# Microsoft Agent Framework (slim)

> Microsoft Agent Framework is an open-source SDK for building AI agents and multi-agent workflows in Python and .NET, with a Go version in public preview. Microsoft names it the successor to AutoGen and Semantic Kernel.

- Full: https://www.anchorterminal.com/tools/microsoft-agent-framework.md (~7,550 tokens) · this version ~1,530 tokens · JSON https://www.anchorterminal.com/tools/microsoft-agent-framework.json · canonical https://www.anchorterminal.com/tools/microsoft-agent-framework
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-08

**A · 82.2/100 · rank #6 of 722 · #3 in Agent frameworks & SDKs · agent-ready · confidence high**


Assessment: 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.

## Facts

- Kind: Agent framework · vendor: Microsoft · category: Agent frameworks & SDKs · legal entity: Microsoft Corporation · provenance 80/100
- Packages: pypi `agent-framework`, nuget `Microsoft.Agents.AI`
- Auth: None · pricing: Free · x402: no · licence: MIT
- Languages: Python 3.10 or newer and .NET (net8.0 to net10.0, netstandard2.0, net472). Go in public preview at v0.1.0
- Version: Python 1.21.0 on 8 October 2026 and .NET 1.24.0 on 7 October 2026. 1.0.0 on 2 April 2026
- Models: Microsoft Foundry, Azure OpenAI, OpenAI, Anthropic, Amazon Bedrock, Google Gemini, Mistral, Ollama and Foundry Local, per the docs. Several Python connectors are beta
- MCP client: `MCPStdioTool` and `MCPStreamableHTTPTool` in the Python core, with `allowed_tools` and `approval_mode`. .NET uses the official MCP C# SDK
- Multi-agent: Graph workflows plus sequential, concurrent, handoff, group chat and Magentic orchestrations. A2A package in beta
- Durable state: Workflow checkpoints with in-memory and file storage in core. Azure Functions durable extension and Foundry hosted agents for hosting
- Human approval: `approval_mode` on function and MCP tools in Python, `ApprovalRequiredAIFunction` in .NET. Off unless set
- Guardrails: Middleware for termination and result overrides. FIDES information-flow control is experimental and Python only
- Sandbox: Hyperlight and Monty CodeAct packages, both beta. FIDES is not enforced inside them
- Tracing: OpenTelemetry. Instrumentation is on by default and sends nothing until an exporter is configured. Message content is opt-in
- Telemetry: Package and version User-Agent on client requests by default, plus a feature-usage token on Foundry and Azure OpenAI paths. Both have opt-out variables
- Releases in 90 days: 23 tags, 12 Python and 11 .NET
- Prices: Foundry hosted agents $0.0994 per vCPU-hour

- Scores: Reliability 78, Performance pending, Schema & documentation 95, Agent ergonomics 87, Security & auth 93, Payments & pricing 60, Task success pending, Maintenance & community 91, Transparency & trust 83 · negative events -2 · total over the 7 assessed categories
- Why: Reliability, Read with the local-software lines. · Schema & documentation, Typed in both languages, with py.typed markers and API references for Python and .NET on Microsoft Learn (25). · Agent ergonomics, The documented Python agent with one MCP server is about 12 lines with `MCPStdioTool` from the core package, and `allowed_tools`… · Security & auth, Framework reading, so SOC 2 isn't scored. · Payments & pricing, Read with the self-hosted rule. · Maintenance & community, Python 1.21.0 on 2026-10-08 and .NET 1.24.0 on 2026-10-07 (30). · Transparency & trust, MIT (30).
- Sources: 29, open questions: 8, both in the full twin
- Capabilities: agent.framework, agent.multi-agent, agent.durable, agent.mcp-client
- JSON: https://www.anchorterminal.com/api/v1/tools/microsoft-agent-framework.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/microsoft-agent-framework.svg` or a link to https://www.anchorterminal.com/tools/microsoft-agent-framework from a page on microsoft.com or one of its subdomains, or the README of github.com/microsoft/agent-framework, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

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

## Connect

```bash
pip install agent-framework   # or: dotnet add package Microsoft.Agents.AI
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| OpenAI Agents SDK | AA | 86.2 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | https://www.anchorterminal.com/tools/openai-agents-sdk.min.md |
| Pydantic AI | A | 83.7 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | https://www.anchorterminal.com/tools/pydantic-ai.min.md |
| Docker Agent | BB | 76.5 | agent.framework, agent.multi-agent, agent.mcp-client, agent.durable | https://www.anchorterminal.com/tools/docker-agent.min.md |
| Agent Development Kit (ADK) | BB | 74.7 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | https://www.anchorterminal.com/tools/google-adk.min.md |
| Agno | BB | 72.8 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | https://www.anchorterminal.com/tools/agno.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)