agent-browser

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

agent-browser - Headless Browser for AI Agents

agent-browser - 面向AI Agent的无头浏览器

When to use this skill

何时使用该技能

  • Web automation and E2E testing
  • Scraping data from modern web apps
  • Deterministic element interaction using accessibility tree refs
  • Isolated browser sessions for different agent tasks

  • Web自动化与端到端测试
  • 从现代Web应用中抓取数据
  • 使用无障碍树引用进行确定性元素交互
  • 为不同Agent任务提供隔离的浏览器会话

1. Installation

1. 安装

bash
npx skills add vercel-labs/agent-browser
bash
npx skills add vercel-labs/agent-browser

or

or

npm install -g agent-browser agent-browser install

---
npm install -g agent-browser agent-browser install

---

2. Core Workflow (Deterministic Interaction)

2. 核心工作流(确定性交互)

AI agents should use the snapshot + ref workflow for best results:
  1. Navigate:
    agent-browser open <url>
  2. Snapshot:
    agent-browser snapshot -i
    (Returns tree with refs like @e1, @e2)
  3. Interact:
    agent-browser click @e1
    or
    agent-browser fill @e2 "text"
  4. Repeat: Snapshot again if page changes

AI Agent应使用“快照+引用”工作流以获得最佳效果:
  1. 导航
    agent-browser open <url>
  2. 快照
    agent-browser snapshot -i
    (返回带有@e1、@e2等引用的树结构)
  3. 交互
    agent-browser click @e1
    agent-browser fill @e2 "text"
  4. 重复:如果页面发生变化,再次生成快照

3. Key Commands

3. 关键命令

CommandDescription
open <url>
Navigate to a URL
snapshot
Get accessibility tree with refs
click <sel>
Click element (by ref or CSS)
fill <sel> <text>
Clear and fill input
screenshot [path]
Take page screenshot
close
Quit browser session

命令描述
open <url>
导航至指定URL
snapshot
获取带引用的无障碍树
click <sel>
点击元素(通过引用或CSS选择器)
fill <sel> <text>
清空并填充输入框
screenshot [path]
截取页面截图
close
退出浏览器会话

4. Advanced Features

4. 高级功能

  • Isolated Sessions: Use
    --session <name>
    to isolate cookies/storage.
  • Persistent Profiles: Use
    --profile <path>
    to persist login sessions.
  • Semantic Locators:
    find role button click --name "Submit"
  • JavaScript Execution:
    eval "window.scrollTo(0, 100)"

  • 隔离会话:使用
    --session <name>
    隔离Cookie/存储。
  • 持久化配置文件:使用
    --profile <path>
    保留登录会话。
  • 语义定位器
    find role button click --name "Submit"
  • JavaScript执行
    eval "window.scrollTo(0, 100)"

Quick Reference

快速参考

bash
undefined
bash
undefined

Optimal AI Workflow

最佳AI工作流

agent-browser open example.com agent-browser snapshot -i --json
agent-browser open example.com agent-browser snapshot -i --json

(AI parses refs)

(AI解析引用)

agent-browser click @e2
undefined
agent-browser click @e2
undefined