---
title: "Agent Settings"
description: "Learn how to configure the agent"
icon: "gear"
---

## Overview

The `Agent` class is the core component of Browser Use that handles browser automation. Here are the main configuration options you can use when initializing an agent.

## Basic Settings

```python
from browser_use import Agent
from langchain_openai import ChatOpenAI

agent = Agent(
    task="Search for latest news about AI",
    llm=ChatOpenAI(model="gpt-4o"),
)
```

### Required Parameters

- `task`: The instruction for the agent to execute
- `llm`: A LangChain chat model instance. See <a href="/customize/supported-models">LangChain Models</a> for supported models.

## Agent Behavior

Control how the agent operates:

```python
agent = Agent(
    task="your task",
    llm=llm,
    controller=custom_controller,  # For custom tool calling
    use_vision=True,              # Enable vision capabilities
    save_conversation_path="logs/conversation"  # Save chat logs
)
```

### Behavior Parameters

- `controller`: Registry of functions the agent can call. Defaults to base Controller. See <a href="/customize/custom-functions">Custom Functions</a> for details.
- `use_vision`: Enable/disable vision capabilities. Defaults to `True`.
  - When enabled, the model processes visual information from web pages
  - Disable to reduce costs or use models without vision support
  - For GPT-4o, image processing costs approximately 800-1000 tokens (~$0.002 USD) per image (but this depends on the defined screen size)
- `save_conversation_path`: Path to save the complete conversation history. Useful for debugging.
- `system_prompt_class`: Custom system prompt class. See <a href="/customize/system-prompt">System Prompt</a> for customization options.

<Note>
  Vision capabilities are recommended for better web interaction understanding,
  but can be disabled to reduce costs or when using models without vision
  support.
</Note>

## (Reuse) Browser Configuration

You can configure how the agent interacts with the browser. To see more `Browser` options refer to the <a href="/customize/browser-settings">Browser Settings</a> documentation.

### Reuse Existing Browser

`browser`: A Browser Use Browser instance. When provided, the agent will reuse this browser instance and automatically create new contexts for each `run()`.

```python
from browser_use import Agent, Browser
from browser_use.browser.context import BrowserContext

# Reuse existing browser
browser = Browser()
agent = Agent(
    task=task1,
    llm=llm,
    browser=browser  # Browser instance will be reused
)

await agent.run()

# Manually close the browser
await browser.close()
```

<Note>
  Remember: in this scenario the `Browser` will not be closed automatically.
</Note>

### Reuse Existing Browser Context

`browser_context`: A Playwright browser context. Useful for maintaining persistent sessions. See <a href="/customize/persistent-browser">Persistent Browser</a> for more details.

```python
from browser_use import Agent, Browser
from playwright.async_api import BrowserContext

# Use specific browser context (preferred method)
async with await browser.new_context() as context:
    agent = Agent(
        task=task2,
        llm=llm,
        browser_context=context  # Use persistent context
    )

    # Run the agent
    await agent.run()

    # Pass the context to the next agent
    next_agent = Agent(
        task=task2,
        llm=llm,
        browser_context=context
    )

    ...

await browser.close()
```

For more information about how browser context works, refer to the [Playwright
documentation](https://playwright.dev/docs/api/class-browsercontext).

<Note>
  You can reuse the same context for multiple agents. If you do nothing, the
  browser will be automatically created and closed on `run()` completion.
</Note>

## Running the Agent

The agent is executed using the async `run()` method:

- `max_steps` (default: `100`)  
  Maximum number of steps the agent can take during execution. This prevents infinite loops and helps control execution time.

## Agent History

The method returns an `AgentHistoryList` object containing the complete execution history. This history is invaluable for debugging, analysis, and creating reproducible scripts.

```python
# Example of accessing history
history = await agent.run()

# Access (some) useful information
history.urls()              # List of visited URLs
history.screenshots()       # List of screenshot paths
history.action_names()      # Names of executed actions
history.extracted_content() # Content extracted during execution
history.errors()           # Any errors that occurred
history.model_actions()     # All actions with their parameters
```

The `AgentHistoryList` provides many helper methods to analyze the execution:

- `final_result()`: Get the final extracted content
- `is_done()`: Check if the agent completed successfully
- `has_errors()`: Check if any errors occurred
- `model_thoughts()`: Get the agent's reasoning process
- `action_results()`: Get results of all actions

<Note>
  For a complete list of helper methods and detailed history analysis
  capabilities, refer to the [AgentHistoryList source
  code](https://github.com/browser-use/browser-use/blob/main/browser_use/agent/views.py#L111).
</Note>

## Run initial actions without LLM
With [this example](https://github.com/browser-use/browser-use/blob/main/examples/features/initial_actions.py) you can run initial actions without the LLM.
Specify the action as a dictionary where the key is the action name and the value is the action parameters. You can find all our actions in the [Controller](https://github.com/browser-use/browser-use/blob/main/browser_use/controller/service.py) source code.
```python

initial_actions = [
	{'open_tab': {'url': 'https://www.google.com'}},
	{'open_tab': {'url': 'https://en.wikipedia.org/wiki/Randomness'}},
	{'scroll_down': {'amount': 1000}},
]
agent = Agent(
	task='What theories are displayed on the page?',
	initial_actions=initial_actions,
	llm=llm,
)
```

## Run with planner model

You can configure the agent to use a separate planner model for high-level task planning:

```python
from langchain_openai import ChatOpenAI

# Initialize models
llm = ChatOpenAI(model='gpt-4o')
planner_llm = ChatOpenAI(model='o3-mini')

agent = Agent(
    task="your task",
    llm=llm,
    planner_llm=planner_llm,           # Separate model for planning
    use_vision_for_planner=False,      # Disable vision for planner
    planner_interval=4                 # Plan every 4 steps
)
```

### Planner Parameters

- `planner_llm`: A LangChain chat model instance used for high-level task planning. Can be a smaller/cheaper model than the main LLM.
- `use_vision_for_planner`: Enable/disable vision capabilities for the planner model. Defaults to `True`.
- `planner_interval`: Number of steps between planning phases. Defaults to `1`.

Using a separate planner model can help:
- Reduce costs by using a smaller model for high-level planning
- Improve task decomposition and strategic thinking
- Better handle complex, multi-step tasks

<Note>
  The planner model is optional. If not specified, the agent will not use the planner model.
</Note>