framework

AutoGen

by Microsoft

AutoGen is Microsoft Research's open-source multi-agent conversation framework that enables building complex agentic workflows through coordinated multi-agent conversations, tool-calling, and code execution. It supports orchestration of multiple LLM-powered agents (AssistantAgent, UserProxyAgent, GroupChat) that can collaborate autonomously to complete tasks. The project underwent a significant architectural rebrand to AG2 in late 2024, which caused fragmentation concerns and community criticism around production readiness.

7 Overall Score

Scores

Capability
8
Ease of Use
5
Documentation
6
Reliability
5
Value
9
Momentum
7

Details

Status
active
Pricing
open-source
Launch Date
2023-09
Website
https://github.com/microsoft/autogen
Last Updated
2026-03-15

Key Features

  • Multi-agent conversation orchestration with flexible agent roles
  • Tool/function calling and sandboxed code execution
  • GroupChat support for dynamic multi-agent collaboration
  • Support for multiple LLM backends (OpenAI, Azure, local models)
  • Stateful memory and human-in-the-loop workflows

Tech Stack

PythonOpenAI APIAzure OpenAIDockerasyncio