Get an audit

Head to head · Agent frameworks · October 2026 research run

Claude Agent SDK vs Microsoft Agent Framework

Microsoft Agent Framework scores 82.2 (A) on agent readiness against Claude Agent SDK's 72.1 (BB), and leads in 5 of 7 scored categories. Claude Agent SDK leads on agent ergonomics. Both do agent frameworks.

Claude Agent SDKAnthropic · Agent framework BB72.1/100#91 of 629 Microsoft Agent FrameworkMicrosoft · Agent framework A82.2/100#6 of 629

Which one, for what

Claude Agent SDK BB

Good for Agents that work on files, code and shells and want Claude Code's tool set and permission model without building them.

Ahead on

  • Agent ergonomics, 94 against 87

Watch for

Claude models only, so a person has to set up a Claude API key or cloud account first

Microsoft Agent Framework A

Good for Teams on Azure or .NET, and for teams moving off AutoGen or Semantic Kernel, that want MCP, approval, checkpointed workflows and OpenTelemetry in one SDK.

Ahead on

  • Reliability, 78 against 70
  • Schema & documentation, 95 against 89
  • Security & auth, 93 against 83
  • Payments & pricing, 60 against 40

Also in its favour

  • No key needed to call it
  • Free to start without a card
  • Open source

Watch for

Changes marked [BREAKING] shipped in minor releases of released packages, including agent-framework-core in 1.20.0 on 2 October 2026

Score by category

CategoryWeight this runClaude Agent SDKMicrosoft Agent FrameworkEdge
Reliability16%207078Microsoft Agent Framework +8
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28995Microsoft Agent Framework +6
Agent ergonomics13%16.29487Claude Agent SDK +7
Security & auth14%17.58393Microsoft Agent Framework +10
Payments & pricing10%12.54060Microsoft Agent Framework +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88791Microsoft Agent Framework +4
Transparency & trust7%8.88383even
Negative events≤15-6-2
Total72.1 · BB82.2 · A

Facts side by side

FactClaude Agent SDKMicrosoft Agent Framework
KindAgent frameworkAgent framework
VendorAnthropicMicrosoft
Hosted endpointno (local only)no (local only)
Transports
AuthAPI keyNone
PricingFreeFree
x402nono
LicenceMIT (Python wrapper), proprietary (TypeScript package and the bundled Claude Code binary)MIT
Read-only variant documentednono
llms.txtyesno
Last release2026-09-302026-10-08
Terms last updatedno date givenno document linked
Privacy policy last updatedno date givenno document linked
Customer content may train modelsyes, with an opt-out
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingyes
Terms or service can change without noticenot found in the text
Arbitration or class-action waiveryes
Popularity8.2k stars, 10.1M npm/wk, 6.1M PyPI/wk14k stars, 48k PyPI/wk

Verdicts

Claude Agent SDK

Claude Code's file, shell, search and web tools, with six permission modes, a canUseTool callback and PreToolUse hooks. Claude models only, so a person has to set up a Claude API key or cloud account first.

Microsoft Agent Framework

Python 1.21.0 and .NET 1.24.0 are MIT, past 1.0 and released about weekly, with an MCP client, tool approval, checkpointed graph workflows and OpenTelemetry. Breaking changes ship in minor releases, a version User-Agent and a feature-usage token are sent by default, and a high-severity advisory in the .NET declarative workflows package was published on 7 October 2026.

Before you call either

Claude Agent SDK

  1. Set DISABLE_TELEMETRY=1 before the first run on the Claude API
  2. List MCP tools in allowed_tools, or the agent sees them and can't call them
  3. Pass permission_mode explicitly. An unset mode can start in auto mode since TypeScript 0.3.286
  4. Pin the version. Releases land almost daily and some get yanked
  5. Check the init message for MCP servers in failed or needs-auth. They don't raise

Microsoft Agent Framework

  1. Pin exact versions. Minor releases have carried [BREAKING] changes, so read python/CHANGELOG.md or the upgrade guides before moving up
  2. Set approval_mode="always_require" on tools and MCP servers that write. The default is never_require
  3. Pass allowed_tools to MCPStdioTool or MCPStreamableHTTPTool so only the named MCP tools reach the model
  4. Set AGENT_FRAMEWORK_USER_AGENT_DISABLED=true to drop the framework's User-Agent and feature token, or AGENT_FRAMEWORK_FEATURE_MASK_DISABLED=true for the token alone
  5. On .NET, use Microsoft.Agents.AI.Workflows.Declarative 1.24.0 or later. Earlier versions could forward protected workflow values to an external MCP server

Questions

Which is better for AI agents, Claude Agent SDK or Microsoft Agent Framework?

Microsoft Agent Framework scores 82.2 (A) on agent readiness against Claude Agent SDK's 72.1 (BB), and leads in 5 of 7 scored categories. Claude Agent SDK leads on agent ergonomics.

Are Claude Agent SDK and Microsoft Agent Framework open source?

No open-source release is listed for Claude Agent SDK. Microsoft Agent Framework is open source (MIT).

Other comparisons with Claude Agent SDK or Microsoft Agent Framework

Disclosure

Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and the panel doesn't review it, because every reviewer runs on Claude too.

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report