AG2 (formerly AutoGen) is an open-source multi-agent AI framework maintained by the original creators of Microsoft AutoGen.¹⁾ Licensed under Apache 2.0 with 4.3K+ GitHub stars, AG2 brands itself as “The Open-Source AgentOS”, providing a stable, community-driven platform for building conversational AI agent systems without the breaking changes introduced by Microsofts AutoGen 0.4 rewrite.

AG2 forked from Microsoft AutoGen v0.2.34 when Microsoft began a complete architectural rewrite (AutoGen 0.4) that shifted toward async messaging, TypeScript support, and Semantic Kernel integration. The original creators, Chi Wang and Qingyun Wu, established AG2 to preserve the familiar, battle-tested agent patterns while evolving the framework through community-driven development with an open RFC process.²⁾

Key features:

• Multi-agent conversations, Flexible patterns from two-agent chats to complex group discussions with LLM-selected speaker rotation
• ConversableAgent, Base agent class with built-in LLM integration, tool use, code execution, and configurable termination conditions
• GroupChat, Orchestrates multi-agent collaboration with automatic speaker selection and message routing
• Code execution, Agents can generate and execute code in sandboxed environments
• Tool integration, Pluggable tools, memory modules, and external API access
• Full backward compatibility, Existing AutoGen 0.2 code runs without modification

Two-agent conversation:

from [[autogen|autogen]] import ConversableAgent, config_list_from_json
 
# Load LLM config (supports [[openai|OpenAI]], Azure, local models)
config_list = config_list_from_json("OAI_CONFIG_LIST")
llm_config = {"config_list": config_list, "temperature": 0}
 
# Create a user proxy that can execute code
user_proxy = ConversableAgent(
    name="User",
    human_input_mode="NEVER",
    code_execution_config={"work_dir": "coding", "use_docker": True}
)
 
# Create an AI assistant
assistant = ConversableAgent(
    name="Assistant",
    llm_config=llm_config,
    system_message="You are a helpful data analyst. Write Python code to solve tasks."
)
 
# Start conversation, agents chat until task is complete
user_proxy.initiate_chat(
    assistant,
    message="Analyze the top 10 Python packages by downloads and create a bar chart."
)

GroupChat with multiple specialized agents:

from [[autogen|autogen]] import ConversableAgent, GroupChat, GroupChatManager
 
llm_config = {"config_list": config_list, "temperature": 0}
 
# Define specialized agents
planner = ConversableAgent(
    name="Planner",
    llm_config=llm_config,
    system_message="You break down tasks into steps. Do not write code."
)
 
engineer = ConversableAgent(
    name="Engineer",
    llm_config=llm_config,
    system_message="You write Python code to implement plans. Always include error handling."
)
 
critic = ConversableAgent(
    name="Critic",
    llm_config=llm_config,
    system_message="You review code for bugs, security issues, and improvements."
)
 
user_proxy = ConversableAgent(
    name="User_proxy",
    human_input_mode="NEVER",
    code_execution_config={"work_dir": "output"}
)
 
# Create group chat, LLM selects next speaker
groupchat = GroupChat(
    agents=[user_proxy, planner, engineer, critic],
    messages=[],
    max_round=12
)
manager = GroupChatManager(groupchat=groupchat, llm_config=llm_config)
 
user_proxy.initiate_chat(
    manager,
    message="Build a REST API that serves stock price predictions."
)

AG2 is installable under multiple package names (all point to the same codebase):

pip install ag2
# or
pip install pyautogen
# or
pip install [[autogen|autogen]]

• v0.10.x, Gemini Thinking Configuration for enhanced reasoning control
• MCP support, Model Context Protocol integration for tool interoperability⁴⁾
• A2A protocol, Agent-to-Agent communication standard support
• AG2 Studio, Visual prototyping interface (in development)

• AutoGen Studio
• AutoGen
• AG-UI Protocol
• Azure AI
• ARC-AGI