Microsoft's Agent Framework Merges AutoGen and Semantic Kernel Into One Open-Source SDK
Microsoft Agent Framework 1.0 hits GA, unifying AutoGen and Semantic Kernel into a single open-source SDK for production-grade AI agents in Python and .NET
PRO- GA shipped: Microsoft Agent Framework 1.0 is generally available, unifying AutoGen and Semantic Kernel into one open-source SDK.
- Dual-language: Full Python and .NET support with consistent APIs, installable via
pip install agent-frameworkordotnet add package Microsoft.Agents.AI. - Five orchestration patterns stable: Sequential, concurrent, handoff, group chat, and Magentic-One, all with checkpointing and human-in-the-loop support.
- AutoGen and Semantic Kernel enter maintenance mode: Security patches only; all new development moves to MAF.
- MCP and A2A built-in: First-class support for Model Context Protocol and Agent-to-Agent cross-runtime communication.
- Migration paths available: Semantic Kernel migration is phased and smooth; AutoGen migration requires more significant rework.
For years, Microsoft developers building AI agents faced an awkward question: AutoGen or Semantic Kernel? The two frameworks grew up in different parts of Microsoft, served different masters, and never quite converged. AutoGen was research-grade: flexible and great for experimental multi-agent workflows, but weak on production concerns like state management and telemetry. Semantic Kernel was the enterprise play: type-safe and telemetry-rich, but with orchestration rigid enough to frustrate anyone who needed agents to reason dynamically. That split is now officially over.
One framework to replace them both
When Microsoft introduced the Agent Framework, they set out to unify the enterprise-ready foundations of Semantic Kernel with the innovative orchestrations of AutoGen into a single, open-source SDK. MAF reached 1.0 GA on April 2, 2026, bringing the convergence of AutoGen and Semantic Kernel into a single, supported platform. The repository has already crossed 10,000 stars and nearly 2,000 forks.
It combines AutoGen's simple abstractions for single- and multi-agent patterns with Semantic Kernel's enterprise-grade features such as session-based state management, type safety, filters, and telemetry. Beyond merging the two, Agent Framework introduces workflows that give developers explicit control over multi-agent execution paths, plus a robust state management system for long-running and human-in-the-loop scenarios.
What's actually in the box
The framework provides a unified programming model across .NET and Python with: simple agent creation, function tools with type-safe definitions, graph-based workflows supporting sequential, concurrent, handoff, and group chat patterns with streaming, checkpointing, and human-in-the-loop support, multi-provider support across Microsoft Foundry, Azure OpenAI, OpenAI, GitHub Copilot, Anthropic Claude, AWS Bedrock, Ollama, and more, and interoperability via A2A, AG-UI, and MCP standards.
This story is for Pro members
You've reached the end of the free preview. Upgrade to AlphaSignal Pro to read the full article - and everything else behind the paywall.
Comments
