# Microsoft Agent Framework

> 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.

- Canonical: https://www.anchorterminal.com/tools/microsoft-agent-framework
- Markdown: https://www.anchorterminal.com/tools/microsoft-agent-framework.md (~7,550 tokens)
- Slim: https://www.anchorterminal.com/tools/microsoft-agent-framework.min.md (~1,530 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/microsoft-agent-framework.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-08

## Overview

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


More from Microsoft, listed separately because each is its own product: [Microsoft Foundry fine-tuning (Azure OpenAI)](https://www.anchorterminal.com/tools/azure-foundry-fine-tuning.md) (Fine-tuning), [Azure AI Content Safety (Prompt Shields)](https://www.anchorterminal.com/tools/azure-ai-content-safety.md) (Guardrails & safety filters), [Azure AI Speech speech-to-text](https://www.anchorterminal.com/tools/azure-speech-to-text.md) (Speech-to-text), [Azure AI Speech text-to-speech](https://www.anchorterminal.com/tools/azure-text-to-speech.md) (Text-to-speech), [Microsoft Execution Containers](https://www.anchorterminal.com/tools/microsoft-execution-containers.md) (Code execution sandboxes), [Microsoft Entra Agent ID](https://www.anchorterminal.com/tools/microsoft-entra-agent-id.md) (Agent auth & delegated access), [Azure Key Vault](https://www.anchorterminal.com/tools/azure-key-vault.md) (Secrets & credential vaults), [Azure DevOps MCP Server](https://www.anchorterminal.com/tools/azure-devops-mcp.md) (Code & developer platforms), [Microsoft Learn MCP Server](https://www.anchorterminal.com/tools/microsoft-learn-mcp.md) (Code & developer platforms), [Playwright MCP](https://www.anchorterminal.com/tools/playwright-mcp.md) (Browser automation), [Azure MCP Server](https://www.anchorterminal.com/tools/azure-mcp.md) (Cloud & infrastructure), [Azure Maps](https://www.anchorterminal.com/tools/azure-maps.md) (Maps, geocoding & places), [Azure Translator](https://www.anchorterminal.com/tools/azure-translator.md) (Translation), [Microsoft Graph Calendar API](https://www.anchorterminal.com/tools/microsoft-graph-calendar.md) (Calendars & scheduling), [Microsoft Teams (Microsoft Graph)](https://www.anchorterminal.com/tools/microsoft-teams.md) (Work & productivity), [Microsoft Dynamics 365 Sales](https://www.anchorterminal.com/tools/dynamics-365-sales.md) (CRM & customer platforms), [Microsoft Power Automate](https://www.anchorterminal.com/tools/power-automate.md) (Workflow automation), [Microsoft Advertising API](https://www.anchorterminal.com/tools/microsoft-advertising-api.md) (Advertising & campaign operations), [Microsoft Excel (Microsoft Graph workbook API)](https://www.anchorterminal.com/tools/microsoft-excel-graph.md) (Spreadsheets & operational tables), [Outlook Mail (Microsoft Graph)](https://www.anchorterminal.com/tools/outlook-mail-graph.md) (Mailbox access).

## 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

| Field | Value |
| --- | --- |
| Vendor | Microsoft (https://www.microsoft.com) |
| Kind | Agent framework |
| Category | Agent frameworks & SDKs (https://www.anchorterminal.com/categories/frameworks) |
| Auth | None · A library with no account of its own. Credentials are for the model provider and the tools used. The quickstarts sign in to Microsoft Foundry with an Azure credential, and the OpenAI, Anthropic and other clients take their own keys from the environment. |
| Pricing | Free (Free · OSS) · Free under MIT, with model calls paid to the provider. Foundry hosted agents, the managed hosting option, is a separate Azure service at $0.0994 a vCPU-hour and $0.0118 an hour for memory in East US, per Azure's retail price API on 8 October 2026. |
| x402 | No · No x402, MPP or L402 found in the repository or the docs (checked 2026-10-08). |
| Licence | MIT |
| Packages | pypi: `agent-framework`; nuget: `Microsoft.Agents.AI` |
| Source | https://github.com/microsoft/agent-framework |
| Docs | https://learn.microsoft.com/en-us/agent-framework/overview/ |
| llms.txt | not found |
| Last release | 2026-10-08 |
| GitHub stars | 14,015 (as of 2026-10-08) |
| PyPI downloads / week | 47,507 |
| 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 |
| Capabilities | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client |
| Tags | official, framework, python, dotnet, go, open-source, durable, free, no-card |
| JSON | https://www.anchorterminal.com/api/v1/tools/microsoft-agent-framework.json |

