agent-browser
agent-browser lets you script repetitive web workflows by automating clicks, form inputs, and navigation across pages. Perfect for testing, data collection, or hands-off browser control, it integrates seamlessly into your automation pipelines.
agent-browser is a browser automation tool designed to script repetitive web workflows by automating clicks, form inputs, and navigation across pages. It excels at automating web interactions like form filling, clicking, and navigation with a weight of 0.95, making it ideal for testing, data collection, and hands-off browser control integrated into your automation pipelines.
AI-generated summary based on this skill's SKILL.md
Install
vercel-labs/open-agents/agent-browser · repository language: TypeScript
git clone https://github.com/vercel-labs/open-agents
cp -r open-agents/.agents/skills/agent-browser ~/.claude/skills/agent-browserFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is agent-browser used for?
agent-browser is a browser automation tool designed to script repetitive web workflows by automating clicks, form inputs, and navigation across pages. It excels at automating web interactions like form filling, clicking, and navigation with a weight of 0.95, making it ideal for testing, data collection, and hands-off browser control integrated into your automation pipelines.
Can agent-browser extract data from web pages?
Yes, agent-browser supports extracting data and content from web pages programmatically, which is one of its core capabilities with a weight of 0.85. This makes agent-browser particularly useful for web scraping tasks where you need to pull structured or unstructured content from multiple pages as part of an automated workflow.
How can I use agent-browser for web scraping and form filling?
agent-browser enables web scraping and form filling by allowing you to script browser interactions programmatically. You can automate the process of navigating to pages, locating form fields, filling them with data, and submitting forms—all without manual intervention. This capability makes agent-browser perfect for bulk data entry, testing workflows, or collecting information from multiple web sources.
Does agent-browser support headless browser automation?
Yes, agent-browser supports headless browser automation via CLI or API for scripting, with a weight of 0.65. This means agent-browser can control a browser without a graphical interface, making it ideal for server-side automation, continuous integration pipelines, and scenarios where you need to run browser tasks in the background without visual overhead.
Can agent-browser take screenshots of websites?
agent-browser includes the capability to capture screenshots and visual records of web pages, with a weight of 0.7. This feature allows agent-browser to create visual documentation of web pages at specific points in your automation workflow, useful for testing verification, reporting, or archiving page states.
Is agent-browser suitable for automated web application testing?
Yes, agent-browser is well-suited for testing web applications and user workflows automatically, with a weight of 0.8. agent-browser can simulate user interactions, validate page behavior, and verify that web applications function correctly across different scenarios—making it a valuable tool for quality assurance and regression testing. agent-browser is released under the MIT license, allowing flexible use in your testing infrastructure.
SKILL.md
rendered from the published skill — quoted content, verbatim
Browser Automation with agent-browser
Quick start
agent-browser open <url> # Navigate to page
agent-browser snapshot -i # Get interactive elements with refs
agent-browser click @e1 # Click element by ref
agent-browser fill @e2 "text" # Fill input by ref
agent-browser close # Close browser
Core workflow
- Navigate:
agent-browser open <url> - Snapshot:
agent-browser snapshot -i(returns elements with refs like@e1,@e2) - Interact using refs from the snapshot
- Re-snapshot after navigation or significant DOM changes
Commands
Navigation
```bash agent-browser open <url> # Navigate to URL (aliases: goto, navigate) # Supports: https://, http://, file://, about:, data:// # Auto-prepends https:// if no protocol
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 9 files
.agents/skills/agent-browser/SKILL.md
.agents/skills/agent-browser/references/authentication.md
.agents/skills/agent-browser/references/proxy-support.md
.agents/skills/agent-browser/references/session-management.md
.agents/skills/agent-browser/references/snapshot-refs.md
.agents/skills/agent-browser/references/video-recording.md
.agents/skills/agent-browser/templates/authenticated-session.sh
.agents/skills/agent-browser/templates/capture-workflow.sh
.agents/skills/agent-browser/templates/form-automation.sh