Hyperbrowser | Composio Docs

Overview

SLUG: HYPERBROWSER

Description

Hyperbrowser is a next-generation platform empowering AI agents and enabling effortless, scalable browser automation.

Authentication Details

API Key

generic_api_key

stringRequired

Connecting to Hyperbrowser

Create an auth config

Use the dashboard to create an auth config for the Hyperbrowser toolkit. This allows you to connect multiple Hyperbrowser accounts to Composio for agents to use.

Select App

Navigate to Hyperbrowser.

Configure Auth Config Settings

Select among the supported auth schemes of and configure them here.

Create and Get auth config ID

Click “Create Hyperbrowser Auth Config”. After creation, copy the displayed ID starting with ac_. This is your auth config ID. This is not a sensitive ID — you can save it in environment variables or a database. This ID will be used to create connections to the toolkit for a given user.

Connect Your Account

Using API Key

1 from composio import Composio
2 
3 # Replace these with your actual values
4 hyperbrowser_auth_config_id = "ac_YOUR_HYPERBROWSER_CONFIG_ID" # Auth config ID created above
5 user_id = "0000-0000-0000"  # UUID from database/app
6 
7 composio = Composio()
8 
9 def authenticate_toolkit(user_id: str, auth_config_id: str):
10     # Replace this with a method to retrieve an API key from the user.
11     # Or supply your own.
12     user_api_key = input("[!] Enter API key")
13 
14     connection_request = composio.connected_accounts.initiate(
15         user_id=user_id,
16         auth_config_id=auth_config_id,
17         config={"auth_scheme": "API_KEY", "val": {"generic_api_key": user_api_key}}
18     )
19 
20     # API Key authentication is immediate - no redirect needed
21     print(f"Successfully connected Hyperbrowser for user {user_id}")
22     print(f"Connection status: {connection_request.status}")
23     
24     return connection_request.id
25 
26 
27 connection_id = authenticate_toolkit(user_id, hyperbrowser_auth_config_id)
28 
29 # You can verify the connection using:
30 connected_account = composio.connected_accounts.get(connection_id)
31 print(f"Connected account: {connected_account}")

Tools

Executing tools

To prototype you can execute some tools to see the responses and working on the Hyperbrowser toolkit’s playground

OpenAI (Python)

Anthropic (TypeScript)

Google (Python)

Vercel (TypeScript)

Python

1 from composio import Composio
2 from openai import OpenAI
3 import json
4 
5 openai = OpenAI()
6 composio = Composio()
7 
8 # User ID must be a valid UUID format
9 user_id = "0000-0000-0000"  # Replace with actual user UUID from your database
10 
11 tools = composio.tools.get(user_id=user_id, toolkits=["HYPERBROWSER"])
12 
13 print("[!] Tools:")
14 print(json.dumps(tools))
15 
16 def invoke_llm(task = "What can you do?"):
17     completion = openai.chat.completions.create(
18         model="gpt-4o",
19         messages=[
20             {
21                 "role": "user",
22                 "content": task,  # Your task here!
23             },
24         ],
25         tools=tools,
26     )
27 
28     # Handle Result from tool call
29     result = composio.provider.handle_tool_calls(user_id=user_id, response=completion)
30     print(f"[!] Completion: {completion}")
31     print(f"[!] Tool call result: {result}")
32 
33 invoke_llm()

Tool List

HYPERBROWSER_CREATE_PROFILE

Tool Name: Create Hyperbrowser Profile

Description

Tool to create a new profile. Use when you need to initialize a Hyperbrowser profile before analysis.

Action Parameters

name

string

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_CREATE_SCRAPE_JOB

Tool Name: Create Scrape Job

Description

Tool to initiate a new scrape job. Use when you need to extract structured content from a target URL with custom session and scrape settings.

