Microsoft Agent Framework
Agent and workflow framework from Microsoft
Microsoft Agent Framework is Microsoft's open-source framework for agents and multi-agent workflows in Python and .NET. Version 1.0 shipped in April 2026 and is the unified successor of Semantic Kernel and AutoGen. A graph-based workflow engine supports branching, parallelism, checkpoints and human approvals; ready-made patterns exist for sequential, concurrent, handoff, group chat and Magentic-One orchestration. MCP and A2A are supported.
Good fit if
Focus: Developer teams in the Microsoft and Azure ecosystem and teams migrating from Semantic Kernel or AutoGen
- your project is about Enterprise workflows with multiple agents, Long-running processes with approvals or Migration from Semantic Kernel and AutoGen
- someone on your team writes code
Probably not if
- nobody on your team writes code (1/5 for use without developers)
Key figures
- Usable without developers
- 1/5
- Scalability
- 5/5
- Integrations
- 4/5
- Versioning
- 3/5
- Observability
- 4/5
Editorial rating on a scale from 1 to 5. Methodology
Fact sheet
- Category
- Developer
- Type
- Agent and workflow framework from Microsoft
- Licence
- Open Source (MIT)
- Pricing
- Open SourceFramework free (MIT). Costs arise from model APIs and, where used, Azure services such as Microsoft Foundry.
- Deployment
- Self-Hosted, Azure, Cloud, Any
- Models
- Microsoft Foundry, Azure OpenAI, OpenAI, Anthropic, Amazon Bedrock, Google Gemini, Ollama
- RAG
- Yes
- Multi-Agent
- Yes
- SSO, roles (RBAC)
- SSO no, RBAC no
- Latest version
- 1.21.0 (Python)
- GitHub stars
- 14,000
Key features
- Graph-based workflows with checkpoints
- Orchestration patterns (sequential, concurrent, handoff, group chat, Magentic-One)
- MCP and A2A
- Python and .NET
Typical use cases
- Enterprise workflows with multiple agents
- Long-running processes with approvals
- Migration from Semantic Kernel and AutoGen
- Agents in Microsoft Foundry
Implementation
Get Microsoft Agent Framework implemented
Free for you. Partners only pay for requests they accept.
Alternatives
Similar systems
Similar in category, features or use cases.
- DeveloperGoogle Agent Development Kit (ADK)The Agent Development Kit (ADK) is an open-source framework from Google for building, evaluating and deploying agents in code. It is available for Python, TypeScript, Go, Java and Kotlin and offers workflow agents for sequential, parallel and loop flows, plus graph-based workflows since version 2.0. ADK is optimized for Gemini but also works with Claude, OpenAI models and local models; deployment targets include Agent Runtime, Cloud Run and GKE.View profile
- DeveloperCrewAICrewAI is a Python framework for teams of agents with defined roles, goals and tasks. Crews work through tasks sequentially or hierarchically, while Flows control event-driven, stateful processes. The framework is MIT licensed; for deployment, monitoring and management CrewAI offers the commercial platform CrewAI AMP.View profile
- DeveloperClaude Agent SDKThe Claude Agent SDK exposes the agent loop, tools and context management of Claude Code as a library for Python and TypeScript. Agents can read and edit files, run commands, search the web and spawn subagents for subtasks; hooks, permissions, sessions and MCP servers are built in. It was formerly called the Claude Code SDK. Use is governed by Anthropic's Commercial Terms, while the Python package itself is MIT licensed.View profile
- DeveloperInngest AIInngest is an event-driven durable execution platform: functions consist of steps that are retried automatically on failure and resumed after interruptions. For AI applications Inngest offers AgentKit and steps for LLM calls, so multi-step agents run reliably without operating your own queues. The server and CLI are licensed under the SSPL with delayed publication under Apache 2.0, the SDKs under Apache 2.0.View profile