## Score breakdown (methodology v0.4, October 2026 research run)

Assessed 2026-10-08 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: high. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points.

| Category | Weight | This run | Score (0–100) | Points |
| --- | --- | --- | --- | --- |
| Reliability | 16% | 20 | 78 | 15.6 |
| Performance | 10% | pending | pending | n/a |
| Schema & documentation | 13% | 16.2 | 95 | 15.4 |
| Agent ergonomics | 13% | 16.2 | 87 | 14.1 |
| Security & auth | 14% | 17.5 | 93 | 16.3 |
| Payments & pricing | 10% | 12.5 | 60 | 7.5 |
| Task success | 10% | pending | pending | n/a |
| Maintenance & community | 7% | 8.8 | 91 | 8.0 |
| Transparency & trust (editorial 86, provenance 80) | 7% | 8.8 | 83 | 7.3 |
| Negative events | up to −15 | up to −15 | 2026-10-07. High-severity advisory GHSA-9f26-7mqc-9vc4 (CVSS 7.5). Microsoft.Agents.AI.Workflows.Declarative before 1.24.0 could forward values marked sensitive, including environment-scoped secrets, to an external MCP server from an InvokeMcpTool action. Fixed in 1.24.0 and published the same day, so 2 points. Two medium advisories published the same day (GHSA-q7g7-7c7x-frcq, approval not bound to transport headers, and GHSA-r2mq-wgc9-vgh3, Foundry toolbox bearer token sent to an unintended origin) weren't deducted. https://github.com/microsoft/agent-framework/security/advisories/GHSA-9f26-7mqc-9vc4  | -2 |
| **Total** | | | | **82.2 → A** |

