semantic-kernel
Build model-agnostic agent workflows across Python, .NET, and Java
- Stars
- 28,292
- Forks
- 4,672
- Updated
- Updated Jul 10, 2026
Build model-agnostic agent workflows across Python, .NET, and Java
Semantic Kernel is a model-agnostic SDK for building, orchestrating, and deploying AI agents and multi-agent systems across Python, .NET, and Java. It supports multiple model providers, plugins, structured workflows, and vector-database integrations. The project now identifies Microsoft Agent Framework as its successor and provides a migration guide, which is relevant when maintaining or starting an application.
Resource types
Use cases
Capabilities
Connect AI agents to authenticated apps, user accounts, and executable tools.
Build Python agent workflows with tools, handoffs, guardrails, sessions, and tracing.
Audience
Public GitHub facts last synced Jul 10, 2026.
Calls Claude Agent from Python with async queries, in-process tools, hooks, and interactive sessions.
Build controllable AI agents in Python or TypeScript