AutoGen
by Various
A programming framework for agentic AI
Apps
AutoGen
Added 1 June 2026
Overview
AutoGen is a Python framework for building multi-agent systems where LLM-powered agents collaborate to solve tasks through conversation and code execution. Agents can be customized with different roles, tools, and conversation patterns to orchestrate complex workflows.
Best for
Best for
Developers building multi-agent systems in Python who need structured agent orchestration and code execution capabilities.
Use cases
- Building conversational AI systems where multiple agents debate or collaborate on solutions
- Automating multi-step workflows that require reasoning, code generation, and execution
- Prototyping agentic applications without managing low-level orchestration logic
Notes
AutoGen is a Python framework for building multi-agent systems where LLM-powered agents collaborate to solve tasks through conversation and code execution. Agents can be customized with different roles, tools, and conversation patterns to orchestrate complex workflows.
58,610 stars on GitHub. Last updated 2026-04-15. Licensed CC-BY-4.0.
Use cases
- Building conversational AI systems where multiple agents debate or collaborate on solutions
- Automating multi-step workflows that require reasoning, code generation, and execution
- Prototyping agentic applications without managing low-level orchestration logic
Pros
- Handles agent communication and state management, reducing boilerplate for multi-agent setups
- Supports code execution within agent loops for grounding outputs in real computation
- Active open-source project with substantial community adoption (58k+ stars)
Cons
- Requires Python and familiarity with agent design patterns, steeper learning curve than single-agent frameworks
- Performance and cost scale with number of agents and conversation turns, can become expensive with large models
- Limited built-in observability and debugging tools for complex multi-agent interactions
Indexed from awesome-generative-ai and enriched against its public facts.
Pros
- Handles agent communication and state management, reducing boilerplate for multi-agent setups
- Supports code execution within agent loops for grounding outputs in real computation
- Active open-source project with substantial community adoption (58k+ stars)
Cons
- Requires Python and familiarity with agent design patterns, steeper learning curve than single-agent frameworks
- Performance and cost scale with number of agents and conversation turns, can become expensive with large models
- Limited built-in observability and debugging tools for complex multi-agent interactions
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
awesome-llm-agents
Community
A curated list of awesome LLM agents frameworks.
OpenHands
All Hands AI
Open-source autonomous coding agent platform. Spins up a sandboxed dev environment, ships PRs end to end.
Playground
Community
Kadoa
Underlying paper - Generative Agents
Community
Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping t
dcostenco/prism-mcp
Various
The Mind Palace for AI Agents - HIPAA-hardened Cognitive Architecture with on-device LLM (prism-coder:7b), Hebbian learning, ACT-R spreading activation, adversarial evaluation, per
edobusy/agenthold
Various
Shared versioned state for multi-agent AI workflows. An MCP server.
elisymlabs/elisym
Various
Open infrastructure for AI agents to discover and pay each other
jamjet-labs/jamjet
Various
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
oxgeneral/agentnet
Various
Your agent has zero users. This fixes that. An agent-to-agent referral network where AI agents discover each other, cross-refer users, and earn credits. Available as an MCP server
rafapra3008/cervellaswarm
Various
Lingua Universale -- a verification language for AI agent protocols. Like mypy for multi-agent communication. 3696 tests, zero deps.
valado/pantheon-mcp
Various
A collection of AI agents
AgentsMesh
Community
The AI Agent Workforce Platform — where teams scale beyond headcount. Give every team member an AI agent squad.
ai-evaluation
Community
Evaluation Framework for all your AI related Workflows
Autochain
Community
AutoChain: Build lightweight, extensible, and testable LLM Agents
AutoGPT
Community
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
brood-box
Community
CLI tool for running coding agents inside hardware-isolated microVMs
ClevAgent
Community
Run AI agents inside a supervised terminal. ClevAgent adds guidance, visibility, and better execution to real agent work.
Code Interpreter API
Community
👾 Open source implementation of the ChatGPT Code Interpreter
Codel
Community
✨ Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor.
e2b
Community
Open-source, secure environment with real-world tools for enterprise-grade agents.
gotoHuman
Community
Approve and revise critical steps in your AI workflows. Ensure AI-generated content is on-brand, messages to customers are accurate, and high-stakes decisions are made by humans.
llama-agents
Community
Llama Agents + Workflows are an event-driven, async-first, step-based way to control the execution flow of AI applications like agents.
LLM Agents
Community
Build agents which are controlled by LLMs
Memary
Community
The Open Source Memory Layer For Autonomous Agents
OpenAI o3-mini
Community
Pushing the frontier of cost-effective reasoning.
Phidata
Community
Build, run, and manage agent platforms.
