AutoGen Multi-Agent Framework Cheat Sheet

Overview

AutoGen is a groundbreaking open-source framework developed by Microsoft Research that revolutionizes the development of Large Language Model (LLM) applications by enabling sophisticated multi-agent conversations. Unlike traditional single-agent systems, AutoGen allows developers to create complex applications by composing multiple specialized AI agents that can converse with each other, collaborate on tasks, and even involve humans in the loop seamlessly.

What makes AutoGen particularly powerful is its emphasis on conversation as the primary mechanism for agent interaction. This approach allows for natural, flexible, and dynamic collaboration between agents, mirroring how human teams work together to solve complex problems. AutoGen provides a rich set of tools for defining agent roles, capabilities, and communication protocols, making it possible to build highly adaptable and intelligent systems that can tackle a wide range of tasks, from code generation and data analysis to creative writing and strategic planning.

The framework is designed for both simplicity and extensibility, offering high-level abstractions for common multi-agent patterns while also providing deep customization options for advanced use cases. With its event-driven architecture and support for diverse LLMs and tools, AutoGen empowers developers to build next-generation AI applications that are more capable, robust, and human-aligned than ever before.

Installation and Setup

Basic Installation

# Install AutoGen
pip install pyautogen

# Install with specific integrations (e.g., OpenAI)
pip install "pyautogen[openai]"

# Install development version
pip install git+https://github.com/microsoft/autogen.git

# Install with all optional dependencies
pip install "pyautogen[all]"

Environment Configuration

import os
import autogen

# Configure LLM provider (OpenAI example)
config_list_openai = [
    {
        "model": "gpt-4",
        "api_key": os.environ.get("OPENAI_API_KEY")
    },
    {
        "model": "gpt-3.5-turbo",
        "api_key": os.environ.get("OPENAI_API_KEY")
    }
]

# Configure for other LLMs (e.g., Azure OpenAI, local models)
# See AutoGen documentation for specific configurations

# Set up logging
autogen.ChatCompletion.set_cache(seed=42) # For reproducibility

Project Structure

autogen_project/
├── agents/
│   ├── __init__.py
│   ├── researcher_agent.py
│   └── coder_agent.py
├── workflows/
│   ├── __init__.py
│   ├── coding_workflow.py
│   └── research_workflow.py
├── tools/
│   ├── __init__.py
│   └── custom_tools.py
├── skills/
│   ├── __init__.py
│   └── code_execution_skill.py
├── config/
│   ├── __init__.py
│   └── llm_config.py
└── main.py

Core Concepts

Agents

Agents are the fundamental building blocks in AutoGen. They are conversational entities that can send and receive messages, execute code, call functions, and interact with humans.

ConversableAgent

This is the base class for most agents in AutoGen, providing core conversational capabilities.

UserProxyAgent

A specialized agent that acts as a proxy for human users, allowing them to participate in conversations, provide input, and execute code.

AssistantAgent

An agent designed to act as an AI assistant, typically powered by an LLM, capable of writing code, answering questions, and performing tasks.

GroupChat

AutoGen supports multi-agent conversations through GroupChat and GroupChatManager, enabling complex interactions between multiple agents.

Agent Configuration

Basic Agent Creation

import autogen

# Assistant Agent (LLM-powered)
assistant = autogen.AssistantAgent(
    name="Assistant",
    llm_config={
        "config_list": config_list_openai,
        "temperature": 0.7,
        "timeout": 600
    },
    system_message="You are a helpful AI assistant. Provide concise and accurate answers."
)

# User Proxy Agent (Human in the loop)
user_proxy = autogen.UserProxyAgent(
    name="UserProxy",
    human_input_mode="TERMINATE",  # Options: ALWAYS, TERMINATE, NEVER
    max_consecutive_auto_reply=10,
    is_termination_msg=lambda x: x.get("content", "").rstrip().endswith("TERMINATE"),
    code_execution_config={
        "work_dir": "coding_output",
        "use_docker": False  # Set to True to use Docker for code execution
    },
    system_message="A human user. Reply TERMINATE when the task is done or if you want to stop."
)

