An open, multi-language framework for building and orchestrating production-grade AI agents and multi-agent workflows across Python and .NET. It supports graph-based workflows with sequential, concurrent, and group collaboration patterns, requiring developers to write code and configure authentication.
Project overview
The framework provides a consistent foundation for orchestrating complex multi-agent systems and offers provider flexibility alongside hosting options.
Project type
AI Agent · Workflow
Use cases
Automation
Deployment
Refer to project documentation
License
MIT
Best for
Developers and AI engineers building production-grade multi-agent systems who need provider flexibility and code-based orchestration.
Key capabilities
Build multi-agent systems with graph-based workflows supporting sequential, concurrent, handoff, and group collaboration patterns, including checkpointing, streaming, human-in-the-loop, and time-travel.
Limitations and risks
Using DefaultAzureCredential in production may lead to latency issues, unintended credential probing, and potential security risks.
Defining and running agents requires writing code; it is not a no-code solution.
Getting started
Installation is considered medium difficulty. Users install the framework via pip or dotnet, configure environment variables for credentials and model deployments, write code to define an agent, and execute the script.
Alternatives and comparisons
Provides a visual authoring experience to quickly get started and iterate on AI workflows.
Build and operationalize AI workflows and multi-step agents using your own data, models, and tools.
An intuitive, low-code interface allowing users to design and configure their own AI agents.
GitHub project description: A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
README: Microsoft Agent Framework (MAF) is an open, multi-language framework for building **production-grade AI agents and multi-agent workflows** in **.NET and Python**.
README: MAF is a strong fit if you: - are building agents and workflows you expect to run in production, - need orchestration beyond a single prompt or stateless chat loop,
README: **Orchestration Patterns & Workflows**: Build multi-agent systems with graph-based workflows supporting sequential, concurrent, handoff, and group collaboration patterns; includes…