Skip to main content

Menu

LEVEL 0
0/5 XP
HomeAboutTopicsPricingMy VaultStats

Categories

πŸ€– Artificial Intelligence
☁️ Cloud and Infrastructure
πŸ’Ύ Data and Databases
πŸ’Ό Professional Skills
🎯 Programming and Development
πŸ”’ Security and Networking
πŸ“š Specialized Topics
HomeAboutTopicsPricingMy VaultStats
LEVEL 0
0/5 XP
GitHub
Β© 2026 CheatGridβ„’. All rights reserved.
Privacy PolicyTerms of UseAboutContact

AutoGen (Microsoft Multi-Agent Framework) Cheat Sheet

AutoGen (Microsoft Multi-Agent Framework) Cheat Sheet

Back to Generative AI
Updated 2026-05-21
Next Topic: Chain-of-Thought Reasoning Cheat Sheet

AutoGen is Microsoft's open-source Python framework for building multi-agent AI applications where LLM-powered agents collaborate through structured conversations to complete complex tasks. It sits at the intersection of agentic orchestration and LLM tooling, providing everything from a simple two-agent chat to distributed, event-driven systems spanning multiple processes. The key mental model: AutoGen agents are not autonomous executors β€” they are conversational actors whose behavior is shaped by system messages, registered tools, and termination conditions, making them composable and debuggable by design.

What This Cheat Sheet Covers

This topic spans 16 focused tables and 100 indexed concepts. Below is a complete table-by-table outline of this topic, spanning foundational concepts through advanced details.

Table 1: Core Agent Types (AutoGen 0.2)Table 2: Agent Initialization ParametersTable 3: LLM Configuration and Model ClientsTable 4: Conversation PatternsTable 5: GroupChat Speaker SelectionTable 6: Tool and Function RegistrationTable 7: Code ExecutionTable 8: AutoGen 0.4 Team Types (AgentChat)Table 9: Termination Conditions (AutoGen 0.4)Table 10: Swarm and Handoff PatternTable 11: GraphFlow and StateFlow (Advanced Workflows)Table 12: AutoGen Core β€” Event-Driven RuntimeTable 13: Memory and Context ManagementTable 14: AutoGen StudioTable 15: AutoGenBench Evaluation HarnessTable 16: Package Architecture and Version Guide

Table 1: Core Agent Types (AutoGen 0.2)

The three built-in agent classes in AutoGen 0.2 cover the majority of real-world use cases. Every more complex workflow is built by composing or subclassing these types, so understanding their default behaviors and parameters is the foundation of the entire framework.

TypeExampleDescription
ConversableAgent
agent = autogen.ConversableAgent(
name="agent",
llm_config={"config_list": cfg},
human_input_mode="NEVER")
Base class for all AutoGen agents; supports both LLM-based replies and code execution via register_reply(); all other agents are subclasses.
AssistantAgent
assistant = autogen.AssistantAgent(
name="assistant",
llm_config={"config_list": cfg})
LLM-powered agent preconfigured to write code and suggest fixes; does not execute code and does not request human input by default.
UserProxyAgent
proxy = autogen.UserProxyAgent(
name="user_proxy",
human_input_mode="NEVER",
code_execution_config={"work_dir": "coding"})
Proxy agent that auto-executes code blocks found in messages; solicits human input based on human_input_mode; can optionally use an LLM for replies.

More in Generative AI

  • Amazon Bedrock Cheat Sheet
  • Chain-of-Thought Reasoning Cheat Sheet
  • Advanced RAG Patterns and Optimization Cheat Sheet
  • CrewAI (Multi-Agent Framework) Cheat Sheet
  • LlamaIndex Cheat Sheet
  • pgvector for Postgres Vector Search Cheat Sheet
View all 95 topics in Generative AI