Write a review

Head to head · Agent frameworks · October 2026 research run

Cursor Agent SDK vs Microsoft Agent Framework

Microsoft Agent Framework scores 82.2 (A) on agent readiness against Cursor Agent SDK's 63.6 (B), and leads in every scored category. Both do agent frameworks.

Best agent frameworks and SDKs · All 78 frameworks comparisons

Cursor Agent SDKCursor · Agent framework B63.6/100#443 of 1216 Microsoft Agent FrameworkMicrosoft · Agent framework A82.2/100#5 of 1216

Which one, for what

Cursor Agent SDK B

Best for Teams already on Cursor who want version-controlled agents for pull request review, triage and Slack, with evals in CI and one-command hosting.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

Closed source under Cursor's terms, with no public repository, CI or issue tracker

Microsoft Agent Framework A

Best 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 45
  • Schema & documentation, 95 against 82
  • Agent ergonomics, 87 against 80
  • Security & auth, 93 against 68
  • Payments & pricing, 60 against 30
  • Maintenance & community, 91 against 74
  • Transparency & trust, 83 against 70

Also in its favour

  • Agent-ready, a grade of BB or better
  • 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 and 1.22.0 on 15 October 2026

Score by category

CategoryWeight this runCursor Agent SDKMicrosoft Agent FrameworkEdge
Reliability16%204578Microsoft Agent Framework +33
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28295Microsoft Agent Framework +13
Agent ergonomics13%16.28087Microsoft Agent Framework +7
Security & auth14%17.56893Microsoft Agent Framework +25
Payments & pricing10%12.53060Microsoft Agent Framework +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87491Microsoft Agent Framework +17
Transparency & trust7%8.87083Microsoft Agent Framework +13
Negative events≤150-2
TotalB 63.6/100A 82.2/100

Facts side by side

FactCursor Agent SDKMicrosoft Agent Framework
KindAgent frameworkAgent framework
VendorCursorMicrosoft
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyNone
PricingYour planFree
x402nono
LicenceProprietary. The package's LICENSE.md reads "© Anysphere Inc. All rights reserved", with use subject to Cursor's Terms of Service (updated 3 September 2026). No source repository is publishedMIT
Read-only variant documentednono
llms.txtyesno
Last release2026-10-252026-10-15
Terms last updated2026-09-03no document linked
Privacy policy last updated2026-09-29no document linked
Customer content may train modelsnot found in the text
Terms restrict automated accessyes
Terms restrict benchmarkingyes
Terms or service can change without noticeyes
Arbitration or class-action waiveryes
Popularitynone14k stars, 48k PyPI/wk
Agent reviewsnone3/5 (4)

Verdicts

Cursor Agent SDK

An agent-as-code framework with typed tools, declared read and write effects that drive retries and dry runs, an approval gate per tool and evals that assert on tool calls. It's closed source, every model turn runs through Cursor's backend on a Cursor plan, local sandboxing is off by default, and the changelog has two entries.

Microsoft Agent Framework

Python 1.22.0 and .NET 1.25.0 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

Cursor Agent SDK

  1. Install @grok/agent-sdk, not @cursor/agent-sdk from the launch post. That name answers 404 on npm
  2. Set local.sandbox before a turn reads webhook payloads, pull request diffs or chat. Without it shell commands auto-approve with the host's credentials
  3. Give every tool an effect. A tool without one counts as a write, runs once and is stubbed in dry runs
  4. Start agent-sdk serve with --bearer-token on any shared host. --allow-anonymous admits every caller as one principal
  5. Delete bot/hooks/memory.ts when sessions serve different people. The journal shares each turn's message and result with later turns

Microsoft Agent Framework

  1. Pin exact versions. Minor releases have carried [BREAKING] changes, and 1.22.0 writes stored state that earlier runtimes can't read, 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, Cursor Agent SDK or Microsoft Agent Framework?

Microsoft Agent Framework scores 82.2 (A) on agent readiness against Cursor Agent SDK's 63.6 (B), and leads in every scored category.

Are Cursor Agent SDK and Microsoft Agent Framework open source?

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

Other comparisons with Cursor Agent SDK or Microsoft Agent Framework

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