Skip to main content
ToolAutomationopen-sourceactive9+
9/10Top-tier
Active

Free (open source)

Best plan

Free (open source)

Risk: Active 1

Try Microsoft Agent Framework

Editorial · no paid placements

Should you use it?

Microsoft Agent Framework 1.0 shipped April 2026 as the successor to both Semantic Kernel and AutoGen. Its current release stream is python-1.9.0 (June 18) and dotnet-1.11.0 (June 23). It is open source, free, and aligned with Microsoft Foundry, Azure OpenAI, OpenAI, Anthropic, Ollama, GitHub Copilot, and Copilot Studio. As of June 26, Work IQ APIs are generally available with Copilot Credits billing. Pick it for Microsoft-aligned enterprise agent deployments, but pin versions and verify Work IQ access, admin controls, and cost before production architecture.

  • Buy ifAzure and Microsoft Foundry enterprises building AI agents
  • PickFree (open source)
  • Skip ifTypeScript-first teams (pick Mastra)

Plan guidance

What to buy

Best planFree (open source)

Watch: Active 1

Price rangeFree (open source)

Use the official pricing page before purchase because AI plans change often.

Upgrade only ifNot for typescript-first teams (pick mastra)

Active 1

Fit

Use it for this, skip it for that

Best for

  • Azure and Microsoft Foundry enterprises building AI agents
  • Teams currently on Semantic Kernel or AutoGen
  • .NET and Python shops wanting one unified framework
  • Production deployments needing Microsoft-backed SLAs

Avoid if

  • TypeScript-first teams (pick Mastra)
  • Solo devs without Azure infrastructure
  • Simple agent use cases (framework is heavy)
Watch out
Active 1.x framework cadence plus fast-moving Work IQ/Foundry/Copilot Credit surfaces. As of June 26, GitHub releases still show python-1.9.0 from June 18 and dotnet-1.11.0 from June 23; Work IQ APIs are generally available and billed through Copilot Credits. Verify GA access, admin billing controls, provider support, non-Azure data boundaries, and exact .NET/Python package versions before architecture decisions.

Alternatives

Best swaps

Langfuse

Open-source LLM engineering platform for observability, prompt management, evals, datasets, and OpenTelemetry tracing. ClickHous

$0 free / $29 Core / $199 Pro / $2,499 Enterprise · 8.8/10LangGraph

LangChain's low-level orchestration runtime for long-running, stateful AI agents. MIT-licensed Python and JavaScript libraries;

$0 library / $39 Plus / LCU/LSU usage meters · 8.8/10LinkedIn Recruiter

LinkedIn's recruiting platform with Hiring Assistant, AI-assisted sourcing, candidate messaging, applicant review, projects, rep

Contact sales; Hiring Assistant is an add-on · 8.8/10
Build comparison
Proof and score mathVerified Jun 26

Proof

Why this recommendation is trusted

EvidenceMicrosoft Build 2026 Work IQ and agent stack
Source
Registered source
Freshness
Review due
Confidence
Low confidence
Verified
Review
Volatility
Drifts

Stale source microsoft-work-iq-partner-center.

Editorial score

Unweighted average of 4 axes · confidence high

  • Utility9/10

    How much real work it can do for a competent operator, end to end.

  • Value10/10

    What you get for the dollar relative to the closest alternative.

  • Moat8/10

    How hard it would be for a competitor to replicate the underlying advantage.

  • Longevity9/10

    How likely the product is to still be best-in-class 24 months out.

