Microsoft Agent Framework is an open-source SDK and runtime for building, orchestrating, and deploying AI agents and multi-agent workflows in .NET and Python. It is the direct successor to Semantic Kernel and AutoGen, and it shipped version 1.0 on April 3, 2026, with stable APIs and a long-term support commitment. Orchestration frameworks like this one decide how an agent plans and calls tools; they say nothing about whether the data behind those calls is current, certified, or governed, which is the gap Atlan’s context layer for AI closes underneath them.
| Quick facts | |
|---|---|
| Vendor | Microsoft |
| License | MIT (open source) |
| Predecessor frameworks | Semantic Kernel (launched March 2023) and AutoGen |
| Public preview | October 2025 |
| Version 1.0 GA | April 3, 2026 |
| Languages | .NET, Python, and Go (public preview) |
| Model providers | Microsoft Foundry, Azure OpenAI, OpenAI, Anthropic, AWS Bedrock, Ollama |
| Standards support | MCP, A2A, AG-UI, OpenAPI |
What does Microsoft Agent Framework do?
Permalink to “What does Microsoft Agent Framework do?”Microsoft Agent Framework (MAF) simplifies agent development for .NET and Python developers, giving them a clean programming model for agent logic: chat clients, tools, context providers, middleware, and multi-step workflows.
Source: Microsoft Foundry Blog
It brings together three of Microsoft’s existing solutions:
- Semantic Kernel for agent orchestration.
- AutoGen for multi-agent collaboration.
- Microsoft.Extensions.AI for providing the standardized AI building blocks for .NET developers.
Source: Microsoft .NET Blog
Microsoft shipped version 1.0 on April 3, 2026, positioning MAF as its single call to action for developers building AI agents, with deep hooks into Azure, Microsoft Foundry, and broad third-party model support.
9 key capabilities of Microsoft Agent Framework
Permalink to “9 key capabilities of Microsoft Agent Framework”The top capabilities of Microsoft Agent Framework are:
-
Single-agent abstractions: The AIAgent abstraction provides one interface for any model behind Microsoft.Extensions.AI’s IChatClient, with type-safe function tools that let agents call your code.
-
Harness Agent: A Harness Agent is an opinionated, ready-made agent for long, multi-step autonomous work. It wraps a chat client with planning and todo tracking, context compaction, file-based memory, approval-gated tools with a don’t-ask-again option, and pre-wired telemetry in a single call. Where it sits relative to a hand-rolled agent loop is its own decision; see agent harness vs agent framework for the distinction.
-
Multi-agent workflows: Functional and graph-based workflows give explicit control over execution paths, supporting sequential, concurrent, handoff, and group chat patterns, plus research patterns like Magentic-One.
-
Integrations: Connections to model providers, agent services, tools, context providers, middleware, evaluation services, and UI frameworks.
-
Memory management: Agent sessions and threads manage conversation state across turns and long-running tasks.
-
Context providers: The memory mechanism that supplies agents with persistent knowledge between sessions, distinct from retrieval-augmented generation over a document store.
-
Middleware: Interception points for agent actions, where teams wire in access controls, guardrails, and custom policy logic.
-
Observability: Built-in OpenTelemetry integration emits traces, logs, and metrics that follow the OpenTelemetry GenAI Semantic Conventions, giving teams agent observability inside the monitoring stack they already run.
-
Open standards support: Native support for Model Context Protocol (MCP) for tool discovery, Agent2Agent (A2A) for cross-runtime agent coordination, AG-UI for streaming agent output to frontend surfaces, and OpenAPI for wrapping any API as an agent tool.
Which capabilities are still in preview?
Permalink to “Which capabilities are still in preview?”Microsoft Agent Framework 1.0 is stable, but several surfaces are still maturing:
-
Go SDK: The Agent Framework for Go is in public preview, and declarative agents, RAG, CodeAct, and functional workflows are not yet available in Go.
-
CodeAct: The pattern where a model writes one short program to call multiple tools ships in alpha packages, with sandboxed execution in isolated Hyperlight micro VMs.
-
Beta integrations: Foundry hosting, Gemini, Mistral, and several tooling packages have been promoted to beta but sit below the stable tier.
-
AF Labs: Experimental packages cover benchmarking, reinforcement learning, and research initiatives, isolated from the stable installation surface used at production scale.
-
DevUI: The development interface is a sample for local testing, not a production surface.
A framework that ships this much in a year moves fast on orchestration mechanics. None of these preview surfaces touch what an agent is allowed to know or trust, which is the layer that has to come from outside the SDK regardless of which package graduates next.
Who is Microsoft Agent Framework for?
Permalink to “Who is Microsoft Agent Framework for?”MAF targets teams taking agents from prototype to production rather than hobbyist experimentation. Four groups get the most value from it, and each is solving a slightly different problem with the same framework.
-
Enterprise .NET and Python teams: Organizations already invested in Microsoft’s developer stack get one consistent agent model across both languages, instead of maintaining separate mental models for a .NET service layer and a Python data science team building the same kind of agent.
