{
 "kind": "tool",
 "slug": "autogen-agentchat",
 "path": "tools/autogen-agentchat/",
 "name": "AutoGen AgentChat",
 "maker": null,
 "density": "basic",
 "crumbs": [
  [
   "Tools",
   "tools/"
  ],
  [
   "Agent, MCP and tool libraries",
   "tools/agent-libraries/"
  ]
 ],
 "lead": "Build multi-agent systems and teams with AutoGen agents for collaborative AI workflows.",
 "chips": [
  {
   "label": "Agent, MCP and tool libraries",
   "path": "tools/agent-libraries/"
  },
  {
   "label": "PYPI"
  }
 ],
 "primary": {
  "label": "Copy install command",
  "copy": "pip install autogen-agentchat"
 },
 "links": [],
 "track": "New versions, deprecation and license changes on your dashboard",
 "verdicts": [
  {
   "key": "license",
   "label": "License",
   "value": "MIT",
   "status": "yes",
   "sub": "Use it in paid apps",
   "quote": null,
   "note": "License from PyPI classifier.",
   "src": ""
  },
  {
   "key": "maint",
   "label": "Maintained",
   "value": "Not checked yet",
   "status": "unknown",
   "sub": null,
   "note": "",
   "src": ""
  },
  {
   "key": "pop",
   "label": "Used by agents' projects",
   "value": "4 projects",
   "status": "info",
   "sub": "#57 of 189 in its category",
   "note": "Dependency in 4 public GitHub projects set up for AI coding agents that we scanned (0.1%).",
   "src": null
  },
  {
   "key": "agent",
   "label": "Agent access",
   "value": "Install only",
   "status": "info",
   "sub": null,
   "note": "Agent skills for this library in the skills catalog; community skills are written by others, read them before you install.",
   "src": null
  }
 ],
 "vfoot": "From the package registry and GitHub, checked daily.",
 "blocks": [
  {
   "id": "overview",
   "nav": "Overview",
   "h2": "What AutoGen AgentChat does",
   "parts": [
    {
     "t": "prose",
     "text": "Build multi-agent systems and teams with AutoGen agents for collaborative AI workflows."
    }
   ]
  },
  {
   "id": "popularity",
   "nav": "Popularity",
   "h2": "AutoGen AgentChat popularity",
   "parts": [
    {
     "t": "stats",
     "items": [
      {
       "n": "46",
       "of": "/ 100",
       "l": "Gid Score, #2373 overall"
      },
      {
       "n": "104K",
       "l": "downloads a week, pypi"
      },
      {
       "n": "4",
       "l": "agent projects use it"
      }
     ]
    },
    {
     "t": "small",
     "text": "Gid Score measures public popularity and activity, not quality.",
     "link": "How the Gid Score is calculated",
     "path": "tools/top/"
    }
   ]
  },
  {
   "id": "usage",
   "nav": "How it is used",
   "h2": "How AutoGen AgentChat is used",
   "parts": [
    {
     "t": "list",
     "items": [
      "AutoGen AgentChat is a dependency in 4 of the 6,254 public GitHub projects set up for AI coding agents that we scanned, too few to describe it from them alone. Our scan also samples projects by dependency (Solana 3,063, Ethereum and EVM 1,777, 3D and games 3,120, agent frameworks and SDKs 13,629); counting those, it appears in 185 projects, and what it is used with below comes from all of them.",
      "The most used alternative in our scan is LangChain (127 projects).",
      "Projects that use it most often also use AutoGen Extensions (73.5%), python-dotenv (73.5%), OpenAI Python Library (61.6%)."
