Semantic Kernel

Health v2 · maintenance only

Adoption not part of the score

28582 stars · 4777 forks observed · 2026-09-21

What it is AI-extracted, prompt v1, taxonomy v1, 2026-10-05, confidence 0.97

Semantic Kernel is a model‑agnostic SDK that lets developers integrate large language models and build AI agents quickly. It provides tools for orchestration, plugin integration, memory, planning, and vector‑database connectivity.

Use cases

• Create a chatbot that can call external APIs and maintain conversation context
• Orchestrate a workflow where multiple specialized agents collaborate on a task
• Add LLM‑driven features to an existing .NET, Python, or Java application
• Build a knowledge‑base assistant that retrieves information from a vector store
• Prototype AI‑augmented tools with plug‑in support for custom functions

When to choose

• You need a unified SDK that works across .NET, Python, and Java
• Your project requires multi‑agent orchestration or tool‑calling capabilities
• You want built‑in support for many LLM providers and vector databases

When to avoid

• You are looking for a lightweight, single‑purpose LLM client without orchestration features
• Your stack is limited to languages not supported by the SDK (e.g., Go or Rust)
• You need a production‑grade agent platform that is already marketed as a separate product (Microsoft Agent Framework)

Facets

library · maturity active

llm-inference plugin-system api-framework vector-database middleware artificial-intelligence large-language-models dotnet python jvm windows cross-platform sdk multi-agent orchestration model-agnostic enterprise-ready ai-agents retrieval-augmented-generation linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="microsoft/semantic-kernel")