, and observable architecture.
  • +Includes security-enhancing capabilities like telemetry, hooks, and filters.
  • +Offers stable V1.0+ support with commitment to non-breaking changes.
  • +Allows easy swapping of AI models without code rewrites.
  • +Integrates prompts with existing APIs using OpenAPI specifications.
  • +Supports expanding existing APIs to additional modalities like voice and video.

Weaknesses

    Project Health

    Is this project alive, well-maintained, and safe to bet on long-term?

    Stars

    28,536

    Open Issues

    284

    Last Commit

    2d ago

    Commit Frequency

    6x/week

    Bus Factor Score

    9 / 10

    Maintainers

    100

    Latest Version

    dotnet-1.80.1

    Total Releases

    99

    Repo Age

    3y 6mo

    Forks

    4,757

    Monthly Downloads

    2.5M

    last 30 days

    Versions Published

    138

    Known Vulnerabilities

    2Highest: Critical

    Dependent Repos

    205

    public repos using this

    Fit

    Does it support the workflows, patterns, and capabilities your team actually needs?

    State Management

    no data

    Perspective

    Your expertise shapes what we build next.

    We build for engineers who make real architectural decisions. If something is missing, inaccurate, or could be more useful — we want to hear it.

    Last updated: 7 September 2026

    ·

    FrameworkPicker — The technical decision engine for the agentic AI era.