mirror of
https://github.com/browser-use/browser-use
synced 2026-05-06 17:52:15 +02:00
229 lines
6.9 KiB
Markdown
229 lines
6.9 KiB
Markdown
<img src="./static/browser-use.png" alt="Browser Use Logo" width="full"/>
|
|
|
|
<br/>
|
|
|
|
[](https://github.com/gregpr07/browser-use/stargazers)
|
|
[](https://opensource.org/licenses/MIT)
|
|
[](https://www.python.org/downloads/)
|
|
[](https://link.browser-use.com/discord)
|
|
|
|
Make websites accessible for AI agents 🤖.
|
|
|
|
Browser use is the easiest way to connect your AI agents with the browser. If you have used Browser Use for your project feel free to show it off in our [Discord](https://link.browser-use.com/discord).
|
|
|
|
# Quick start
|
|
|
|
With pip:
|
|
|
|
```bash
|
|
pip install browser-use
|
|
```
|
|
|
|
(optional) install playwright:
|
|
|
|
```bash
|
|
playwright install
|
|
```
|
|
|
|
Spin up your agent:
|
|
|
|
```python
|
|
from langchain_openai import ChatOpenAI
|
|
from browser_use import Agent
|
|
import asyncio
|
|
|
|
async def main():
|
|
agent = Agent(
|
|
task="Find a one-way flight from Bali to Oman on 12 January 2025 on Google Flights. Return me the cheapest option.",
|
|
llm=ChatOpenAI(model="gpt-4o"),
|
|
)
|
|
result = await agent.run()
|
|
print(result)
|
|
|
|
asyncio.run(main())
|
|
```
|
|
|
|
And don't forget to add your API keys to your `.env` file.
|
|
|
|
```bash
|
|
OPENAI_API_KEY=
|
|
ANTHROPIC_API_KEY=
|
|
```
|
|
|
|
# Demos
|
|
|
|
<div style="font-size: 4em;">
|
|
Prompt: Read my CV & find ML jobs, save them to a file, and then start applying for them in new tabs, if you need help, ask me.' (8x speed)
|
|
</div>
|
|
|
|
https://github.com/user-attachments/assets/171fb4d6-0355-46f2-863e-edb04a828d04
|
|
|
|
<div style="font-size: 4em;">
|
|
Prompt: Find flights on kayak.com from Zurich to Beijing from 25.12.2024 to 02.02.2025. (8x speed)
|
|
</div>
|
|
|
|
|
|
|
|
<div style="font-size: 4em;">
|
|
Prompt: Look up models with a license of cc-by-sa-4.0 and sort by most likes on Hugging face, save top 5 to file. (1x speed)
|
|
</div>
|
|
|
|
https://github.com/user-attachments/assets/de73ee39-432c-4b97-b4e8-939fd7f323b3
|
|
|
|
# Features ⭐
|
|
|
|
- Vision + html extraction
|
|
- Automatic multi-tab management
|
|
- Extract clicked elements XPaths and repeat exact LLM actions
|
|
- Add custom actions (e.g. save to file, push to database, notify me, get human input)
|
|
- Self-correcting
|
|
- Use any LLM supported by LangChain (e.g. gpt4o, gpt4o mini, claude 3.5 sonnet, llama 3.1 405b, etc.)
|
|
- Parallelize as many agents as you want
|
|
|
|
## Register custom actions
|
|
|
|
If you want to add custom actions your agent can take, you can register them like this:
|
|
|
|
You can use BOTH sync or async functions.
|
|
|
|
```python
|
|
from browser_use.agent.service import Agent
|
|
from browser_use.browser.service import Browser
|
|
from browser_use.controller.service import Controller
|
|
|
|
# Initialize controller first
|
|
controller = Controller()
|
|
|
|
@controller.action('Ask user for information')
|
|
def ask_human(question: str, display_question: bool) -> str:
|
|
return input(f'\n{question}\nInput: ')
|
|
```
|
|
|
|
Or define your parameters using Pydantic
|
|
|
|
```python
|
|
class JobDetails(BaseModel):
|
|
title: str
|
|
company: str
|
|
job_link: str
|
|
salary: Optional[str] = None
|
|
|
|
@controller.action('Save job details which you found on page', param_model=JobDetails, requires_browser=True)
|
|
async def save_job(params: JobDetails, browser: Browser):
|
|
print(params)
|
|
|
|
# use the browser normally
|
|
page = browser.get_current_page()
|
|
page.go_to(params.job_link)
|
|
```
|
|
|
|
and then run your agent:
|
|
|
|
```python
|
|
model = ChatAnthropic(model_name='claude-3-5-sonnet-20240620', timeout=25, stop=None, temperature=0.3)
|
|
agent = Agent(task=task, llm=model, controller=controller)
|
|
|
|
await agent.run()
|
|
```
|
|
|
|
## Parallelize agents
|
|
|
|
In 99% cases you should use 1 Browser instance and parallelize the agents with 1 context per agent.