Action Parameters

scrapeOptions

object

sessionOptions

object

url

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_CREATE_SESSION

Tool Name: Create Session

Description

Tool to create a new browser session with custom stealth, proxy, and privacy settings. Use when initializing an automated browsing session with specific configuration.

Action Parameters

acceptCookies

boolean

adblock

boolean

annoyances

boolean

browserArgs

array

device

array

enableVideoWebRecording

boolean

enableWebRecording

booleanDefaults to True

extensionIds

array

imageCaptchaParams

array

locales

array

operatingSystems

array

platform

array

profile

object

proxyCity

string

proxyCountry

string

proxyServer

string

proxyServerPassword

string

proxyServerUsername

string

proxyState

string

screen

object

solveCaptchas

boolean

timeoutMinutes

integer

trackers

boolean

urlBlocklist

array

useProxy

boolean

useStealth

boolean

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_DELETE_PROFILE

Tool Name: Delete Profile

Description

Tool to delete a profile. Use when you need to remove a profile by its unique identifier after confirming its existence.

Action Parameters

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_GET_BROWSER_USE_TASK_STATUS

Tool Name: Get browser-use task status

Description

Tool to retrieve the current status of a browser-use task. Use when checking if a browser automation task has completed or is still pending.

Action Parameters

task_id

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_GET_CLAUDE_COMPUTER_USE_TASK_STATUS

Tool Name: Get Claude Computer Use Task Status

Description

Tool to retrieve the status of a Claude Computer Use task. Use after creating a task to poll its status.

Action Parameters

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_GET_CRAWL_JOB_RESULT

Tool Name: Get Crawl Job Result

Description

Tool to retrieve the result of a completed crawl job. Use after confirming crawl job completion to fetch current page batch and status. Supports pagination via page and batchSize.

Action Parameters

batchSize

integer

stringRequired

page

integer

Action Response

batchSize

integerRequired

currentPageBatch

integerRequired

data

arrayRequired

error

string

jobId

stringRequired

status

stringRequired

successful

booleanRequired

totalCrawledPages

integerRequired

totalPageBatches

integerRequired

HYPERBROWSER_GET_CRAWL_JOB_STATUS

Tool Name: Get Crawl Job Status

Description

Tool to retrieve the status and results of a specific crawl job. Use after submitting a crawl job to check its progress or fetch results.

Action Parameters

job_id

stringRequired

Action Response

batchSize

integerRequired

currentPageBatch

integerRequired

data

arrayRequired

error

string

jobId

stringRequired

status

stringRequired

successful

booleanRequired

totalCrawledPages

integerRequired

totalPageBatches

integerRequired

HYPERBROWSER_GET_EXTRACT_JOB_RESULT

Tool Name: Get Extract Job Result

Description

Tool to fetch the status and results of a specific extract job. Use after initiating an extract job to monitor progress and retrieve final data.

Action Parameters

stringRequired

Action Response

data

error

string

jobId

stringRequired

status

stringRequired

successful

booleanRequired

HYPERBROWSER_GET_EXTRACT_JOB_STATUS

Tool Name: Get Extract Job Status

Description

Tool to retrieve the status of an extract job. Use after submitting an extract job to poll its status.

Action Parameters

job_id

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_GET_PROFILE_BY_ID

Tool Name: Get Profile By ID

Description

Tool to retrieve profile details by ID. Use after confirming the profile ID.

Action Parameters

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_GET_SCRAPE_JOB_RESULT

Tool Name: Get Scrape Job Result

Description

Tool to fetch the status and results of a specific scrape job. Use after initiating a scrape job to monitor its progress and retrieve final data.

Action Parameters

stringRequired

Action Response

data

object

error

string

jobId

stringRequired

status

stringRequired

successful

booleanRequired

HYPERBROWSER_GET_SCRAPE_JOB_STATUS

Tool Name: Get Scrape Job Status

Description

Tool to retrieve the current status of a specific scrape job. Use after initiating a scrape job to poll its status.