Advanced Agent Customization

import autogen

# Agent with custom reply function
def custom_reply_func(messages, sender, config):
    last_message = messages[-1]["content"]
    if "hello" in last_message.lower():
        return "Hello there! How can I help you today?"
    return "I received your message."

custom_agent = autogen.ConversableAgent(
    name="CustomAgent",
    llm_config=False,  # No LLM for this agent
    reply_func_list=[custom_reply_func]
)

# Agent with specific skills (function calling)
@autogen.register_function(
    name="get_stock_price",
    description="Get the current stock price for a given symbol.",
    parameters={"symbol": {"type": "string", "description": "Stock symbol"}}
)
def get_stock_price(symbol: str) -> str:
    # Implement stock price retrieval logic
    return f"The price of {symbol} is $150."

stock_analyst_agent = autogen.AssistantAgent(
    name="StockAnalyst",
    llm_config={
        "config_list": config_list_openai,
        "functions": [autogen.AssistantAgent.construct_function_description(get_stock_price)]
    },
    function_map={"get_stock_price": get_stock_price}
)

Specialized Agent Types

import autogen

# TeachableAgent for learning from feedback
teachable_agent = autogen.TeachableAgent(
    name="TeachableAnalyst",
    llm_config={"config_list": config_list_openai},
    teach_config={
        "verbosity": 0,  # 0 for no teaching, 1 for normal, 2 for detailed
        "reset_db": False, # Set to True to clear previous learnings
        "path_to_db_dir": "./teachable_agent_db"
    }
)

# RetrieveUserProxyAgent for RAG (Retrieval Augmented Generation)
rag_agent = autogen.retrieve_chat.RetrieveUserProxyAgent(
    name="RAGAgent",
    human_input_mode="TERMINATE",
    retrieve_config={
        "task": "qa",
        "docs_path": "./documents_for_rag",
        "chunk_token_size": 2000,
        "model": config_list_openai[0]["model"],
        "collection_name": "rag_collection",
        "get_or_create": True
    }
)

Agent Conversations

Two-Agent Chat

import autogen

# Initiate chat between user_proxy and assistant
user_proxy.initiate_chat(
    assistant,
    message="What is the capital of France?",
    summary_method="reflection_with_llm", # For summarizing conversation history
    max_turns=5
)

# Example with code execution
user_proxy.initiate_chat(
    assistant,
    message="Write a Python script to print numbers from 1 to 5 and run it."
)

Group Chat with Multiple Agents

import autogen

# Define agents for group chat
planner = autogen.AssistantAgent(
    name="Planner",
    llm_config={"config_list": config_list_openai},
    system_message="You are a project planner. Create detailed plans for tasks."
)

engineer = autogen.AssistantAgent(
    name="Engineer",
    llm_config={"config_list": config_list_openai},
    system_message="You are a software engineer. Implement the plans provided."
)

reviewer = autogen.AssistantAgent(
    name="Reviewer",
    llm_config={"config_list": config_list_openai},
    system_message="You are a code reviewer. Review the implemented code for quality."
)

# Create group chat and manager
group_chat = autogen.GroupChat(
    agents=[user_proxy, planner, engineer, reviewer],
    messages=[],
    max_round=12,
    speaker_selection_method="auto" # auto, round_robin, random, manual
)

manager = autogen.GroupChatManager(
    groupchat=group_chat,
    llm_config={"config_list": config_list_openai}
)

# Initiate group chat
user_proxy.initiate_chat(
    manager,
    message="Develop a Python script to calculate Fibonacci numbers up to n."
)

Advanced Conversation Control

import autogen

# Custom speaker selection
def custom_speaker_selector(last_speaker, groupchat):
    if last_speaker is user_proxy:
        return planner
    elif last_speaker is planner:
        return engineer
    elif last_speaker is engineer:
        return reviewer
    else:
        return user_proxy

custom_group_chat = autogen.GroupChat(
    agents=[user_proxy, planner, engineer, reviewer],
    messages=[],
    speaker_selection_method=custom_speaker_selector
)

# Nested chats
def initiate_nested_chat(recipient, message):
    user_proxy.initiate_chat(recipient, message=message, clear_history=False)

# Example of agent calling nested chat
class MainAgent(autogen.AssistantAgent):
    def generate_reply(self, messages, sender, **kwargs):
        # ... logic ...
        if needs_specialized_help:
            initiate_nested_chat(specialist_agent, "Need help with this sub-task.")
            # ... process specialist_agent response ...
        return "Main task processed."

