README.md
AutoGen is a framework for building LLM apps from multiple agents that converse to solve tasks, with support for tool use, human participation and flexible conversation patterns.
pip install autogen-agentchat
Explore / AutoGen
microsoft
AutoGen
Multi-agent conversation framework for building LLM applications with cooperating agents.
60,533 9,127 Python CC-BY-4.0updated 4 months ago
Continue your stack
What teams reach for next — and why each earns a place beside AutoGen. Ranked by curator confidence.
Pairs well with
Ragas
Evaluation toolkit for your RAG and agent pipelines — faithfulness, relevance, and more.
Why it fitsScore the outputs of your multi-agent conversations for faithfulness and relevance.
CubeSandbox
Hardware-isolated microVM sandboxes for AI agents — sub-60ms boot, <5MB overhead, E2B-compatible API, self-hosted on your own KVM nodes.
Why it fitsAutoGen's code-executor step is the canonical sandbox case: run generated Python in an isolated microVM instead of on the host or a shared container.
Alternative to See all + compare →
CrewAI
Orchestrate role-playing, autonomous AI agents that collaborate on tasks.
Why it fitsBoth do multi-agent collaboration; CrewAI is more opinionated about roles, AutoGen about conversation.
MetaGPT
The original "AI software company" multi-agent framework — role-assigned agents (PM, architect, engineer) turn a one-line requirement into PRD, design, and code.
Why it fitsSame job — multi-agent LLM apps — opposite philosophy: AutoGen is a conversation substrate you shape freely; MetaGPT hard-codes the workflow as company SOPs.
PraisonAI
Low-code multi-agent framework: autonomous agents with built-in memory, RAG and MCP support across 100+ LLMs — from one agent to an 'AI workforce' in a few lines or YAML.
Why it fitsBoth orchestrate cooperating agents; AutoGen is the research-grade conversation framework, PraisonAI the low-code productized bundle.