     ]
    },
    {
     "t": "h3",
     "text": "Often used with"
    },
    {
     "t": "rows",
     "rows": [
      {
       "l": "In 73.5% of its projects",
       "v": "AutoGen Extensions",
       "path": "tools/autogen-ext/"
      },
      {
       "l": "In 73.5% of its projects",
       "v": "python-dotenv",
       "path": "tools/python-dotenv/"
      },
      {
       "l": "In 61.6% of its projects",
       "v": "OpenAI Python Library",
       "path": "tools/openai-pypi/"
      },
      {
       "l": "In 47.6% of its projects",
       "v": "Pydantic",
       "path": "tools/pydantic/"
      },
      {
       "l": "In 44.9% of its projects",
       "v": "AutoGen Core",
       "path": "tools/autogen-core/"
      },
      {
       "l": "In 40.0% of its projects",
       "v": "Requests",
       "path": "tools/requests-py/"
      },
      {
       "l": "In 40.0% of its projects",
       "v": "pandas",
       "path": "tools/pandas/"
      },
      {
       "l": "In 36.8% of its projects",
       "v": "NumPy",
       "path": "tools/numpy/"
      }
     ]
    }
   ]
  },
  {
   "id": "more",
   "nav": null,
   "spy_as": "usage",
   "h2": "More about AutoGen AgentChat",
   "parts": [
    {
     "t": "more",
     "items": [
      {
       "title": "More in Agent, MCP and tool libraries",
       "path": "tools/agent-libraries/",
       "items": [
        {
         "text": "Model Context Protocol SDK (JavaScript)",
         "path": "tools/modelcontextprotocol/"
        },
        {
         "text": "Model Context Protocol SDK (Python)",
         "path": "tools/mcp/"
        },
        {
         "text": "FastMCP (Python)",
         "path": "tools/fastmcp-pypi/"
        },
        {
         "text": "Agent Client Protocol SDK",
         "path": "tools/agentclientprotocol-sdk/"
        },
        {
         "text": "LangChain.js",
         "path": "tools/langchain-npm/"
        },
        {
         "text": "Mastra",
         "path": "tools/mastra/"
        },
        {
         "text": "MCP Inspector",
         "path": "tools/modelcontextprotocol-inspector/"
        },
        {
         "text": "fastMCP (JavaScript)",
         "path": "tools/fastmcp-npm/"
        }
       ]
      }
     ]
    }
   ]
  },
  {
   "id": "alternatives",
   "nav": "Alternatives",
   "h2": "Alternatives",
   "parts": [
    {
     "t": "alts",
     "items": [
      {
       "name": "AutoGen AgentChat",
       "me": true,
       "facts": [
        "MIT",
        "Gid 46",
        "104K/wk"
       ]
      },
      {
       "name": "LangChain",
       "why": "Framework for composing applications with LLMs through chains and agents.",
       "path": "tools/langchain-pypi/",
       "facts": [
        "MIT",
        "Gid 88",
        "36.5M/wk"
       ]
      },
      {
       "name": "LangGraph",
       "why": "Framework for building stateful, multi-actor applications with LLMs.",
       "path": "tools/langgraph/",
       "facts": [
        "MIT",
        "Gid 80",
        "14.6M/wk"
       ]
      },
      {
       "name": "Pydantic AI",
       "why": "AI agent framework built with Pydantic for structured, typed agent development.",
       "path": "tools/pydantic-ai/",
       "facts": [
        "MIT",
        "Gid 64",
        "1.5M/wk"
       ]
      },
      {
       "name": "LangGraph SDK",
       "why": "SDK for interacting with LangGraph API to build and run agent workflows.",
       "path": "tools/langgraph-sdk/",
       "facts": [
        "MIT",
        "Gid 75",
        "14.1M/wk"
       ]
      },
      {
       "name": "Google Agent Development Kit",
       "why": "Agent framework from Google for building AI agents.",
       "path": "tools/google-adk-pypi/",
       "facts": [
        "Apache-2.0",
        "Gid 66",
        "2.7M/wk"
       ]
      },
      {
       "name": "smolagents",
       "why": "Barebones library for building agents that write Python code to call tools.",
       "path": "tools/smolagents/",
       "facts": [
        "Gid 52",
        "200K/wk"
       ]
      },
      {
       "name": "CrewAI",
       "why": "Framework for orchestrating collaborative AI agents to solve complex autonomous tasks.",
       "path": "tools/crewai/",
       "facts": [
        "MIT",
        "Gid 65",
        "600K/wk"
       ]
      },
      {
       "name": "Semantic Kernel",
       "why": "Microsoft SDK for integrating LLMs with traditional code for AI applications.",
       "path": "tools/semantic-kernel/",
       "facts": [
        "MIT",
        "Gid 54",
        "80.1K/wk"
       ]
      }
     ],
     "more": "Compare AutoGen AgentChat with another tool",
     "more_path": "tools/compare/"
    }
   ]
  },
  {
   "id": "start",
   "nav": "Get started",
   "h2": "Get started",
   "parts": [
    {
     "t": "install",
     "intro": "Install it.",
     "code": "pip install autogen-agentchat"
    },
    {
     "t": "gap",
     "text": "No step-by-step start for AutoGen AgentChat yet: we have not written its hand-checked card."
    }
   ]
  }
 ],
 "glance": [
  [
   "Package",
   "pypi autogen-agentchat"
  ],
  [
   "Category",
   "Agent, MCP and tool libraries"
  ],
  [
   "License",
   "MIT"
  ],
  [
   "Gid Score",
   "45.6"
  ],
  [
   "Rank in category",
   "#57 of 189"
  ]
 ],
 "good": [],
 "checked_line": "From the package registry, GitHub and our scan of public agent projects; numbers update daily.",
 "logo": null
}