Tool and Function Integration

Using Built-in Tools

AutoGen doesn_t have a large set of pre-built tools like some other frameworks. Instead, it focuses on enabling agents to execute code (Python scripts, shell commands) which can then interact with any library or tool available in the execution environment.

Custom Function Calling (Skills)

import autogen

# Define a function (skill)
@autogen.register_function
def get_weather(location: str) -> str:
    """Get the current weather for a given location."""
    # Replace with actual API call
    if location == "London":
        return "Weather in London is 15°C and cloudy."
    elif location == "Paris":
        return "Weather in Paris is 18°C and sunny."
    else:
        return f"Weather data not available for {location}."

# Agent that can use the function
weather_assistant = autogen.AssistantAgent(
    name="WeatherAssistant",
    llm_config={
        "config_list": config_list_openai,
        "functions": [autogen.AssistantAgent.construct_function_description(get_weather)]
    },
    function_map={"get_weather": get_weather}
)

# User proxy to trigger function call
user_proxy.initiate_chat(
    weather_assistant,
    message="What is the weather in London?"
)

Code Execution

import autogen

# UserProxyAgent is configured for code execution by default
# Ensure `code_execution_config` is set appropriately

# Example: Agent asks UserProxyAgent to execute code
coder_agent = autogen.AssistantAgent(
    name="Coder",
    llm_config={"config_list": config_list_openai}
)

user_proxy.initiate_chat(
    coder_agent,
    message="Write a Python script that creates a file named 'test.txt' with content 'Hello AutoGen!' and then execute it."
)
# UserProxyAgent will prompt for confirmation before executing the code.

Human-in-the-Loop (HIL)

Configuring Human Input

import autogen

# UserProxyAgent configured for human input
hil_user_proxy = autogen.UserProxyAgent(
    name="HumanReviewer",
    human_input_mode="ALWAYS",  # ALWAYS: Human input required for every message
                               # TERMINATE: Human input required if no auto-reply, or to terminate
                               # NEVER: No human input (fully autonomous)
    is_termination_msg=lambda x: x.get("content", "").rstrip() == "APPROVE"
)

# Example workflow with human review
planner = autogen.AssistantAgent(name="Planner", llm_config=llm_config)
executor = autogen.AssistantAgent(name="Executor", llm_config=llm_config)

groupchat_with_review = autogen.GroupChat(
    agents=[hil_user_proxy, planner, executor],
    messages=[],
    max_round=10
)
manager_with_review = autogen.GroupChatManager(
    groupchat=groupchat_with_review, llm_config=llm_config
)

hil_user_proxy.initiate_chat(
    manager_with_review,
    message="Plan and execute a task to summarize a long document. I will review the plan and the final summary."
)

Asynchronous Human Input

AutoGen primarily handles HIL synchronously within the conversation flow. For more complex asynchronous HIL, you would typically integrate with external task management or UI systems.

Advanced Features

Teachable Agents

import autogen

# Setup TeachableAgent
teachable_coder = autogen.TeachableAgent(
    name="TeachableCoder",
    llm_config={"config_list": config_list_openai},
    teach_config={
        "verbosity": 1,
        "reset_db": False,
        "path_to_db_dir": "./teachable_coder_db",
        "recall_threshold": 1.5,  # Higher value means less recall
    }
)

# User teaches the agent
user_proxy.initiate_chat(
    teachable_coder,
    message="When I ask for a quick sort algorithm, always implement it in Python using a recursive approach."
)

# Later, the agent uses the learned information
user_proxy.initiate_chat(
    teachable_coder,
    message="Implement a quick sort algorithm."
)

# To clear learnings:
# teachable_coder.clear_mem L() # For in-memory (if not using DB)
# Or set teach_config["reset_db"] = True and re-initialize

Retrieval Augmented Generation (RAG)

import autogen
from autogen.agentchat.contrib.retrieve_assistant_agent import RetrieveAssistantAgent

# Ensure you have a directory with documents (e.g., ./my_documents)
# Supported formats: .txt, .md, .pdf, .html, .htm, .json, .jsonl, .csv, .tsv, .xls, .xlsx, .doc, .docx, .ppt, .pptx, .odt, .rtf, .epub

# Create a RetrieveAssistantAgent (combines LLM with retrieval)
retrieval_assistant = RetrieveAssistantAgent(
    name="RetrievalAssistant",
    system_message="You are a helpful assistant that answers questions based on provided documents.",
    llm_config={"config_list": config_list_openai}
)

# Create a RetrieveUserProxyAgent to handle document processing and querying
rag_user_proxy = autogen.retrieve_chat.RetrieveUserProxyAgent(
    name="RAGUserProxy",
    human_input_mode="TERMINATE",
    max_consecutive_auto_reply=5,
    retrieve_config={
        "task": "qa",  # Can be "qa", "code", "chat"
        "docs_path": "./my_documents", # Path to your documents
        "chunk_token_size": 2000,
        "model": config_list_openai[0]["model"],
        "collection_name": "my_rag_collection",
        "get_or_create": True, # Creates collection if it doesn_t exist
        "embedding_model": "all-mpnet-base-v2" # Example sentence transformer model
    },
    code_execution_config=False
)

# Initiate RAG chat
# The RAGUserProxy will first try to answer from documents, then pass to RetrievalAssistant if needed.
rag_user_proxy.initiate_chat(
    retrieval_assistant,
    problem="What are the main features of AutoGen according to the documents?"
)

# To update or add new documents, you might need to re-index or manage the collection.
# rag_user_proxy.retrieve_config["update_context"] = True (for some RAG setups)

Multi-Modal Conversations

AutoGen supports multi-modal inputs (e.g., images) if the underlying LLM supports it (like GPT-4V).

import autogen

# Ensure your config_list points to a multimodal LLM (e.g., gpt-4-vision-preview)
multimodal_config_list = [
    {
        "model": "gpt-4-vision-preview",
        "api_key": os.environ.get("OPENAI_API_KEY")
    }
]

multimodal_agent = autogen.AssistantAgent(
    name="MultimodalAgent",
    llm_config={"config_list": multimodal_config_list}
)

# Example message with an image URL
user_proxy.initiate_chat(
    multimodal_agent,
    message=[
        {"type": "text", "text": "What is in this image?"},
        {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
    ]
)

# Example with local image (requires proper handling to make it accessible to the LLM)
# This might involve uploading the image or using a local multimodal LLM setup.
# For local images with OpenAI, you typically need to base64 encode them.
import base64

def image_to_base64(image_path):
    with open(image_path, "rb") as img_file:
        return base64.b64encode(img_file.read()).decode("utf-8")

local_image_path = "./path_to_your_image.png"
base64_image = image_to_base64(local_image_path)

user_proxy.initiate_chat(
    multimodal_agent,
    message=[
        {"type": "text", "text": "Describe this local image:"},
        {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{base64_image}"}}
    ]
)

Agent Workflow Patterns

Reflection and Self-Correction

import autogen

# Agent that reflects on its own output
self_reflecting_agent = autogen.AssistantAgent(
    name="Reflector",
    llm_config={"config_list": config_list_openai},
    system_message="You are an AI that writes code. After writing code, reflect on its quality and correctness. If you find issues, try to correct them."
)

# User proxy to facilitate reflection
reflection_user_proxy = autogen.UserProxyAgent(
    name="ReflectionProxy",
    human_input_mode="NEVER",
    max_consecutive_auto_reply=3, # Allow a few turns for reflection
    # Custom message to trigger reflection or provide feedback
    # This often involves a more complex setup where the proxy or another agent critiques the output.
)

# This pattern is often implemented with a sequence of chats or a GroupChat
# where one agent produces work and another critiques it, then the first agent revises.

