rysweet avatar

Microsoft Agent Framework

Microsoft's new Agent Framework unifies AutoGen's simplicity with Semantic Kernel's enterprise features into a production-ready platform for building AI agents and workflows. You get stateful conversational agents, graph-based orchestration with conditional routing, and proper tooling like middleware, telemetry, and human-in-the-loop approvals. It's available in both Python and C#, which matters if you're working in .NET shops. The framework is still in preview (0.1.0) but already has 5.1k stars on GitHub. Use this when you need multi-agent systems with actual production concerns like logging and approval workflows, not just research prototypes. The skill includes integration guidance for deciding when to use Agent Framework versus simpler alternatives.

skills.sh installs
259
GitHub stars
76
last updated
Aug 21, 2026

Install

$ npx -y skills add rysweet/amplihack --skill microsoft-agent-framework --agent claude-code

Installs into .claude/skills of the current project.

Files

Microsoft Agent Framework Skill

Version: 0.1.0-preview | Last Updated: 2025-11-15 | Framework Version: 0.1.0-preview Languages: Python 3.10+, C# (.NET 8.0+) | License: MIT

Quick Reference

Microsoft Agent Framework is an open-source platform for building production AI agents and workflows, unifying AutoGen's simplicity with Semantic Kernel's enterprise features.

Core Capabilities: AI Agents (stateful conversations, tool integration) | Workflows (graph-based orchestration, parallel processing) | Enterprise features (telemetry, middleware, MCP support)

Installation:

  • Python: pip install agent-framework-core --pre
  • C#: dotnet add package Microsoft.Agents.AI --prerelease

Repository: https://github.com/microsoft/agent-framework (5.1k stars)


When to Use This Skill

Use Microsoft Agent Framework when you need:

Sponsors

Details

Repository
github.com/rysweet/amplihack
Categories
AI & Agent Building, Automation & Workflows, Design & UI/UX
First seen
Jun 3, 2026

More from rysweet/amplihack

All 58
1patricio0312rev avatarembedding-pipeline-builderpatricio0312rev/skillsBuilds document embedding pipelines with text chunking, embedding generation, indexing, and retrieval optimization. Use when users request "embedding pipeline",255skills.sh installs
2personamanagmentlayer avatarai-engineer-expertpersonamanagmentlayer/pclExpert-level AI implementation, deployment, LLM integration, and production AI systems239skills.sh installs
3laguagu avatarai-sdk-6laguagu/claude-code-nextjs-skillsVercel AI SDK v6 development. Use when building AI agents, chatbots, tool integrations, streaming apps, or structured output with the ai package. Covers ToolLoo216skills.sh installs
4aiskillstore avataragent-developmentaiskillstore/marketplaceThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent ex199skills.sh installs
5existential-birds avatarpydantic-ai-tool-systemexistential-birds/beagleRegister and implement PydanticAI tools with proper context handling, type annotations, and docstrings. Use when adding tool capabilities to agents, implementin161skills.sh installs
6rohitg00 avatarllm-gaterohitg00/pro-workflowLLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing operations. Use to set u158skills.sh installs