Real browser docs

docs/customize/agent-settings.mdx

@@ -16,7 +16,7 @@ from langchain_openai import ChatOpenAI
 
 agent = Agent(
     task="Search for latest news about AI",
-    llm=ChatOpenAI(model="gpt-4"),
+    llm=ChatOpenAI(model="gpt-4o"),
 )
 ```
 
@@ -33,7 +33,7 @@ Control how the agent operates:
 agent = Agent(
     task="your task",
     llm=llm,
-    controller=custom_controller,  # Custom function registry
+    controller=custom_controller,  # For custom tool calling
     use_vision=True,              # Enable vision capabilities
     save_conversation_path="logs/conversation.json"  # Save chat logs
 )

docs/customize/custom-functions.mdx

@@ -10,13 +10,14 @@ Functions can be either `sync` or `async`. Keep them focused and single-purpose.
 
 ```python
 from browser_use.controller.service import Controller
-
+from browser_use import ActionResult
 # Initialize the controller
 controller = Controller()
 
 @controller.action('Ask user for information')
-def ask_human(question: str, display_question: bool) -> str:
-    return input(f'\n{question}\nInput: ')
+def ask_human(question: str) -> str:
+    answer = input(f'\n{question}\nInput: ')
+    return ActionResult(extracted_content=answer)
 ```
 
 <Note>
@@ -50,6 +51,7 @@ from browser_use.browser.service import Browser
 async def open_website(url: str, browser: Browser):
     page = browser.get_current_page()
     await page.goto(url)
+    return ActionResult(extracted_content='Website opened')
 ```
 
 ## Structured Parameters with Pydantic
@@ -110,3 +112,8 @@ await agent2.run()
   The controller is stateless and can be used to register multiple actions and
   multiple agents.
 </Note>
+
+
+
+For more examples like file upload or notifications, visit [examples/custom-functions](https://github.com/browser-use/browser-use/tree/main/examples/custom-functions).
+

docs/customize/real-browser.mdx

@@ -0,0 +1,53 @@
+---
+title: "Connect to a Real Browser"
+description: "With this you can connect to your real browser, where you are logged in with all your accounts."
+icon: "message"
+---
+
+## Overview
+
+You can connect the agent to your real Chrome browser instance, allowing it to access your existing browser profile with all your logged-in accounts and settings. This is particularly useful when you want the agent to interact with services where you're already authenticated.
+
+<Note>
+  First make sure to close all running Chrome instances.
+</Note>
+
+## Basic Configuration
+
+To connect to your real Chrome browser, you'll need to specify the path to your Chrome executable when creating the Browser instance:
+
+```python
+from browser_use import Agent, Browser, BrowserConfig
+from langchain_openai import ChatOpenAI
+import asyncio
+# Configure the browser to connect to your Chrome instance
+browser = Browser(
+    config=BrowserConfig(
+        # Specify the path to your Chrome executable
+        chrome_instance_path='/Applications/Google Chrome.app/Contents/MacOS/Google Chrome',  # macOS path
+        # For Windows, typically: 'C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe'
+        # For Linux, typically: '/usr/bin/google-chrome'
+    )
+)
+
+# Create the agent with your configured browser
+agent = Agent(
+    task="Your task here",
+    llm=ChatOpenAI(model='gpt-4o'),
+    browser=browser,
+)
+
+async def main():
+    await agent.run()
+
+    input('Press Enter to close the browser...')
+    await browser.close()
+
+if __name__ == '__main__':
+    asyncio.run(main())
+```
+
+
+<Note>
+  When using your real browser, the agent will have access to all your logged-in sessions. Make sure to review the task you're giving to the agent and ensure it aligns with your security requirements.
+</Note>

docs/customize/system-prompt.mdx

@@ -6,7 +6,7 @@ icon: "message"
 
 ## Overview
 
-You can customize the system prompt by extending the `SystemPrompt` class. Internally, this adds extra instructions to the default system prompt (which is general and quite optimized at this point).
+You can customize the system prompt by extending the `SystemPrompt` class. Internally, this adds extra instructions to the default system prompt.
 
 <Note>
   Custom system prompts allow you to modify the agent's behavior at a
@@ -36,17 +36,6 @@ class MySystemPrompt(SystemPrompt):
         return f'{existing_rules}\n{new_rules}'
 ```
 
-The `important_rules()` are written in format like this. Keeping the format
-consistent helps with redundancy and readability.
-
-```text
-8. ACTION SEQUENCING:
-   - Actions are executed in the order they appear in the list
-   - ...
-```
-
-<Note>Try not to override other methods unless you have a specific need.</Note>
-
 ## Using Custom System Prompt
 
 Apply your custom system prompt when creating an agent:

docs/mint.json

@@ -50,6 +50,7 @@
         "customize/agent-settings",
         "customize/browser-settings",
         "customize/system-prompt",
+        "customize/real-browser",
         "customize/custom-functions"
       ]
     },

examples/browser/real_browser.py

@@ -15,22 +15,16 @@ from browser_use.browser.context import BrowserContext
 
 browser = Browser(
 	config=BrowserConfig(
-		headless=False,
 		# NOTE: you need to close your chrome browser - so that this can open your browser in debug mode
 		chrome_instance_path='/Applications/Google Chrome.app/Contents/MacOS/Google Chrome',
 	)
 )
-controller = Controller()
 
 
 async def main():
-	task = f'In docs.google.com write my Papa a quick thank you for everything letter \n - Magnus'
-	task += f' and save the document as pdf'
-	model = ChatOpenAI(model='gpt-4o')
 	agent = Agent(
-		task=task,
-		llm=model,
-		controller=controller,
+		task='In docs.google.com write my Papa a quick letter',
+		llm=ChatOpenAI(model='gpt-4o'),
 		browser=browser,
 	)