browser-use-apiCloud browser automation via Browser Use API. Use when you need AI-driven web browsing, scraping, form filling, or multi-step web tasks without local browser control. Triggers on "browser use", "cloud browser", "scrape website", "automate web task", or when local browser isn't available/suitable.
Install via ClawdBot CLI:
clawdbot install jfrux/browser-use-apiCloud-based AI browser automation. Send a task in plain English, get structured results.
# Submit task
curl -s -X POST https://api.browser-use.com/api/v2/tasks \
-H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"task": "Go to example.com and extract the main heading"}'
# Poll for result (replace TASK_ID)
curl -s "https://api.browser-use.com/api/v2/tasks/TASK_ID" \
-H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY"Use scripts/browser-use.sh for simpler execution:
# Run task and wait for result
./scripts/browser-use.sh "Go to hacker news and get the top 3 stories"
# Just submit (don't wait)
./scripts/browser-use.sh --no-wait "Search Google for AI news"POST https://api.browser-use.com/api/v2/tasksBody:
{
"task": "Plain English description of what to do",
"llm": "gemini-3-flash-preview" // optional, default is fast model
}Response:
{
"id": "task-uuid",
"sessionId": "session-uuid"
}GET https://api.browser-use.com/api/v2/tasks/{taskId}Response fields:
status: pending | started | finished | failedoutput: Result text when finishedsteps: Array of actions taken (with screenshots)cost: Cost in dollars (e.g., "0.02")isSuccess: Boolean resultPOST https://api.browser-use.com/api/v2/tasks/{taskId}/stop~$0.01-0.05 per task depending on complexity. Check balance:
curl -s https://api.browser-use.com/api/v2/credits \
-H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY"web_fetch instead)browser tool)Generated Mar 1, 2026
Automate daily checks on competitor websites to extract product prices and availability. The skill can navigate through product pages, handle dynamic content, and return structured data for analysis, enabling businesses to adjust pricing strategies in real-time.
Scrape property listings from multiple real estate portals to gather details like price, location, and amenities. It handles complex site structures and anti-scraping measures, providing consolidated data for market analysis and investment decisions.
Automate the collection of job postings from various career sites to analyze trends in skills, salaries, and demand. The skill can fill search forms, navigate results pages, and extract key information for HR and recruitment agencies.
Gather data from scientific journals and databases by automating searches and extracting publication details, abstracts, and citations. This supports researchers in literature reviews and data synthesis without manual browsing.
Monitor brand mentions and trends across social media platforms by automating login, scrolling, and data extraction. It captures screenshots and text for sentiment analysis and marketing insights in regulated or complex environments.
Offer tiered subscription plans based on usage volume, such as tasks per month, with premium features like priority processing and advanced analytics. This provides recurring revenue and scales with customer demand for automated web tasks.
Charge customers per task executed, with pricing based on complexity, such as $0.01-$0.05 per task as noted in the skill. This attracts users with sporadic needs and allows flexible scaling without upfront commitments.
License the technology to large corporations for internal use, such as in data analytics or customer service departments, with customization and integration support. This generates high-value contracts and long-term partnerships.
💬 Integration Tip
Set up the BROWSER_USE_API_KEY environment variable securely and use the provided helper script for quick testing before integrating into production workflows.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with w...
Playwright-based web scraping OpenClaw Skill with anti-bot protection. Successfully tested on complex sites like Discuss.com.hk.
Browser automation and web scraping with Playwright. Forms, screenshots, data extraction. Works standalone or via MCP. Testing included.
Performs deep scraping of complex sites like YouTube using containerized Crawlee, extracting validated, ad-free transcripts and content as JSON output.
Automate web tasks like form filling, data scraping, testing, monitoring, and scheduled jobs with multi-browser support and retry mechanisms.
Web scraping and content comprehension agent — multi-strategy extraction with cascade fallback, news detection, boilerplate removal, structured metadata, and...