Action Parameters

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_GET_SESSION_DETAILS

Tool Name: Get Session Details

Description

Tool to retrieve session details by ID. Use after confirming the session ID.

Action Parameters

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_GET_SESSION_DOWNLOADS_URL

Tool Name: Get Session Downloads URL

Description

Tool to retrieve the downloads URL for a session. Use when you need the signed URL for session downloads after processing is complete.

Action Parameters

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_GET_SESSION_RECORDING

Tool Name: Get Session Recording

Description

Tool to retrieve the recording URL of a session. Use after confirming the session ID and when the recording is expected to be ready.

Action Parameters

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_LIST_PROFILES

Tool Name: List Profiles

Description

Tool to list profiles. Use when you need to fetch paginated profiles and optionally filter by name.

Action Parameters

limit

integerDefaults to 10

name

string

page

integerDefaults to 1

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_LIST_SESSIONS

Tool Name: List Sessions

Description

Tool to list sessions with optional status filter. Use when you need a paginated overview of browser sessions before acting on them.

Action Parameters

page

integerDefaults to 1

status

string

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_START_BROWSER_USE_TASK

Tool Name: Start Browser Use Task

Description

Tool to start an asynchronous browser-use task. Use when you need to automate web interactions given a task instruction.

Action Parameters

apiKeys

object

initialActions

array

keepBrowserOpen

boolean

llm

stringDefaults to gemini-2.0-flash

maxActionsPerStep

integerDefaults to 10

maxFailures

integerDefaults to 3

maxInputTokens

integerDefaults to 128000

maxSteps

integerDefaults to 20

pageExtractionLlm

stringDefaults to gemini-2.0-flash

plannerInterval

integerDefaults to 10

plannerLlm

stringDefaults to gemini-2.0-flash

sessionId

string

sessionOptions

object

task

stringRequired

useCustomApiKeys

boolean

useVision

booleanDefaults to True

useVisionForPlanner

boolean

validateOutput

boolean

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_START_CLAUDE_COMPUTER_USE_TASK

Tool Name: Start Claude Computer Use Task

Description

Tool to start a Claude Computer Use task. Use when you need AI-driven automated browser interactions. Call after you have your task prompt and any session preferences configured.

Action Parameters

apiKeys

object

keepBrowserOpen

boolean

llm

stringDefaults to claude-3-7-sonnet-20250219

maxFailures

integerDefaults to 3

maxSteps

integerDefaults to 20

sessionId

string

sessionOptions

object

task

stringRequired

useComputerAction

boolean

useCustomApiKeys

boolean

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_START_CRAWL_JOB

Tool Name: Start Crawl Job

Description

Tool to start a new crawl job for a specified URL. Use when you need to initiate a web crawl before checking job status.

Action Parameters

excludePatterns

array

followLinks

booleanDefaults to True

ignoreSitemap

boolean

includePatterns

array

maxPages

integer

scrapeOptions

object

sessionOptions

object

url

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_START_EXTRACT_JOB

Tool Name: Start Extract Job

Description

Tool to start an extract job. Use when you need to initiate a new extraction with custom prompts, schema, and session options. Call after preparing URLs and desired extraction schema.

Action Parameters

maxLinks

integer

prompt

string

schema

object

sessionOptions

object

systemPrompt

string

urls

arrayRequired

waitFor

integer

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_STOP_BROWSER_USE_TASK

Tool Name: Stop Browser Use Task

Description

Tool to stop a running browser-use task. Use when halting an in-progress browser automation task after confirming its task ID.

Action Parameters

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_STOP_CLAUDE_COMPUTER_USE_TASK

Tool Name: Stop Claude Computer Use Task

Description

Tool to stop a running Claude computer use task. Use when a Claude computer use task is in progress and needs to be terminated.

Action Parameters

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

HYPERBROWSER_STOP_SESSION

Tool Name: Stop Session

Description

Tool to stop a running session by ID. Use after confirming the session is active.

Action Parameters

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired