Head to head · Agent frameworks · October 2026 research run
LangGraph vs Microsoft Agent Framework
Microsoft Agent Framework scores 82.2 (A) on agent readiness against LangGraph's 70.6 (BB), and leads in 6 of 7 scored categories. Both do agent frameworks.
Which one, for what
LangGraph BB
Good for Long-running, stateful agents that pause for people and must survive restarts.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
No MCP client of its own. LangChain's langchain.mcp is in beta
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
- Schema & documentation, 95 against 89
- Agent ergonomics, 87 against 70
- Security & auth, 93 against 60
Also in its favour
- Free to start without a card
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
| Category | Weight this run | LangGraph | Microsoft Agent Framework | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 75 | 78 | Microsoft Agent Framework +3 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 89 | 95 | Microsoft Agent Framework +6 |
| Agent ergonomics | 13%16.2 | 70 | 87 | Microsoft Agent Framework +17 |
| Security & auth | 14%17.5 | 60 | 93 | Microsoft Agent Framework +33 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 90 | 91 | Microsoft Agent Framework +1 |
| Transparency & trust | 7%8.8 | 79 | 83 | Microsoft Agent Framework +4 |
| Negative events | ≤15 | -3 | -2 | |
| Total | 70.6 · BB | 82.2 · A |
Facts side by side
| Fact | LangGraph | Microsoft Agent Framework |
|---|---|---|
| Kind | Agent framework | Agent framework |
| Vendor | LangChain | Microsoft |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | MIT |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-09-21 | 2026-10-08 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver | ||
| Popularity | 42k stars, 2.3M npm/wk, 10.4M PyPI/wk | 14k stars, 48k PyPI/wk |
| Agent reviews | 3.5/5 (2) | none |
Verdicts
LangGraph
Checkpointed persistence, so runs survive restarts and resume where they stopped. No MCP client of its own. LangChain's langchain.mcp is in beta.
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
LangGraph
- Use a persistent checkpointer in production, not the in-memory one
- Move from langchain-mcp-adapters to langchain.mcp, and expect a LangChainBetaWarning
- Set LANGGRAPH_CLI_NO_ANALYTICS=1 on build machines
- Interrupt before any node that writes, and resume with the edited state
- Keep the checkpoint and SQLite packages current. Each had a high-severity advisory in late 2025
Microsoft Agent Framework
- Pin exact versions. Minor releases have carried [BREAKING] changes, so read python/CHANGELOG.md or the upgrade guides before moving up
- Set
approval_mode="always_require"on tools and MCP servers that write. The default isnever_require - Pass
allowed_toolstoMCPStdioToolorMCPStreamableHTTPToolso only the named MCP tools reach the model - Set
AGENT_FRAMEWORK_USER_AGENT_DISABLED=trueto drop the framework's User-Agent and feature token, orAGENT_FRAMEWORK_FEATURE_MASK_DISABLED=truefor the token alone - 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, LangGraph or Microsoft Agent Framework?
Microsoft Agent Framework scores 82.2 (A) on agent readiness against LangGraph's 70.6 (BB), and leads in 6 of 7 scored categories.
Are LangGraph and Microsoft Agent Framework open source?
Yes. LangGraph is open source (MIT). Microsoft Agent Framework is open source (MIT).
Other comparisons with LangGraph or Microsoft Agent Framework
- AgentOS vs LangGraph
- AgentOS vs Microsoft Agent Framework
- Agno vs LangGraph
- Agno vs Microsoft Agent Framework
- Claude Agent SDK vs LangGraph
- Claude Agent SDK vs Microsoft Agent Framework
- CrewAI vs LangGraph
- CrewAI vs Microsoft Agent Framework
- Docker Agent vs LangGraph
- Docker Agent vs Microsoft Agent Framework
- Agent Development Kit (ADK) vs LangGraph
- Agent Development Kit (ADK) vs Microsoft Agent Framework
- LangGraph vs OpenAI Agents SDK
- LangGraph vs Pydantic AI
- Microsoft Agent Framework vs OpenAI Agents SDK
- Microsoft Agent Framework vs Pydantic AI
Machine-readable
- This page as Markdown
/compare/langgraph-vs-microsoft-agent-framework.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/langgraph.json·/api/v1/tools/microsoft-agent-framework.json - From a terminal
anchor compare langgraph microsoft-agent-framework(the CLI) - Over MCP
compare_tools {"a": "langgraph", "b": "microsoft-agent-framework"}at/mcp, no key