agent/agent-framework
2
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: refine README intro paragraph

Browse Source
This commit is contained in:
Chetan Toshniwal
2026-04-29 13:07:31 -07:00
Unverified
parent 668862caf9
commit c8ff0e344b
1 changed files with 1 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -13
View File
@@ -11,16 +11,7 @@
Microsoft Agent Framework (MAF) is an open, multi-language framework for building **production-grade AI agents and multi-agent workflows** in **.NET and Python**.
It is designed for teams moving beyond prototypes who need:
- a consistent agent programming model with tools, middleware, and provider flexibility,
- graph-based workflows with checkpointing, streaming, human-in-the-loop, and time-travel,
- durable and restartable execution for long-running, stateful orchestration,
- interoperable architectures through MCP and Agent-to-Agent (A2A) communication,
- built-in observability and tracing with OpenTelemetry,
- and practical paths to test, host, and operate agents in real production systems.
MAF supports a broad ecosystem including Microsoft Foundry, Azure OpenAI, OpenAI, and the GitHub Copilot SDK, with samples and hosting patterns for both local development and cloud deployment.
Microsoft Agent Framework is built for teams taking agents from prototype to production. It provides a consistent foundation for building, orchestrating, and operating agent systems across Python and .NET, while keeping architecture choices open as requirements evolve, and supports a broad ecosystem including Microsoft Foundry, Azure OpenAI, OpenAI, and the GitHub Copilot SDK, with samples and hosting patterns for both local development and cloud deployment.
<p align="center">
<a href="https://www.youtube.com/watch?v=AAgdMhftj8w" title="Watch the full Agent Framework introduction (30 min)">
@@ -43,9 +34,6 @@ MAF is a strong fit if you:
- care about durability, restartability, observability, governance, or human-in-the-loop control,
- need provider flexibility so your architecture can evolve without major rewrites.
If your scope is limited to experimentation or simple single-prompt chatbots,
MAF may be more than what you need today. It is intentionally designed for systems where agent behavior, reliability, and operational needs grow over time.
## Key Features
Explore new MAF capabilities and real implementation patterns on the [official blog](https://devblogs.microsoft.com/agent-framework/).