|
|
You can also reuse the context after the agent finishes.
|
|
|
|
```python
|
|
browser = Browser()
|
|
```
|
|
|
|
```python
|
|
for i in range(10):
|
|
# This create a new context and automatically closes it after the agent finishes (with `__aexit__`)
|
|
async with browser.new_context() as context:
|
|
agent = Agent(task=f"Task {i}", llm=model, browser_context=context)
|
|
|
|
# ... reuse context
|
|
```
|
|
|
|
If you would like to learn more about how this works under the hood you can learn more at [playwright browser-context](https://playwright.dev/python/docs/api/class-browsercontext).
|
|
|
|
### Context vs Browser
|
|
|
|
If you don't specify a `browser` or `browser_context` the agent will create a new browser instance and context.
|
|
|
|
## Get XPath history
|
|
|
|
To get the entire history of everything the agent has done, you can use the output of the `run` method:
|
|
|
|
```python
|
|
history: list[AgentHistory] = await agent.run()
|
|
|
|
print(history)
|
|
```
|
|
|
|
## Browser configuration
|
|
|
|
You can configure the browser using the `BrowserConfig` and `BrowserContextConfig` classes.
|
|
|
|
The most important options are:
|
|
|
|
- `headless`: Whether to run the browser in headless mode
|
|
- `keep_open`: Whether to keep the browser open after the script finishes
|
|
- `disable_security`: Whether to disable browser security features (very useful if dealing with cross-origin requests like iFrames)
|
|
- `cookies_file`: Path to a cookies file for persistence
|
|
- `minimum_wait_page_load_time`: Minimum time to wait before getting the page state for the LLM input
|
|
- `wait_for_network_idle_page_load_time`: Time to wait for network requests to finish before getting the page state
|
|
- `maximum_wait_page_load_time`: Maximum time to wait for the page to load before proceeding anyway
|
|
|
|
## More examples
|
|
|
|
For more examples see the [examples](examples) folder or join the [Discord](https://link.browser-use.com/discord) and show off your project.
|
|
|
|
## Telemetry
|
|
|
|
We collect anonymous usage data to help us understand how the library is being used and to identify potential issues. There is no privacy risk, as no personal information is collected. We collect data with PostHog.
|
|
|
|
You can opt out of telemetry by setting the `ANONYMIZED_TELEMETRY=false` environment variable.
|
|
|
|
# Contributing
|
|
|
|
Contributions are welcome! Feel free to open issues for bugs or feature requests.
|
|
|
|
## Local Setup
|
|
|
|
1. Create a virtual environment and install dependencies:
|
|
|
|
```bash
|
|
# To install all dependencies including dev
|
|
pip install . ."[dev]"
|
|
```
|
|
|
|
2. Add your API keys to the `.env` file:
|
|
|
|
```bash
|
|
cp .env.example .env
|
|
```
|
|
|
|
or copy the following to your `.env` file:
|
|
|
|
```bash
|
|
OPENAI_API_KEY=
|
|
ANTHROPIC_API_KEY=
|
|
```
|
|
|
|
You can use any LLM model supported by LangChain by adding the appropriate environment variables. See [langchain models](https://python.langchain.com/docs/integrations/chat/) for available options.
|
|
|
|
### Building the package
|
|
|
|
```bash
|
|
hatch build
|
|
```
|
|
|
|
Feel free to join the [Discord](https://link.browser-use.com/discord) for discussions and support.
|
|
|
|
---
|
|
|
|
<div align="center">
|
|
<b>Star ⭐ this repo if you find it useful!</b><br>
|
|
Made with ❤️ by the Browser-Use team
|
|
</div>
|