-
Semantic Kernel and AutoGen users: Both communities are directed to MAF as the successor, with migration assistants that analyze existing code and generate step-by-step plans, closing the fragmentation two competing frameworks created. A team that spent a year choosing between the two no longer has to defend that choice going forward.
-
Azure and Foundry shops: Teams deploying on Azure AI Foundry gain observability, durability, and compliance hooks without building hosting infrastructure themselves, which matters more the moment an agent moves from a demo to something a customer or regulator can see.
-
Teams choosing between frameworks: Anyone still weighing MAF against LangGraph, CrewAI, or a cloud-native option like Google ADK or AWS Bedrock Agents benefits from a structured framework comparison rather than a feature-by-feature guess; see how to choose an agentic framework for the enterprise.
None of these four groups picks MAF for the same reason, but they run into the same wall once the agent is live: the framework tells you it executed successfully, not whether the answer it gave was the right one.
Semantic Kernel vs. Microsoft Agent Framework: What has changed?
Permalink to “Semantic Kernel vs. Microsoft Agent Framework: What has changed?”Microsoft describes MAF as Semantic Kernel v2.0, built by the same team. The table below breaks down what moved.
| Semantic Kernel + AutoGen (before) | Microsoft Agent Framework (now) |
|---|---|
| Two separate frameworks: one for enterprise plumbing, one for multi-agent chat | A single SDK carrying Semantic Kernel’s enterprise features (session state, type safety, filters, telemetry, wide model support) plus AutoGen’s agent abstractions |
| Prompt-based planners decide the next step | Graph-based workflows with sequential, concurrent, handoff, and group chat patterns, streamed and checkpointed |
| Kernel-centered construction | Agent and chat-client primitives |
| MCP, A2A, and AG-UI added later, unevenly | MCP, A2A, and AG-UI ship natively from day one |
What is the current status of Semantic Kernel and AutoGen?
Permalink to “What is the current status of Semantic Kernel and AutoGen?”Semantic Kernel v1.x will receive critical bug fixes for at least one year after MAF’s general availability, which extends the window into 2027. AutoGen, meanwhile, has moved to maintenance mode.
New features land only in Agent Framework, so stable production systems can stay put for now, but new projects should start on MAF. For a deeper look at that decision, see Atlan’s guide to Semantic Kernel’s features, status, and successor.
What are the top use cases for Microsoft Agent Framework?
Permalink to “What are the top use cases for Microsoft Agent Framework?”The biggest use cases of Microsoft Agent Framework involve multi-agent orchestration, where the value comes from splitting a task across specialists rather than asking one model to do everything. Examples include:
-
Copilots and assistants grounded in company tools and APIs, from support triage bots that pull order status and policy terms before replying, to internal knowledge assistants that answer a question once instead of routing it to three different Slack channels.
-
Multi-agent business workflows, such as a handoff workflow routing a customer query between a knowledge agent and a billing specialist, or a group chat of research, drafting, and review agents that iterate on a document the way a small team would, with checkpoints instead of a single unreviewed pass.
-
Long-running, human-in-the-loop processes like approval chains, compliance reviews, and document pipelines that pause for people, checkpoint state, and resume days later, without a person having to re-explain the task from scratch each time they return to it.
-
Cross-runtime agent fleets, where A2A messaging lets MAF agents coordinate with agents built on other frameworks, vital for heterogeneous AI estates that span LangChain and homegrown tooling alike, since few enterprises standardize on one agent framework across every team.
Every one of these patterns still assumes the agent already knows what “the customer,” “the invoice,” or “compliant” means inside your business. MAF doesn’t supply that part, and neither does any other orchestration framework; it is a decision the enterprise has to make and maintain separately, on purpose.
Why does Microsoft Agent Framework need an enterprise context layer for AI?
Permalink to “Why does Microsoft Agent Framework need an enterprise context layer for AI?”MAF solves how agents run, but not what they know. Microsoft’s own documentation notes that developers remain responsible for quality, reliability, and trustworthiness of what they build. In enterprise deployments, those properties depend on context the framework never sees.
Three gaps show up consistently once teams move past pilots.
-
No shared business context: MAF retrieves and routes, but it cannot tell an agent what “revenue” means, which of its numerous conflicting definitions is canonical, or which dataset was certified.
-
No context freshness or lineage signals: An agent can execute a workflow perfectly over a stale metric or a broken pipeline, producing confident answers that are wrong in the business sense.
-
No cross-agent consistency: Ten well-built MAF agents across finance, sales, and operations can still give ten different answers, because each assembles its own context in isolation, the same context management problem that shows up whether the agents run on MAF, LangGraph, or CrewAI.
This is where the context layer sits in the enterprise AI stack: below orchestration frameworks and above raw data, supplying the governed definitions, lineage, quality signals, and policy rules every agent should share. Atlan, the Context Layer for AI, fills exactly this gap.
Atlan’s Context Engineering Studio turns existing enterprise knowledge into agent-ready context, packaged as versioned, model-agnostic context repositories, while Agentic Data Stewards keep that context current as the data estate changes.
