> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-lginte-1765488813-6406a61.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# MultiOn Toolkit

[MultiON](https://www.multion.ai/blog/multion-building-a-brighter-future-for-humanity-with-ai-agents) has built an AI Agent that can interact with a broad array of web services and applications.

This notebook walks you through connecting LangChain to the `MultiOn` Client in your browser.

This enables custom agentic workflow that utilize the power of MultiON agents.

To use this toolkit, you will need to add `MultiOn Extension` to your browser:

* Create a [MultiON account](https://app.multion.ai/login?callbackUrl=%2Fprofile).
* Add  [MultiOn extension for Chrome](https://multion.notion.site/Download-MultiOn-ddddcfe719f94ab182107ca2612c07a5).

```python theme={null}
pip install -qU  multion langchain -q
```

```python theme={null}
pip install -qU langchain-community
```

```python theme={null}
from langchain_community.agent_toolkits import MultionToolkit

toolkit = MultionToolkit()
toolkit
```

```output theme={null}
MultionToolkit()
```

```python theme={null}
tools = toolkit.get_tools()
tools
```

```output theme={null}
[MultionCreateSession(), MultionUpdateSession(), MultionCloseSession()]
```

## MultiOn Setup

Once you have created an account, create an API key at [app.multion.ai/](https://app.multion.ai/).

Login to establish connection with your extension.

```python theme={null}
# Authorize connection to your Browser extention
import multion

multion.login()
```

```output theme={null}
Logged in.
```

## Use Multion Toolkit within an Agent

This will use MultiON chrome extension to perform the desired actions.

We can run the below, and view the [trace](https://smith.langchain.com/public/34aaf36d-204a-4ce3-a54e-4a0976f09670/r) to see:

* The agent uses the `create_multion_session` tool
* It then uses MultiON to execute the query

```python theme={null}
from langchain_classic import hub
from langchain.agents import AgentExecutor, create_openai_functions_agent
from langchain_openai import ChatOpenAI
```

```python theme={null}
# Prompt
instructions = """You are an assistant."""
base_prompt = hub.pull("langchain-ai/openai-functions-template")
prompt = base_prompt.partial(instructions=instructions)
```

```python theme={null}
# LLM
llm = ChatOpenAI(temperature=0)
```

```python theme={null}
# Agent
agent = create_openai_functions_agent(llm, toolkit.get_tools(), prompt)
agent_executor = AgentExecutor(
    agent=agent,
    tools=toolkit.get_tools(),
    verbose=False,
)
```

```python theme={null}
agent_executor.invoke(
    {
        "input": "Use multion to explain how AlphaCodium works, a recently released code language model."
    }
)
```

```output theme={null}
WARNING: 'new_session' is deprecated and will be removed in a future version. Use 'create_session' instead.
WARNING: 'update_session' is deprecated and will be removed in a future version. Use 'step_session' instead.
WARNING: 'update_session' is deprecated and will be removed in a future version. Use 'step_session' instead.
WARNING: 'update_session' is deprecated and will be removed in a future version. Use 'step_session' instead.
WARNING: 'update_session' is deprecated and will be removed in a future version. Use 'step_session' instead.
```

```output theme={null}
{'input': 'Use multion to how AlphaCodium works, a recently released code language model.',
 'output': 'AlphaCodium is a recently released code language model that is designed to assist developers in writing code more efficiently. It is based on advanced machine learning techniques and natural language processing. AlphaCodium can understand and generate code in multiple programming languages, making it a versatile tool for developers.\n\nThe model is trained on a large dataset of code snippets and programming examples, allowing it to learn patterns and best practices in coding. It can provide suggestions and auto-complete code based on the context and the desired outcome.\n\nAlphaCodium also has the ability to analyze code and identify potential errors or bugs. It can offer recommendations for improving code quality and performance.\n\nOverall, AlphaCodium aims to enhance the coding experience by providing intelligent assistance and reducing the time and effort required to write high-quality code.\n\nFor more detailed information, you can visit the official AlphaCodium website or refer to the documentation and resources available online.\n\nI hope this helps! Let me know if you have any other questions.'}
```

***

<Callout icon="pen-to-square" iconType="regular">
  [Edit the source of this page on GitHub.](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/tools/multion.mdx)
</Callout>

<Tip icon="terminal" iconType="regular">
  [Connect these docs programmatically](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
</Tip>