Hyperbrowser

aid: hyperbrowser
name: Hyperbrowser
description: >-
  Hyperbrowser provides cloud browser infrastructure tailored for AI agents,
  bundling managed Chromium sessions with web scraping, crawling, and
  data-extraction APIs. The platform ships an open-source HyperAgent framework
  and first-class integrations for Browser-Use, Claude Computer Use, Gemini
  Computer Use, and OpenAI's CUA, so teams can deploy general-purpose web
  agents quickly. Customers include AI startups, data teams, and enterprises
  needing stealthy, multi-region browsers with CAPTCHA solving, proxies, and
  session profiles. Python and Node SDKs cover sessions, scrape/crawl jobs,
  extraction, and agent task management, with an MCP server for use inside
  Claude, Cursor, and other MCP clients. Pricing is usage-based via the
  hyperbrowser.ai pricing page.
type: Index
position: Provider
access: 3rd-Party
image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
tags:
  - Headless Browser
  - Browser Infrastructure
  - Web Scraping
  - Web Crawling
  - Data Extraction
  - AI Agents
  - Browser Automation
  - Computer Use
  - Stealth
  - Proxies
  - CAPTCHA Solving
  - MCP
  - HyperAgent
url: https://raw.githubusercontent.com/api-evangelist/hyperbrowser/refs/heads/main/apis.yml
created: '2026-05-23'
modified: '2026-05-23'
specificationVersion: '0.20'
apis:
  - aid: hyperbrowser:browser-api
    name: Hyperbrowser API
    description: >-
      Hyperbrowser's REST API manages cloud browser sessions, profiles,
      extensions, scrape and crawl jobs, structured extraction jobs, and
      agentic task runs across Browser-Use, HyperAgent, Claude Computer Use,
      Gemini Computer Use, and OpenAI CUA. Returns content in HTML, Markdown,
      JSON, and screenshot formats.
    humanURL: https://hyperbrowser.ai/docs
    baseURL: https://api.hyperbrowser.ai
    tags:
      - Sessions
      - Scrape
      - Crawl
      - Extract
      - Agents
      - Profiles
      - Extensions
      - Computer Use
    properties:
      - type: Documentation
        url: https://hyperbrowser.ai/docs
      - type: APIReference
        url: https://hyperbrowser.ai/docs/api-reference
      - type: GettingStarted
        url: https://hyperbrowser.ai/docs/quickstart
      - type: SignUp
        url: https://app.hyperbrowser.ai/signup
      - type: SDK
        url: https://github.com/hyperbrowserai/python-sdk
      - type: SDK
        url: https://github.com/hyperbrowserai/node-sdk
      - type: GitHubRepository
        url: https://github.com/hyperbrowserai/HyperAgent
      - type: Pricing
        url: https://hyperbrowser.ai/pricing
      - type: LLMsTxt
        url: https://hyperbrowser.ai/docs/llms.txt
    features:
      - name: Cloud Browser Sessions
        description: Managed Chromium sessions with lifecycle, recording, and download retrieval.
      - name: Scrape and Crawl
        description: Single-page scrape, batch scrape, and recursive crawl jobs with status polling.
      - name: Structured Extraction
        description: Extract typed data from pages using prompts and schemas.
      - name: Agent Task APIs
        description: Start, stop, and monitor agentic tasks across HyperAgent, Browser-Use, Claude CUA, Gemini CUA, and OpenAI CUA.
      - name: Stealth and Proxies
        description: Anti-detection features, residential/datacenter proxies, static IPs, and multi-region routing.
      - name: Browser Profiles
        description: Persist authenticated state and cookies across sessions.
      - name: CAPTCHA Solving
        description: Built-in CAPTCHA handling for protected sites.
      - name: Extensions and Uploads
        description: Add custom Chrome extensions and handle file uploads/downloads.
      - name: Sandbox Snapshots
        description: Save and restore sandbox state and shared volumes for long-running agent work.
      - name: MCP Server
        description: Model Context Protocol server for use inside Claude Desktop, Cursor, and other MCP clients.
    useCases:
      - name: Production Web Agents
        description: Power agents that browse, click, and complete real workflows on third-party sites.
      - name: Large-Scale Data Extraction
        description: Run scrape and crawl jobs across millions of pages with proxy rotation.
      - name: Computer Use Agents
        description: Provide a stealthy browser for Claude, Gemini, and OpenAI computer-use models.
      - name: Lead and Market Research
        description: Crawl sites and extract structured records into CRMs and data warehouses.
      - name: RL and Eval Environments
        description: Use sandbox snapshots to train and evaluate web-using agents.
    integrations:
      - name: HyperAgent
      - name: Browser-Use
      - name: Playwright
      - name: Puppeteer
      - name: Stagehand
      - name: OpenAI Function Calling
      - name: Anthropic Tool Use
      - name: LangChain
      - name: LlamaIndex
      - name: MCP
      - name: X402 Payment Protocol
    authentication:
      - type: API Key
        description: Account API keys passed via an HTTP header authenticate all REST and SDK calls.
common:
  - type: Website
    url: https://hyperbrowser.ai
  - type: Documentation
    url: https://hyperbrowser.ai/docs
  - type: Blog
    url: https://hyperbrowser.ai/blog
  - type: GitHubOrganization
    url: https://github.com/hyperbrowserai
  - type: Pricing
    url: https://hyperbrowser.ai/pricing
  - type: SignUp
    url: https://app.hyperbrowser.ai/signup
  - type: TermsOfService
    url: https://hyperbrowser.ai/terms
  - type: PrivacyPolicy
    url: https://hyperbrowser.ai/privacy
maintainers:
  - FN: Kin Lane
    email: [email protected]