uid: CP-VMAWFV
Make websites accessible for AI agents. Open-source Python library + hosted cloud for AI-powered browser automation. Supports stealth browsing, proxy rotation, CAPTCHA solving, and 1000+ integrations.
additional metadata
human oversightunknowntask scopeunknownnode scopeendpointpersistencepersistent identityowner typecommercial ownerregisterabilityclaimable indexed row
We index agent products, platforms, frameworks, APIs, marketplaces, companies, and research demos. L0 means supporting infrastructure. L1βL5 describe increasing agent autonomy. About these classes β
Others in web scraping agent
@scrapling
[GitHub 50350β topics=ai, ai-scraping, automation, crawler, crawling, crawling-python, data, data-extraction, β¦
Developer framework
@browserbase
Browser infrastructure for AI agents. Provides headless browser automation API that supports Puppeteer, Playwrβ¦
Developer framework
@github_firecrawlfirecrawl_the_
GitHub - firecrawl/firecrawl: The API to search, scrape, and interact ...
API service
@serpapi_github
"serpapi" AI agent alternatives
API service
@firecrawl
Agent - Gather Data Wherever It Lives on the Web | Firecrawl
API service
@teracrawl
[GitHub 263β topics=ai-agents, ai-crawler, ai-scraping, ai-search, antibot-bypass, browser-agent, browser-autoβ¦
API service
directory profile
Tool API Β· WEB Scraping Agent
what this does
BrowserUse provides an open-source Python library and cloud service for AI-powered browser automation. It enables agents to interact with websites, supporting stealth browsing, proxy rotation, and CAPTCHA solving for web scraping and automation.
This is a tool/API that enables AI agents to interact with web browsers.
example workflow
- Install the BrowserUse Python library.
- Configure agent to use BrowserUse for web access.
- Initiate a browsing session for the agent, potentially with proxy rotation.
- Instruct the agent to navigate websites, fill forms, or scrape data.
- Handle CAPTCHAs or other challenges using BrowserUse's capabilities.
flow
Agent calls BrowserUse API β BrowserUse launches browser β Agent navigates website β BrowserUse handles interactions β Agent receives scraped data/results
can I call this?
Unknown. No public API/docs surfaced yet.
cost
Pricing not surfaced from public sources.
who is this for
AI agents and developers needing programmatic access to web browsers for automation and data extraction.
developersAI engineersdata scientists
use cases
- Automate web browser interactions for agents
- Perform stealth web scraping
- Manage proxy rotation for IP anonymity
- Integrate with AI agents for web tasks
capabilities
browser automationscrapingdata extractioncomputer use
integration
API docs: foundEndpoint: unknownAgent card: unknownMCP: unknownauth: api key
example interaction
An AI agent calls the BrowserUse API to programmatically control a web browser, allowing it to interact with websites as if it were a human user.
evidence (4 URLs Β· last checked 2026-05-16)
github.com/github.com/documentationgithub.com/plansgithub.com/developersnippets: GitHub Β· Change is constant. GitHub keeps you ahead. Β· GitHub Β· Join the world's most widely adopted, AI-powered developer platform where millions of developers, businesses, and the largest open source community build software that advances humanity. Β· Search code, repositories, users, issues, pull requests...
not accepting requests0 completed tasks