Verified facts

  1. Best ForMicrosoft's open-source agentic AI engine, merging Semantic Kernel and AutoGen. Free, production-oriented, and tightly integrated with Microsoft Foundry; June 2026 Build updates make Work IQ, Foundry IQ, Microsoft 365 tenant context, Agent 365, and Copilot Credits the adjacent enterprise-agent layer. Best for .NET and Python agentic workflows, multi-agent orchestration, and Microsoft-aligned business-process automation.
    highDrifts2026-06-26Microsoft Build 2026 Work IQ and agent stack
  2. Pricing AnchorFree open source under the MIT license on GitHub; cost lives in LLM inference, Microsoft Foundry/Azure infrastructure, Work IQ API consumption through Copilot Credits, and any third-party models or tools used by the deployed agent
    highStable2026-06-26Microsoft Agent Framework GitHub
  3. Watch Out ForActive 1.x framework cadence plus fast-moving Work IQ/Foundry/Copilot Credit surfaces. As of June 26, GitHub releases still show python-1.9.0 from June 18 and dotnet-1.11.0 from June 23; Work IQ APIs are generally available and billed through Copilot Credits. Verify GA access, admin billing controls, provider support, non-Azure data boundaries, and exact .NET/Python package versions before architecture decisions.
    highDrifts2026-06-26Microsoft Partner Center Work IQ API and consumptive pricing update
Open SourceRecent activity
microsoft/agent-framework
11.3kstars
1,909forks
Pythonlanguage
MITlicense
1 month agolast commit
View on GitHub
Full review notesLong-form details, FAQ, and source history

Microsoft’s consolidated answer to the agent-framework fragmentation of 2024-2025. It merges the orchestration strengths of Semantic Kernel with the multi-agent patterns of AutoGen into one framework. By the June 26 check, the release stream showed python-1.9.0 and dotnet-1.11.0. The June 2026 Build and Work IQ GA updates also make the surrounding Microsoft stack clearer: Agent Framework for code, Microsoft Foundry for model/app development, Work IQ APIs for Microsoft 365 work context, and Agent 365/Defender/Purview-style controls for governed agents.

The current docs lean on Microsoft Foundry (renamed from Azure AI Foundry) as the reference platform, but the framework speaks directly to Microsoft Foundry, Anthropic, Azure OpenAI, OpenAI, Ollama, and a growing list of providers.

Recent developments
  • June 26, 2026 check: GitHub releases show python-1.9.0 from June 18 and dotnet-1.11.0 from June 23. Recent release notes include AgentLoopMiddleware, harness tool approval, shell-tool integration, telemetry improvements, and breaking MCP sampling guardrails.
  • June 16, 2026 check: Work IQ APIs are generally available. Microsoft’s licensing notice says billing uses Copilot Credits with no separate Work IQ API subscription, SKU, or per-user license, while Partner Center tells administrators to configure consumptive billing, access policies, limits, and alerts before custom or third-party Work IQ agents use Microsoft 365 data.
  • June 23, 2026: dotnet-1.11.0 is the checked .NET release line. Recent releases include multiple breaking or experimental changes, so pin tested package versions before production rollout.
  • June 2, 2026: Microsoft Build 2026 put Work IQ APIs, Foundry IQ, Fabric IQ, Copilot Credits, Agent 365, and new Microsoft AI models around the enterprise-agent stack. Agent Framework remains the open-source code layer, but Microsoft-aligned buyers should evaluate it with Work IQ, Foundry, and governance controls rather than in isolation.
  • May 8, 2026: dotnet-1.5.0 was the May baseline release. It has now been superseded by the June release stream.
  • May 1, 2026: Microsoft put a legal AI agent directly inside Word through its Frontier program. That is not the open-source Agent Framework itself, but it shows the same Microsoft pattern: domain-specific agents wrapped in structured workflows, approvals, and familiar enterprise surfaces.

System Verdict

Pick Microsoft Agent Framework if you’re already on Microsoft Foundry or migrating from Semantic Kernel or AutoGen. The framework is open source, production-oriented, and deeply integrated with Microsoft Foundry, Azure OpenAI, GitHub Copilot, and Copilot Studio. If your organization is a Microsoft shop, this is the default agent framework to evaluate first.

Skip it if your stack is not Microsoft-aligned. TypeScript teams should use Mastra. Python-first teams not on Azure should look at LangGraph or CrewAI. The framework is technically independent of Azure but meaningfully better inside that ecosystem.

AutoGen is now maintenance-only. If you’re on AutoGen, Microsoft recommends migration to Agent Framework. AG2 (the community-forked AutoGen continuation) is the other path.