### Why each score

- Reliability 78: Read with the local-software lines. Official packages on PyPI (Requires-Python >=3.10) and NuGet (net8.0 to net10.0, netstandard2.0, net472) (20). The .NET build and test workflow passed on 11 of the 12 most recent pushes to main on 8 October 2026, with one cancelled, and the Python merge tests passed on each nightly run from 1 to 8 October (25). 575 open issues and 201 open pull requests, with 260 issues closed in the 30 days to 8 October and 14 open issues labelled bug (10). The Python changelog follows Keep a Changelog and states semantic versioning, and marks breaking changes, but they shipped in minor releases of released packages, such as agent-framework-core in 1.20.0 on 2 October 2026 (8). Python 1.21.0 and .NET 1.24.0, classed 5 - Production/Stable on PyPI (15).
- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.
- Schema & documentation 95: Typed in both languages, with py.typed markers and API references for Python and .NET on Microsoft Learn (25). Learn returns each docs page as Markdown when asked with an Accept header. No llms.txt was found (10). The overview has a table for when to use an agent or a workflow, and says to write a function instead where one would do (20). Tools are Python functions typed with Annotated and Pydantic Field, or AIFunction in .NET (15). Samples for every area and a typed exception hierarchy in the source, but we found no exception reference in the docs pages we read (12). A dated Python changelog and four upgrade guides. No changelog file was found for .NET (13).
- Agent ergonomics 87: The documented Python agent with one MCP server is about 12 lines with `MCPStdioTool` from the core package, and `allowed_tools`, `load_tools` and progressive disclosure limit what reaches the model (25). The function loop stops at 40 iterations by default with a `max_function_calls` option, and compaction has its own docs page (20). A typed exception hierarchy, and the loop stops after three consecutive tool errors by default. We didn't find MCP failures documented (16). Workflows resume from checkpoints and sessions serialise, but we found no retry setting for model calls in the core client (14). An agent needs a client and instructions. Python and .NET are stable, Go is in preview, and the quickstarts assume a Microsoft Foundry project (12).
- Security & auth 93: Framework reading, so SOC 2 isn't scored. A package and version User-Agent goes out on client requests by default, with a feature-usage token on Foundry and Azure OpenAI paths. Both are documented with opt-out variables, and the observability module says the framework contacts no external system itself, with message content in traces off by default (25). `approval_mode` on function and MCP tools, an MCP tool allow-list, and Hyperlight and Monty sandboxes for model-written code in beta. Tools run without approval unless set (20). An Agent Safety page treats model-supplied arguments as untrusted, and FIDES labels content and enforces policy before sensitive tools run, though it is experimental and Python only (15). OpenTelemetry traces, metrics and logs to any exporter (15). SECURITY.md routes reports to MSRC with a bounty programme and coordinated disclosure, CodeQL runs in CI and three advisories were published with fixed versions on 7 October 2026. Microsoft's security.txt expired on 23 September 2026 (18).
- Payments & pricing 60: Read with the self-hosted rule. No payment protocol (0). The package is free under MIT, and Foundry hosted agents, the managed option, has per-unit prices in Azure's public retail price API ($0.0994 a vCPU-hour and $0.0118 an hour for memory in East US). The pricing web page showed no figures to our reader (20). The packages install with no card (20) and no account, and run local models through the Ollama and Foundry Local connectors (20).
- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.
- Maintenance & community 91: Python 1.21.0 on 2026-10-08 and .NET 1.24.0 on 2026-10-07 (30). 23 release tags in the 90 days to 8 October, 12 Python and 11 .NET (20). 575 open issues and 201 open pull requests, 260 issues closed in 30 days, and triage and labelling workflows run on new issues. We couldn't see reply times (17). Python and .NET packages are current, and Go is a prerelease at v0.1.0 from 1 September 2026 (15). CI, CodeQL and Dependabot run, though two of four Dependabot update runs failed on 8 October (9).
- Transparency & trust 83: MIT (30). The core README says what the User-Agent and feature token are, and a design spec in the repository says the token goes only to Foundry and Azure OpenAI pipelines and not to third-party providers. That spec is marked proposed, and we found no statement of how long Microsoft keeps the data and no privacy document for the framework (22). Package lifecycle states are published per package, experimental APIs raise warnings, breaking changes are dated in the Python changelog and there are upgrade guides, but we found no written support window (14). Telemetry is disclosed with two opt-out variables (20).

Fix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (18 items): https://www.anchorterminal.com/fixes/microsoft-agent-framework.md (JSON https://www.anchorterminal.com/fixes/microsoft-agent-framework.json)

### What we couldn't check

- unchecked: prices on the Foundry Agent Service pricing page. Our reader saw placeholders where the figures load, so the hosted agent prices are from Azure's retail price API for East US, and the unit of the memory meter is given there only as 1 Hour
- unchecked: reply times on issues. We counted open and closed issues through the GitHub API and did not read threads
- unchecked: a retry setting for model calls. None was found in the core client source, and the provider SDKs may retry on their own
- unchecked: the .NET release notes. No changelog file is in the repository and we did not read the GitHub release pages
- unchecked: the Python and .NET API reference pages. Both URLs answered with a redirect and we did not read their content
- No terms or privacy document specific to the framework was found, so provenance.terms and provenance.privacy are left out
- The feature-usage telemetry spec is marked proposed while the code ships the token. We found no statement of how long Microsoft keeps User-Agent data
- The support FAQ says .NET and Python are the supported languages, while the overview adds Go in public preview