The connection point is the standard MAF already speaks. Atlan’s MCP server exposes the context layer to any MCP-compatible agent, so a MAF agent can check what an asset means, whether it is trusted, and which policies apply at reasoning time instead of guessing, and that same context travels with the agent if the team later migrates orchestration frameworks.
Building on Microsoft Agent Framework without the context gap
Permalink to “Building on Microsoft Agent Framework without the context gap”Microsoft Agent Framework is a credible choice for agent development on the Microsoft stack. Version 1.0 delivers stable APIs, real multi-agent orchestration, open standards support, and a path from laptop to Foundry-hosted production. Teams on Semantic Kernel or AutoGen have clear migration guides and a support window generous enough to move deliberately, rather than a hard cutoff that forces a rewrite under deadline pressure.
The framework decision, however, is only half the architecture. Agents built on MAF will only be as accurate as the context they can reach, and no orchestration layer, this one included, supplies governed definitions, lineage, or policy rules on its own. That work doesn’t disappear just because the SDK handles planning and tool calls; it moves to whichever team owns the data the agent reads from, whether anyone assigned it to them or not.
Pair the framework with an enterprise context layer for AI like Atlan that keeps enterprise knowledge current, consistent, and queryable over MCP, so the question isn’t whether an agent CAN call a tool, but whether it should trust what that tool just told it.
FAQs about Microsoft Agent Framework
Permalink to “FAQs about Microsoft Agent Framework”1. Is Microsoft Agent Framework still in preview?
Permalink to “1. Is Microsoft Agent Framework still in preview?”No. It entered public preview in October 2025, reached Release Candidate on February 19, 2026, and shipped version 1.0 on April 3, 2026 with stable APIs and a long-term support commitment from Microsoft.
2. How is Microsoft Agent Framework different from Semantic Kernel?
Permalink to “2. How is Microsoft Agent Framework different from Semantic Kernel?”Microsoft Agent Framework is the direct successor to Semantic Kernel, built by the same team. It combines Semantic Kernel’s enterprise features with AutoGen’s agent abstractions and adds graph-based workflows.
3. Does Microsoft Agent Framework support MCP and A2A?
Permalink to “3. Does Microsoft Agent Framework support MCP and A2A?”Yes. Agents can dynamically discover and invoke tools exposed by MCP-compliant servers, and the A2A protocol enables structured coordination with agents running in other frameworks. OpenAPI integration covers conventional APIs.
4. Why should you use Microsoft Agent Framework?
Permalink to “4. Why should you use Microsoft Agent Framework?”Use it when you need a supported path from agent prototype to production. It gives you one programming model across .NET and Python, multi-agent workflows with checkpointing and human-in-the-loop control, and built-in enterprise controls like OpenTelemetry observability and middleware, plus Microsoft’s long-term support commitment and a managed deployment target in Foundry Hosted Agents.
5. Does Microsoft Agent Framework only work with Azure OpenAI?
Permalink to “5. Does Microsoft Agent Framework only work with Azure OpenAI?”No. Through the IChatClient abstraction it supports Microsoft Foundry, Azure OpenAI, OpenAI, Anthropic Claude, AWS Bedrock, Ollama, and other providers, and you can swap providers without rewriting agent code.
6. How is Microsoft Agent Framework different from LangChain or CrewAI?
Permalink to “6. How is Microsoft Agent Framework different from LangChain or CrewAI?”All three are orchestration frameworks, but Agent Framework differentiates on first-class .NET support, a unified .NET and Python programming model, enterprise durability features like checkpointing and sessions, and native deployment into Foundry Agent Service. LangChain and CrewAI remain Python-centric with broader community tooling.
7. Should I migrate from Semantic Kernel to Microsoft Agent Framework?
Permalink to “7. Should I migrate from Semantic Kernel to Microsoft Agent Framework?”For new projects, start on Agent Framework directly. For stable production systems, migration can wait, since Semantic Kernel receives critical fixes through at least April 2027.
Sources
Permalink to “Sources”- Introducing Microsoft Agent Framework, Microsoft Azure Blog
- Introducing Microsoft Agent Framework (Preview): Making AI Agents Simple for Every Developer, Microsoft .NET Blog
- Agent Harness, Microsoft Learn
- Workflows, Microsoft Learn
- Introducing Microsoft Agent Framework: The Open-Source Engine for Agentic AI Apps, Microsoft Foundry Blog
- Semantic Kernel and Microsoft Agent Framework, Microsoft Agent Framework Blog
- Migrate Your Semantic Kernel and AutoGen Projects to Microsoft Agent Framework Release Candidate, Microsoft Agent Framework Blog
- Microsoft Agent Framework Version 1.0, Microsoft Agent Framework Blog
- Microsoft Agent Framework at BUILD 2026, Microsoft Agent Framework Blog
- Microsoft Agent Framework Overview, Microsoft Learn
- Semantic Kernel to Microsoft Agent Framework Migration Guide, Microsoft Learn
- microsoft/agent-framework, GitHub
- Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks, Microsoft Research