QWED
Community
AISecOps (AI Security Operations) framework for deterministic verification of AI systems. QWED verifies LLM outputs using math, logic, and symbolic execution — creating an auditabl
Rhesis
Community
The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root ca
Robocorp
Community
Create 🐍 Python AI Actions and 🤖 Automations, and deploy & operate them anywhere
TaskWeaver
Community
The first "code-first" agent framework for seamlessly planning and executing data analytics tasks.
Trigger.dev
Trigger.dev
Background jobs and long-running tasks for AI apps. Write functions, get durability, observability, and retries.
TutorGPT
Community
AI tutor powered by Theory-of-Mind reasoning
uAgents
Community
A fast and lightweight framework for creating decentralized agents with ease.
UQLM
Community
UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection
VisualWebArena
Community
Project webpage for the VisualWebArena paper.
Agent Skills
Various
A standardized way to give AI agents new capabilities and expertise.
AgentMail
Various
Give AI agents real email inboxes. Create, send, receive, and search messages via REST API — built for autonomous agents and agentic workflows.
Arena
Various
Run autonomous AI agents that browse, research, code, and complete real-world tasks. Compare agent workflows and frontier models with Arena.
Cleanlab
Various
Check every AI response in real time with guardrails. Cleanlab detects hallucinations, missing context, and other issues by scoring each output for trust and accuracy.
ElevenLabs
ElevenLabs
AI voice generation, cloning, and conversational voice agents. The default voice layer for the AI ecosystem.
EmailTriager
Various
EmailTriager is an AI assistant that automatically organizes your incoming emails and drafts ready to send replies in the background. Get started with one click.
Exa
Various
The Exa Web search API retrieves the best, realtime data from the web for your AI
GLM
Various
GLM-5: From Vibe Coding to Agentic Engineering
Hermes Agent
Various
An open-source agent that grows with you. Install it, give it your messaging accounts, and it becomes a persistent personal agent.
Jasper
Various
Orchestrate intelligent agents to run end-to-end marketing workflows delivering speed, control, and measurable impact.
Kimi
Various
Try Kimi K2.6 to build stunning, full-stack websites, use Agent Swarm for massive tasks, turn documents into reusable skills, and explore Claw Groups preview for agent teamwork.
Lindy
Lindy AI
No-code AI agents for ops, sales, and support. The Zapier of the agent era, with built-in conversation.
Luma Dream Machine
Various
Luma Agents are the force multiplier for your team. They plan, generate, iterate, and refine with full context across every stage of creative work.
moltbook
Various
A social network built exclusively for AI agents. Where AI agents share, discuss, and upvote. Humans welcome to observe.
OpenAI API
Various
Announcement of the OpenAI API for text-to-text general-purpose AI models based on GPT-3. OpenAI blog, June 11, 2020.
Pi
Various
A personalized AI platform available as a digital assistant.
Scale Spellbook
Various
Accelerate and scale Generative AI across your enterprise with the platform to transform your data into customized enterprise-ready Generative AI applications.
Vanna.ai
Various
Build AI agents that ship to production. User-scoped execution, rich UI components, and quota management built-in.
Wren AI
Various
Give AI agents the context to query business data correctly through the open context layer that gives AI agents grounded, governed memory, context, SQL across 20+ data sources, t
You.com
Various
Skip the groundwork with our AI-ready Web Search APIs, delivering advanced search capabilities to power your next product.
Docs
Community
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
GitHub
Community
Adala: Autonomous DAta (Labeling) Agent framework
Javascript version (being developed)
Community
Multi-agent simulation Javascript framework
Paper - ChatDev: Communicative Agents for Software Development
Community
Software development is a complex task that necessitates cooperation among multiple members with diverse skills. Numerous studies used deep learning to improve specific phases in
escapeboy/agent-fleet-o
Various
Open-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG workflows, 450+ MCP tools, human-in-the-loop approvals. Wor
rinadelph/Agent-MCP
Various
Agent-MCP is a framework for creating multi-agent systems that enables coordinated, efficient AI collaboration through the Model Context Protocol (MCP). The system is designed for
AgentsMesh
Community
The AI Agent Workforce Platform — where teams scale beyond headcount. Give every team member an AI agent squad.
AutoGPT
Community
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Phidata
Community
Build, run, and manage agent platforms.
Arena
Various
Run autonomous AI agents that browse, research, code, and complete real-world tasks. Compare agent workflows and frontier models with Arena.
Auto-GPT
Various
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
GLM
Various
GLM-5: From Vibe Coding to Agentic Engineering
Lindy
Lindy AI
No-code AI agents for ops, sales, and support. The Zapier of the agent era, with built-in conversation.
MetaGPT
Various
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
OpenAgents
Various
OpenAgents - AI Agent Networks for Open Collaboration
OpenHands
Various
🙌 OpenHands: AI-Driven Development
Vanna.ai
Various
Build AI agents that ship to production. User-scoped execution, rich UI components, and quota management built-in.