### Sources

- docs overview, successor statement and Go preview notice: <https://learn.microsoft.com/en-us/agent-framework/overview/> (seen 2026-10-08)
- repository, README, licence, tags and workflows at commit 91ab44f: <https://github.com/microsoft/agent-framework> (seen 2026-10-08)
- Python changelog: <https://github.com/microsoft/agent-framework/blob/main/python/CHANGELOG.md> (seen 2026-10-08)
- Python package lifecycle states: <https://github.com/microsoft/agent-framework/blob/main/python/PACKAGE_STATUS.md> (seen 2026-10-08)
- core package README, telemetry controls: <https://github.com/microsoft/agent-framework/blob/main/python/packages/core/README.md> (seen 2026-10-08)
- feature-usage telemetry design spec: <https://github.com/microsoft/agent-framework/blob/main/docs/specs/004-feature-usage-telemetry.md> (seen 2026-10-08)
- telemetry module in the core package: <https://github.com/microsoft/agent-framework/blob/main/python/packages/core/agent_framework/_telemetry.py> (seen 2026-10-08)
- observability module, defaults for instrumentation and sensitive data: <https://github.com/microsoft/agent-framework/blob/main/python/packages/core/agent_framework/observability.py> (seen 2026-10-08)
- MCP client source: <https://github.com/microsoft/agent-framework/blob/main/python/packages/core/agent_framework/_mcp.py> (seen 2026-10-08)
- security policy: <https://github.com/microsoft/agent-framework/blob/main/SECURITY.md> (seen 2026-10-08)
- repository security advisories: <https://github.com/microsoft/agent-framework/security/advisories> (seen 2026-10-08)
- advisory GHSA-9f26-7mqc-9vc4: <https://github.com/microsoft/agent-framework/security/advisories/GHSA-9f26-7mqc-9vc4> (seen 2026-10-08)
- .NET build and test runs on main: <https://github.com/microsoft/agent-framework/actions/workflows/dotnet-build-and-test.yml?query=branch%3Amain> (seen 2026-10-08)
- Python merge test runs: <https://github.com/microsoft/agent-framework/actions/workflows/python-merge-tests.yml> (seen 2026-10-08)
- repository counts from the GitHub API: <https://api.github.com/repos/microsoft/agent-framework> (seen 2026-10-08)
- PyPI project and release history: <https://pypi.org/project/agent-framework/> (seen 2026-10-08)
- PyPI download counts: <https://pypistats.org/packages/agent-framework> (seen 2026-10-08)
- NuGet package versions: <https://www.nuget.org/packages/Microsoft.Agents.AI> (seen 2026-10-08)
- Go repository and releases: <https://github.com/microsoft/agent-framework-go> (seen 2026-10-08)
- local MCP tools docs: <https://learn.microsoft.com/en-us/agent-framework/agents/tools/local-mcp-tools> (seen 2026-10-08)
- tool approval docs: <https://learn.microsoft.com/en-us/agent-framework/agents/tools/tool-approval> (seen 2026-10-08)
- Agent Safety docs: <https://learn.microsoft.com/en-us/agent-framework/concepts/agents/safety> (seen 2026-10-08)
- FIDES docs: <https://learn.microsoft.com/en-us/agent-framework/agents/security> (seen 2026-10-08)
- workflow checkpoints docs: <https://learn.microsoft.com/en-us/agent-framework/workflows/checkpoints> (seen 2026-10-08)
- upgrade guides: <https://learn.microsoft.com/en-us/agent-framework/support/upgrade/> (seen 2026-10-08)
- Foundry hosted agents docs: <https://learn.microsoft.com/en-us/agent-framework/hosting/foundry-hosted-agent> (seen 2026-10-08)
- Azure retail price API, Foundry Agents meters in East US: <https://prices.azure.com/api/retail/prices?$filter=contains(productName,'Agent')%20and%20armRegionName%20eq%20'eastus'> (seen 2026-10-08)
- Foundry Agent Service pricing page: <https://azure.microsoft.com/en-us/pricing/details/foundry-agent-service/> (seen 2026-10-08)
- security.txt: <https://www.microsoft.com/.well-known/security.txt> (seen 2026-10-08)

## Who's behind it (provenance 80/100, checked 2026-10-08)

| Check | Finding | Points |
| --- | --- | --- |
| Legal entity named | Microsoft Corporation | 20/20 |
| Domain age | microsoft.com, registered 1991-05-02 (35 years) | 15/15 |
| Endpoint on the vendor's domain | no hosted endpoint | n/a |
| Terms of service | nothing hosted, so the MIT licence stands in | 10/10 |
| Privacy policy | nothing hosted, not scored | n/a |
| Status page | not found | 0/10 |
| Changelog | published | 10/10 |
| security.txt | published but past its Expires date | 5/10 |

The repository is under GitHub's microsoft organisation and its licence file reads Copyright (c) Microsoft Corporation.