# Simplified example:
user_proxy.initiate_chat(
    self_reflecting_agent,
    message="Write a Python function to calculate factorial. Then, review your code for potential bugs or improvements and provide a revised version if necessary."
)

Hierarchical Agent Teams

This is typically achieved using GroupChatManager where one agent (e.g., a manager or planner) coordinates other specialized agents.

import autogen

# Manager Agent
manager_agent = autogen.AssistantAgent(
    name="Manager",
    llm_config={"config_list": config_list_openai},
    system_message="You are a project manager. Delegate tasks to your team (Engineer, Researcher) and synthesize their results."
)

# Specialist Agents
engineer_agent = autogen.AssistantAgent(name="Engineer", llm_config=llm_config)
researcher_agent = autogen.AssistantAgent(name="Researcher", llm_config=llm_config)

# Group Chat for the team
team_groupchat = autogen.GroupChat(
    agents=[user_proxy, manager_agent, engineer_agent, researcher_agent],
    messages=[],
    max_round=15,
    # Manager agent can be set to speak or select next speaker
    speaker_selection_method=lambda last_speaker, groupchat: manager_agent if last_speaker != manager_agent else user_proxy # Simplified example
)

team_manager = autogen.GroupChatManager(
    groupchat=team_groupchat, llm_config=llm_config
)

user_proxy.initiate_chat(
    team_manager,
    message="Develop a new feature for our app that requires research on user needs and then engineering implementation."
)

Best Practices

Agent Design

• Clear Roles: Define specific, unambiguous roles and responsibilities for each agent.
• System Messages: Use detailed system messages to guide agent behavior and persona.
• Tool Access: Provide agents only with the tools they need for their role.
• LLM Configuration: Tailor LLM temperature, model, and other settings per agent for optimal performance.

Conversation Management

• Termination Conditions: Clearly define when a conversation or task is complete.
• Max Turns/Rounds: Set limits to prevent infinite loops or excessive costs.
• Speaker Selection: Choose appropriate speaker selection methods for group chats (auto, round_robin, custom).
• Summarization: Use conversation summarization for long-running chats to manage context window.

Code Execution Security

• Sandboxing: Use Docker (use_docker=True in code_execution_config) for safer code execution, especially with untrusted code.
• Human Review: Implement human review (human_input_mode="ALWAYS" or "TERMINATE") before executing potentially risky code.
• Restricted Environments: If not using Docker, ensure the execution environment has limited permissions.

Cost Management

• Model Selection: Use less expensive models (e.g., GPT-3.5-turbo) for simpler tasks or agents.
• Max Tokens/Turns: Limit the length of conversations and LLM outputs.
• Caching: Use autogen.ChatCompletion.set_cache() to cache LLM responses and reduce redundant calls.
• Monitoring: Track token usage and API costs closely.

Debugging

• Verbose Logging: AutoGen provides logging; increase verbosity for debugging.
• Step-by-Step Execution: For complex group chats, consider manual speaker selection or breakpoints to understand flow.
• Agent Isolation: Test agents individually before integrating them into larger groups.

Troubleshooting

Common Issues

Agents Stuck in Loops

• Cause: Vague termination conditions, conflicting agent goals, or overly complex interactions.
• Solution: Refine is_termination_msg lambda, simplify agent instructions, set max_consecutive_auto_reply or max_round limits.

Unexpected Agent Behavior

• Cause: Ambiguous system messages, LLM misinterpretations, or incorrect LLM configurations.
• Solution: Make system messages more specific, experiment with different LLM temperatures, ensure correct function/tool descriptions.

Code Execution Failures

• Cause: Missing dependencies in the execution environment, incorrect code generated by LLM, permission issues.
• Solution: Ensure all necessary packages are installed (or use Docker), improve prompts for code generation, check file/network permissions.

Function Calling Problems

• Cause: Incorrect function descriptions provided to LLM, bugs in the custom function code, LLM failing to generate valid JSON for arguments.
• Solution: Ensure function descriptions are clear and match parameters, test custom functions thoroughly, refine prompts to guide LLM towards correct JSON format.

---

This AutoGen cheat sheet provides a comprehensive guide to building sophisticated multi-agent AI applications. By leveraging AutoGen_s conversational framework, developers can create highly capable and collaborative AI systems. Remember to consult the official AutoGen documentation for the latest features and detailed API references.