Key Facts
Current versionpython-1.9.0 (June 18, 2026) and dotnet-1.11.0 (June 23, 2026) on the public GitHub releases page
LicenseMIT open source
Languages.NET (C#) + Python
Framework costFree
Metered adjacent costsLLM inference consumption through Copilot Credits, and third-party tools/models
Microsoft integrationMicrosoft Foundry, Azure OpenAI Service, GitHub Copilot SDK, Copilot Studio, Work IQ, Agent 365
Predecessors mergedSemantic Kernel (orchestration) + AutoGen (multi-agent)
AutoGen statusMaintenance mode only. New projects should not start there.
Native provider supportMicrosoft Foundry, Azure OpenAI, OpenAI, Anthropic, Ollama, Foundry Local, GitHub Copilot, Copilot Studio, and custom providers
Core primitivesAgents (LLMs + tools + MCP servers) and Workflows (graph-based, type-safe routing, checkpointing, human-in-the-loop)

When to pick Microsoft Agent Framework

  • Azure or Microsoft Foundry enterprises. Deep integration with Microsoft Foundry, Azure OpenAI, Copilot Studio, Entra ID, Azure Monitor. Migration path from existing Copilot Studio agents is the cleanest.
  • Existing Semantic Kernel or AutoGen users. Migration guides shipped with 1.0 and remain the official Microsoft path. Expect refactoring rather than a drop-in swap.
  • .NET / C# shops. The best .NET-native agent framework available in 2026. The June 23 dotnet-1.11.0 release reinforces that .NET is a first-class target, not an afterthought.
  • Graph-based multi-agent orchestration. Workflows give explicit control over execution order, type-safe routing, checkpointing, and human-in-the-loop pauses. Compare to LangGraph for the Python equivalent.
  • Production SLAs matter. Microsoft-backed framework with commercial support options through Azure. Compare to community-maintained alternatives.

When to pick something else

  • TypeScript-first: Mastra is purpose-built for TypeScript ergonomics.
  • Not on Azure, Python-first: LangGraph has the largest Python community and is cloud-agnostic.
  • Multi-agent “crew” patterns: CrewAI emphasizes role-based agent teams with a simpler mental model.
  • Lightweight agent needs: If you just need a single agent with tools, direct provider SDKs (OpenAI Agents, Claude Agent SDK) are simpler than a full framework.

Pricing

Microsoft Agent Framework is free and open source. You pay for:

  • LLM inference (Microsoft Foundry, Azure OpenAI, OpenAI API, Anthropic, Ollama local, or another provider)
  • Azure infrastructure if deployed on Microsoft Foundry or other Azure services
  • Work IQ API consumption when agents ground in Microsoft 365 context through Work IQ APIs. Microsoft’s licensing notice says Work IQ is generally available as of June 16, 2026 and is billed through Copilot Credits, not a separate Work IQ API SKU.
  • Optional Microsoft enterprise support via existing Microsoft contracts

No framework licensing fees.

Verified 2026-06-26 via Microsoft Agent Framework overview, the agent-framework GitHub releases, Microsoft Build 2026, the Work IQ API announcement, the Work IQ licensing notice, and the Partner Center Work IQ update.

Failure modes
  • Azure gravity. The framework works outside Azure, but the reference architecture, documentation, and observability story all assume Microsoft Foundry. Non-Azure users do more setup.
  • Complexity vs simple use cases. A single-agent script that just calls an LLM with a few tools doesn’t need this framework. Use a provider SDK directly.
  • Migration work from AutoGen. Not drop-in. Some multi-agent patterns need rewriting to match the new primitives.
  • Active 1.x cadence. python-1.9.0 shipped June 18 and dotnet-1.11.0 shipped June 23, with recent release notes including breaking guardrail, file-access, hosting, and approval-flow changes. Pin the version you tested against; do not assume patches between minors are non-breaking.
  • Work IQ is a separate consumption surface. As of June 16, Work IQ APIs are generally available, and Microsoft says API consumption draws down Copilot Credits. Do not budget Work IQ agents as “free framework” usage.
  • Third-party model and tool risk. Microsoft explicitly notes in the docs that any non-Azure-direct model or third-party tool is your responsibility for data flow, compliance, and cost. Review before wiring up Anthropic, OpenAI, or Ollama in regulated workloads.
  • Documentation is Microsoft-style. Extensive but dense. Easier to onboard via Microsoft Foundry’s guided experience than raw docs.

