Quickstart — Scrapybara Docs

Deploy your first instance

Python

TypeScript

Generate API key

Install SDK

Install the Python SDK with pip.

$ pip install scrapybara

Configure client

Configure the client with your API key.

1 from scrapybara import Scrapybara
2 
3 client = Scrapybara(api_key="your_api_key")

Start an instance

Start an instance with your desired configuration.

1 instance = client.start(
2     instance_type="small",
3     timeout_hours=1,
4 )

Pause and resume the instance

Pause the instance to save resources and resume it when needed.

Pause the instance

1 instance.pause()

Resume the instance

1 instance.resume(timeout_hours=1)

Interact with the instance

Interact with the instance with screenshot, bash, computer, and edit.

Get the stream URL

1 stream_url = instance.get_stream_url().stream_url

Take a screenshot

1 base_64_image = instance.screenshot().base_64_image

Move the mouse

1 result = instance.computer(
2     action="mouse_move",
3     coordinate=[200, 100]
4 )

Left click

1 result = instance.computer(
2     action="left_click"
3 )

Run a bash command

1 result = instance.bash(
2     command="ls -la"
3 )

Connect to the browser

Connect to the browser with Playwright to enable programmatic browser control and authenticated browser sessions. Learn more here.

Connect to Playwright

1 from playwright.sync_api import sync_playwright
2 
3 cdp_url = instance.browser.start().cdp_url
4 playwright = sync_playwright().start()
5 browser = playwright.chromium.connect_over_cdp(cdp_url)

Save the auth state

1 auth_state_id = instance.browser.save_auth(name="default").auth_state_id

Reuse the auth state on other instances

1 instance.browser.authenticate(auth_state_id=auth_state_id)

Take action!

Build your first agent with the Act SDK to control your Scrapybara instance with BashTool, ComputerTool, EditTool. Learn more here.

1 from scrapybara.tools import BashTool, ComputerTool, EditTool
2 from scrapybara.anthropic import Anthropic
3 from scrapybara.prompts import SYSTEM_PROMPT
4 
5 response = client.act(
6     model=Anthropic(),
7     tools=[
8         BashTool(instance),
9         ComputerTool(instance),
10         EditTool(instance),
11         BrowserTool(instance),
12     ],
13     system=SYSTEM_PROMPT,
14     prompt="Go to the top link on Hacker News",
15     on_step=lambda step: print(step.text),
16 )

Stop the instance

Stop the instance when you’re done. This will delete all data stored during the session.

1 instance.stop()

Start building

Be sure to check out our other resources to learn more. Happy building! ₍ᐢ•(ܫ)•ᐢ₎

Act SDK

Take action with computer use agents

Browser

Control a browser with Playwright

API Reference

Check out our API reference docs

Official Examples

Official open source examples

1	from scrapybara import Scrapybara
2
3	client = Scrapybara(api_key="your_api_key")

1	instance = client.start(
2	instance_type="small",
3	timeout_hours=1,
4	)

1	result = instance.computer(
2	action="mouse_move",
3	coordinate=[200, 100]
4	)

1	from playwright.sync_api import sync_playwright
2
3	cdp_url = instance.browser.start().cdp_url
4	playwright = sync_playwright().start()
5	browser = playwright.chromium.connect_over_cdp(cdp_url)

1	from scrapybara.tools import BashTool, ComputerTool, EditTool
2	from scrapybara.anthropic import Anthropic
3	from scrapybara.prompts import SYSTEM_PROMPT
4
5	response = client.act(
6	model=Anthropic(),
7	tools=[
8	BashTool(instance),
9	ComputerTool(instance),
10	EditTool(instance),
11	BrowserTool(instance),
12	],
13	system=SYSTEM_PROMPT,
14	prompt="Go to the top link on Hacker News",
15	on_step=lambda step: print(step.text),
16	)