Getting Started

AG2 (formerly AutoGen) is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks. AG2 aims to provide an easy-to-use and flexible framework for accelerating development and research on agentic AI, like PyTorch for Deep Learning. It offers features such as agents that can converse with other agents, LLM and tool use support, autonomous and human-in-the-loop workflows, and multi-agent conversation patterns.

​

Main Features

• AG2 enables building next-gen LLM applications based on multi-agent conversations with minimal effort. It simplifies the orchestration, automation, and optimization of a complex LLM workflow. It maximizes the performance of LLM models and overcomes their weaknesses.
• It supports diverse conversation patterns for complex workflows. With customizable and conversable agents, developers can use AG2 to build a wide range of conversation patterns concerning conversation autonomy, the number of agents, and agent conversation topology.
• It provides a collection of working systems with different complexities. These systems span a wide range of applications from various domains and complexities. This demonstrates how AG2 can easily support diverse conversation patterns.

AG2 is powered by collaborative research studies from Microsoft, Penn State University, and University of Washington.

​

Quickstart

pip install autogen

• No code execution
• Local execution
• Docker execution

import os
from autogen import AssistantAgent, UserProxyAgent

llm_config = {"model": "gpt-4", "api_key": os.environ["OPENAI_API_KEY"]}
assistant = AssistantAgent("assistant", llm_config=llm_config)
user_proxy = UserProxyAgent("user_proxy", code_execution_config=False)

# Start the chat
user_proxy.initiate_chat(
    assistant,
    message="Tell me a joke about NVDA and TESLA stock prices.",
)

​

Multi-Agent Conversation Framework

AG2 enables the next-gen LLM applications with a generic multi-agent conversation framework. It offers customizable and conversable agents which integrate LLMs, tools, and humans. By automating chat among multiple capable agents, one can easily make them collectively perform tasks autonomously or with human feedback, including tasks that require using tools via code. For example,

The figure below shows an example conversation flow with AG2.

​

Where to Go Next?

• Go through the tutorial to learn more about the core concepts in AG2
• Read the examples and guides in the notebooks section
• Understand the use cases for multi-agent conversation and enhanced LLM inference
• Read the API docs
• Learn about research around AG2
• Chat on Discord
• Follow on Twitter
• See our roadmaps

If you like our project, please give it a star on GitHub. If you are interested in contributing, please read Contributor’s Guide.