Overview
AutoGen is a framework that enables the creation of AI agents that can converse with each other to solve tasks. Multiple agents collaborate to achieve complex goals.
Key Features
- Multi-Agent Conversations: Agents talk to each other
- Human-in-the-Loop: Human oversight option
- Code Execution: Agents can run code
- Customizable Agents: Define agent roles
- Conversation Patterns: Various interaction modes
Quick Start
import autogen
config_list = [{"model": "gpt-4", "api_key": "your-key"}]
assistant = autogen.AssistantAgent("assistant", llm_config={"config_list": config_list})
user_proxy = autogen.UserProxyAgent("user_proxy", code_execution_config={"work_dir": "coding"})
user_proxy.initiate_chat(assistant, message="Plot a chart of stock prices")
Use Cases
- Software development teams
- Research collaboration
- Complex problem solving
- Automated workflows
Resources
Source: GitHub