No terms or privacy document for the framework itself was found. The MIT licence is the only document that governs the packages, and neither the repository README nor the core package README links a privacy statement, so both fields are left out.

www.microsoft.com/.well-known/security.txt loads and points to the MSRC researcher portal, but its Expires field is 2026-09-23T16:00:00.000Z, which had passed on 8 October 2026. learn.microsoft.com has none.

RDAP gives microsoft.com a registration date of 1991-05-02.

The changelog link is the Python one. No changelog file was found for .NET in the repository.

### Terms and privacy, as read

A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.

**Terms of service**. Nothing is hosted by the vendor, so there are no terms of service to read. The MIT licence stands in and the check scores in full.


**Privacy policy**. Nothing is hosted by the vendor, so there is no privacy policy to read and the check isn't scored.


## Live (updated 2026-10-08 18:24 UTC)

- Watching changelog <https://raw.githubusercontent.com/microsoft/agent-framework/main/python/CHANGELOG.md>
- Always current: https://www.anchorterminal.com/api/v1/live/microsoft-agent-framework.json

## Probe metrics

A library has no endpoint to probe. Reliability is assessed from its tests, release history and issue tracker; performance waits for the task suite run through it. See https://www.anchorterminal.com/benchmark/#kinds

## Prices

| Item | Price | Unit | Note |
| --- | --- | --- | --- |
| Foundry hosted agents | $0.0994 | per vCPU-hour | East US, plus $0.0118 an hour for memory. A separate Azure service |

Across all listings: https://www.anchorterminal.com/prices/index.md

## Strengths

- MIT, with Python 1.21.0 on PyPI (8 October 2026) and .NET 1.24.0 on NuGet (7 October 2026), both past 1.0 since 2 April 2026
- 23 tagged releases in the 90 days to 8 October 2026, 12 for Python and 11 for .NET
- MCP client in the core package over stdio and streamable HTTP, with a tool allow-list, per-tool approval and optional progressive disclosure
- Graph workflows with checkpoints, in-memory and file storage in core, and five orchestration patterns (sequential, concurrent, handoff, group chat, Magentic)
- A safety page and FIDES, an information-flow control middleware for prompt injection, which is experimental and Python only

## Weaknesses

- Changes marked [BREAKING] shipped in minor releases of released packages, including agent-framework-core in 1.20.0 on 2 October 2026
- A package and version User-Agent goes out on client requests by default, with a feature-usage token on Foundry and Azure OpenAI paths. Two environment variables turn them off
- Three advisories were published on 7 October 2026 against .NET packages, one high (CVSS 7.5), all with fixed versions
- Tools run without approval unless approval is set on each tool, per the safety page
- 575 open issues and 201 open pull requests on 8 October 2026, and 26 of 44 Python packages are alpha or beta

## Before you call it (notes for agents)

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

## Get started

Install:

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

## Similar tools

Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.

| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |
| --- | --- | --- | --- | --- | --- | --- |
| OpenAI Agents SDK | AA | 86.2 | 1 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | no | https://www.anchorterminal.com/tools/openai-agents-sdk.md |
| Pydantic AI | A | 83.7 | 3 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | no | https://www.anchorterminal.com/tools/pydantic-ai.md |
| Docker Agent | BB | 76.5 | 30 | agent.framework, agent.multi-agent, agent.mcp-client, agent.durable | no | https://www.anchorterminal.com/tools/docker-agent.md |
| Agent Development Kit (ADK) | BB | 74.7 | 58 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | no | https://www.anchorterminal.com/tools/google-adk.md |
| Agno | BB | 72.8 | 85 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | no | https://www.anchorterminal.com/tools/agno.md |
| LangGraph | BB | 70.6 | 131 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | no | https://www.anchorterminal.com/tools/langgraph.md |

## Panel reviews (0)

Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .

Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md

## Notable

- The overview calls Agent Framework the direct successor to Semantic Kernel and AutoGen, created by the same teams, with migration guides for both (source: <https://learn.microsoft.com/en-us/agent-framework/overview/>)
- agent-framework 1.21.0 on PyPI on 2026-10-08, Requires-Python >=3.10, classed 5 - Production/Stable. 1.0.0 was published on 2026-04-02 and the first beta on 2025-10-01 (source: <https://pypi.org/project/agent-framework/>)
- Microsoft.Agents.AI 1.24.0 on NuGet on 2026-10-07, MIT, targeting net10.0, net9.0, net8.0, netstandard2.0 and net472 (source: <https://www.nuget.org/packages/Microsoft.Agents.AI>)
- The Go SDK is in public preview in its own repository, with v0.1.0 marked a prerelease on 2026-09-01. Declarative agents, RAG, CodeAct and functional workflows are not yet available in Go (source: <https://learn.microsoft.com/en-us/agent-framework/overview/>)
- Agent Framework adds a package and version User-Agent to supported client requests, and Foundry and Azure OpenAI request paths can carry a feature-usage token. Each has an environment variable to turn it off (source: <https://github.com/microsoft/agent-framework/blob/main/python/packages/core/README.md>)
- Three repository advisories on 2026-10-07, all against .NET packages. GHSA-9f26-7mqc-9vc4 is high (CVSS 7.5) and fixed in Microsoft.Agents.AI.Workflows.Declarative 1.24.0 (source: <https://github.com/microsoft/agent-framework/security/advisories>)
- 18 of 44 Python packages are in the released state. The others are alpha or beta, among them the A2A, Anthropic, Ollama, DevUI and Foundry hosting packages (source: <https://github.com/microsoft/agent-framework/blob/main/python/PACKAGE_STATUS.md>)
- agent-framework-core, the package that agent-framework installs, had 292,425 downloads in the week to 8 October 2026 (source: <https://pypistats.org/packages/agent-framework-core>)

## Compare

- [AgentOS vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/agentos-vs-microsoft-agent-framework.md): BB 75.3 vs A 82.2
- [Agno vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/agno-vs-microsoft-agent-framework.md): BB 72.8 vs A 82.2
- [Claude Agent SDK vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-microsoft-agent-framework.md): BB 72.1 vs A 82.2
- [CrewAI vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/crewai-vs-microsoft-agent-framework.md): B 67 vs A 82.2
- [Docker Agent vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/docker-agent-vs-microsoft-agent-framework.md): BB 76.5 vs A 82.2
- [Agent Development Kit (ADK) vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/google-adk-vs-microsoft-agent-framework.md): BB 74.7 vs A 82.2
- [LangGraph vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/langgraph-vs-microsoft-agent-framework.md): BB 70.6 vs A 82.2
- [Microsoft Agent Framework vs OpenAI Agents SDK](https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-openai-agents-sdk.md): A 82.2 vs AA 86.2
- [Microsoft Agent Framework vs Pydantic AI](https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-pydantic-ai.md): A 82.2 vs A 83.7

## Verify this listing

For the vendor. The badge or a plain link to this page verifies the listing, from a page on microsoft.com or one of its subdomains, or the README of github.com/microsoft/agent-framework. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "microsoft-agent-framework", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify

HTML badge:

```html
<a href="https://www.anchorterminal.com/tools/microsoft-agent-framework"><img src="https://www.anchorterminal.com/badges/microsoft-agent-framework.svg" alt="Microsoft Agent Framework on Anchor Terminal" height="20"></a>
```

Markdown badge, for a README:

```markdown
[![Microsoft Agent Framework on Anchor Terminal](https://www.anchorterminal.com/badges/microsoft-agent-framework.svg)](https://www.anchorterminal.com/tools/microsoft-agent-framework)
```

Plain link:

```html
<a href="https://www.anchorterminal.com/tools/microsoft-agent-framework">Microsoft Agent Framework on Anchor Terminal</a>
```

## Share this listing

For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Microsoft Agent Framework is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.

- Dark: https://www.anchorterminal.com/assets/share/microsoft-agent-framework-dark.png
- Light: https://www.anchorterminal.com/assets/share/microsoft-agent-framework-light.png