agent-browser
๐ฏSkillfrom vercel-labs/agent-browser
Automates web browsing tasks by navigating websites, extracting content, interacting with elements, and capturing screenshots programmatically
Overview
The agent-browser is a powerful browser automation tool designed to simplify web interactions, testing, and data extraction. It allows users to programmatically navigate websites, interact with web elements, fill forms, take screenshots, and perform complex browser-based tasks through a command-line interface.
Key Features
- Comprehensive web interaction commands (click, type, fill, scroll, drag)
- Advanced element selection using refs and semantic locators
- Screenshot and video recording capabilities
- Detailed page analysis and element snapshots
- Device and viewport emulation
Who is this for?
Web developers, QA engineers, and automation specialists will find agent-browser invaluable for streamlining web testing, creating automated workflows, and extracting web data. Its flexible command set and intuitive interface make complex browser interactions simple and reproducible, reducing manual effort and increasing testing efficiency.
Same repository
vercel-labs/agent-browser(11 items)
Installation
npx vibeindex add vercel-labs/agent-browser --skill agent-browsernpx skills add vercel-labs/agent-browser --skill agent-browser~/.claude/skills/agent-browser/SKILL.mdSKILL.md
More from this repository10
Headless browser automation for AI agents
Systematically explores and tests web applications to find bugs, UX issues, and other problems.
Skill for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Connects to running Electron apps and controls them programmatically.
Skill from agent-browser, a headless browser automation CLI for AI agents with a fast Rust binary and Node.js fallback for cross-platform support.
A browser automation CLI for AI agents by Vercel Labs, enabling website navigation, form filling, button clicking, screenshot capture, and data extraction through simple commands.
Skill
A concise, practical guide for creating specialized skills that extend Claude's capabilities with domain-specific knowledge and workflows.
Run agent-browser browser automation on AWS Bedrock AgentCore cloud browser sessions, resolving credentials automatically from environment variables or the AWS CLI. All standard agent-browser commands (open, snapshot, click, screenshot, close) work identically โ only the browser runtime changes to a managed AWS-hosted session.
Skill
Skill