Jacob Alber
3b81164a6d
* fix: MessageMerger crashes when there are no dangling messages * refactor: Better logic for AgentId in Workflow-as-Agent If the parent "agent" instance received an Id or Name when being instantiated, we should avoid stomping over it with the subagents' ids. But if there is no parent identifier, and only a single subagent yielded identified messages, pull that in.
Microsoft Agent Framework
Welcome to the Private Preview of Agent Framework!
You're getting early access to Microsoft's comprehensive multi-language framework for building, orchestrating, and deploying AI agents with support for both .NET and Python implementations. This framework provides everything from simple chat agents to complex multi-agent workflows with graph-based orchestration.
📋 Important Setup Information
Package Availability: Public PyPI and NuGet packages are not yet available. You have two options:
Option 1: Run samples directly from this repository (no package installation needed)
- Clone this repository
- For .NET: Run samples with
dotnet runfrom any sample directory (e.g.,dotnet/samples/GettingStarted/Agents/Agent_Step01_Running) - For Python: Run samples from any sample directory (e.g.,
python/samples/getting_started/minimal_sample.py) after setting up the local dev environment following this guide.
Option 2: Install packages in your own project
- .NET Getting Started Guide - Instructions for using nightly packages
- Python Package Installation Guide - Install packages directly from GitHub
Stay Updated: This is an active project - sync your local repository regularly to get the latest updates.
💬 We want your feedback!
- For bugs, please file a GitHub issue.
- For feedback and suggestions for the team, please fill out this survey.
✨ Highlights
- Flexible Agent Framework: build, orchestrate, and deploy AI agents and workflows
- Multi-Agent Orchestration: group chat, sequential, concurrent, and handoff patterns
- Graph-based Workflows: connect agents and deterministic functions using data flows with streaming, checkpointing, time-travel, and Human-in-the-loop.
- Plugin Ecosystem: extend with native functions, OpenAPI, Model Context Protocol (MCP), and more
- LLM Support: OpenAI, Azure OpenAI, Azure AI Foundry, and more
- Runtime Support: in-process and distributed agent execution
- Multimodal: text, vision, and function calling
- Cross-Platform: .NET and Python implementations
Below are the basics for each language implementation. For more details on python see here and for .NET see here.
More Examples & Samples
Python
- Getting Started with Agents: basic agent creation and tool usage
- Chat Client Examples: direct chat client usage patterns
- Azure Integration: Azure OpenAI and AI Foundry integration
- Getting Started with Workflows: basic workflow creation and integration with agents
.NET
- Getting Started with Agents: basic agent creation and tool usage
- Agent Provider Samples: samples showing different agent providers
- Orchestration Samples: advanced multi-agent patterns
Agent Framework Documentation
- Python documentation
- DotNet documentation
- Agent Framework Repository
- Design Documents
- Architectural Decision Records
- Learn docs are coming soon.