Against the alternatives

MS Agent FrameworkLangGraphMastraCrewAIAG2
Primary language.NET + PythonPythonTypeScriptPythonPython
Cloud fitAzureAnyVercel / anyAnyAny
LicenseOpen sourceOpen sourceOpen sourceOpen sourceOpen source
Maturity (2026)1.0 new, polishedEstablishedEarly (1.0)EstablishedAutoGen fork
Best forMS enterprisesPython-firstTS shopsRole-based crewsAutoGen users not on Azure

Methodology

Produced by the aipedia.wiki editorial pipeline. Last verified 2026-06-26 against the Microsoft Agent Framework overview, the providers overview, the agent-framework GitHub releases page, Microsoft Build 2026, the Work IQ API announcement, the Work IQ licensing notice, and the Partner Center Work IQ update.

FAQ

What happened to AutoGen? AutoGen is now in maintenance mode and will not receive new features. Microsoft recommends new projects start on Agent Framework. The community-forked AG2 continues the AutoGen lineage as an independent open-source project for teams that want to stay on that trajectory.

Does Agent Framework require Azure? No. It’s open source and has native client support for Microsoft Foundry, Azure OpenAI, OpenAI, Anthropic, Ollama, Foundry Local, GitHub Copilot, Copilot Studio, and custom providers. Microsoft Foundry is the reference deployment target, not a strict requirement.

Is there a visual agent builder? Not in the framework itself. Microsoft Foundry provides a visual experience for agent composition that sits on top. For pure visual building without Azure, see LangFlow.

How does it compare to Semantic Kernel? Agent Framework is Semantic Kernel’s successor. Existing Semantic Kernel code has a documented migration path. Most orchestration patterns transfer with refactoring.

Sources
ShareLinkedIn
Was this review helpful?
Embed this score on your siteFree. Links back.
Microsoft Agent Framework editorial score badge
<a href="https://aipedia.wiki/tools/microsoft-agent-framework/" target="_blank" rel="noopener"><img src="https://aipedia.wiki/badges/microsoft-agent-framework.svg" alt="Microsoft Agent Framework on aipedia.wiki" width="260" height="72" /></a>
[![Microsoft Agent Framework on aipedia.wiki](https://aipedia.wiki/badges/microsoft-agent-framework.svg)](https://aipedia.wiki/tools/microsoft-agent-framework/)

Badge value auto-updates if the editorial score changes. Attribution via the link is required.

Cite this pageFor journalists, researchers, and bloggers
According to aipedia.wiki Editorial at aipedia.wiki (https://aipedia.wiki/tools/microsoft-agent-framework/)
aipedia.wiki Editorial. (2026). Microsoft Agent Framework: Editorial Review. aipedia.wiki. Retrieved August 3, 2026, from https://aipedia.wiki/tools/microsoft-agent-framework/
aipedia.wiki Editorial. "Microsoft Agent Framework: Editorial Review." aipedia.wiki, 2026, https://aipedia.wiki/tools/microsoft-agent-framework/. Accessed August 3, 2026.
aipedia.wiki Editorial. 2026. "Microsoft Agent Framework: Editorial Review." aipedia.wiki. https://aipedia.wiki/tools/microsoft-agent-framework/.
@misc{microsoft-agent-framework-editorial-revi-2026, author = {{aipedia.wiki Editorial}}, title = {Microsoft Agent Framework: Editorial Review}, year = {2026}, publisher = {aipedia.wiki}, url = {https://aipedia.wiki/tools/microsoft-agent-framework/}, note = {Accessed: 2026-08-02} }
Spotted an error or want to share your experience with Microsoft Agent Framework?

Every tool page is re-verified on a recurring cycle, and corrections land faster when readers flag them directly. If you spot a stale fact, a missing capability, or have used Microsoft Agent Framework and want to share what worked or didn't, the editorial desk reviews every message sent through this form.

Email editorial@aipedia.wiki
Report outdated infoHelp us keep this page accurate