Failed to fetch https://docs.langchain.com/docs/use-cases/agents - status code 404

Failed to fetch https://python.langchain.com/docs/modules/agents/ - status code 404

Contents of https://github.com/microsoft/autogen:
**Important:** This is the official project. We are not affiliated with any fork or startup. See our [statement](https://x.com/pyautogen/status/1857264760951296210).

## AutoGen

**AutoGen** is a framework for creating multi-agent AI applications that can act autonomously or work alongside humans.

## Installation

AutoGen requires **Python 3.10 or later**.

```
# Install AgentChat and OpenAI client from Extensions
pip install -U "autogen-agentchat" "autogen-ext[openai]"
```

The current stable version is v0.4. If you are upgrading from AutoGen v0.2, please refer to the [Migration Guide](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/migration-guide.html) for detailed instructions on how to update your code and configurations.

```
# Install AutoGen Studio for no-code GUI
pip install -U "autogenstudio"
```

## Quickstart

### Hello World

Create an assistant agent using OpenAI's GPT-4o model. See [other supported models](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/models.html).

```
import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

async def main() -> None:
    model_client = OpenAIChatCompletionClient(model="gpt-4o")
    agent = AssistantAgent("assistant", model_client=model_client)
    print(await agent.run(task="Say 'Hello World!'"))
    await model_client.close()

asyncio.run(main())
```

### Web Browsing Agent Team

Create a group chat team with a web surfer agent and a user proxy agent
for web browsing tasks. You need to install [playwright](https://playwright.dev/python/docs/library).

```
# pip install -U autogen-agentchat autogen-ext[openai,web-surfer]
# playwright install
import asyncio
from autogen_agentchat.agents import UserProxyAgent
from autogen_agentchat.conditions import TextMentionTermination
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.agents.web_surfer import MultimodalWebSurfer

async def main() -> None:
    model_client = OpenAIChatCompletionClient(model="gpt-4o")
    # The web surfer will open a Chromium browser window to perform web browsing tasks.
    web_surfer = MultimodalWebSurfer("web_surfer", model_client, headless=False, animate_actions=True)
    # The user proxy agent is used to get user input after each step of the web surfer.
    # NOTE: you can skip input by pressing Enter.
    user_proxy = UserProxyAgent("user_proxy")
    # The termination condition is set to end the conversation when the user types 'exit'.
    termination = TextMentionTermination("exit", sources=["user_proxy"])
    # Web surfer and user proxy take turns in a round-robin fashion.
    team = RoundRobinGroupChat([web_surfer, user_proxy], termination_condition=termination)
    try:
        # Start the team and wait for it to terminate.
        await Console(team.run_stream(task="Find information about AutoGen and write a short summary."))
    finally:
        await web_surfer.close()
        await model_client.close()

asyncio.run(main())
```

### AutoGen Studio

Use AutoGen Studio to prototype and run multi-agent workflows without writing code.

```
# Run AutoGen Studio on http://localhost:8080
autogenstudio ui --port 8080 --appdir ./my-app
```

## Why Use AutoGen?

[![AutoGen Landing](/microsoft/autogen/raw/main/autogen-landing.jpg)](/microsoft/autogen/blob/main/autogen-landing.jpg)

The AutoGen ecosystem provides everything you need to create AI agents, especially multi-agent workflows -- framework, developer tools, and applications.

The *framework* uses a layered and extensible design. Layers have clearly divided responsibilities and build on top of layers below. This design enables you to use the framework at different levels of abstraction, from high-level APIs to low-level components.

* [Core API](/microsoft/autogen/blob/main/python/packages/autogen-core) implements message passing, event-driven agents, and local and distributed runtime for flexibility and power. It also support cross-language support for .NET and Python.
* [AgentChat API](/microsoft/autogen/blob/main/python/packages/autogen-agentchat) implements a simpler but opinionated API for rapid prototyping. This API is built on top of the Core API and is closest to what users of v0.2 are familiar with and supports common multi-agent patterns such as two-agent chat or group chats.
* [Extensions API](/microsoft/autogen/blob/main/python/packages/autogen-ext) enables first- and third-party extensions continuously expanding framework capabilities. It support specific implementation of LLM clients (e.g., OpenAI, AzureOpenAI), and capabilities such as code execution.

The ecosystem also supports two essential *developer tools*:

[![AutoGen Studio Screenshot](https://media.githubusercontent.com/media/microsoft/autogen/refs/heads/main/python/packages/autogen-studio/docs/

<error>Content truncated. Call the fetch tool with a start_index of 5000 to get more content.</error>