agent-browser 浏览器自动化工具：命令行网页操作与测试指南

agent-browser by everyinc/compound-engineering-plugin

323 周安装量

11,000 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/everyinc/compound-engineering-plugin --skill agent-browser

自动化命令行工具测试

🇨🇳中文介绍

使用 agent-browser 进行浏览器自动化

CLI 直接通过 CDP 使用 Chrome/Chromium。通过 npm i -g agent-browser、brew install agent-browser 或 cargo install agent-browser 安装。运行 agent-browser install 以下载 Chrome。运行 agent-browser upgrade 以更新到最新版本。

核心工作流程

每次浏览器自动化都遵循以下模式：

导航 : agent-browser open <url>
快照 : agent-browser snapshot -i (获取元素引用，如 @e1, )

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

使用身份验证保险库进行身份验证（推荐）

# 保存凭据一次（使用 AGENT_BROWSER_ENCRYPTION_KEY 加密）
# 推荐：通过 stdin 管道传输密码以避免 shell 历史记录暴露
echo "pass" | agent-browser auth save github --url https://github.com/login --username user --password-stdin

# 使用保存的配置文件登录（LLM 永远不会看到密码）
agent-browser auth login github

# 列出/显示/删除配置文件
agent-browser auth list
agent-browser auth show github
agent-browser auth delete github

auth login 在交互之前会等待用户名/密码/提交选择器出现，其超时时间与默认操作超时时间相关联。

使用状态持久化进行身份验证

# 登录一次并保存状态
agent-browser open https://app.example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "$USERNAME"
agent-browser fill @e2 "$PASSWORD"
agent-browser click @e3
agent-browser wait --url "**/dashboard"
agent-browser state save auth.json

# 在未来的会话中重用
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboard

# 在浏览器重启时自动保存/恢复 cookies 和 localStorage
agent-browser --session-name myapp open https://app.example.com/login
# ... 登录流程 ...
agent-browser close  # 状态自动保存到 ~/.agent-browser/sessions/

# 下次，状态自动加载
agent-browser --session-name myapp open https://app.example.com/dashboard

# 静态加密状态
export AGENT_BROWSER_ENCRYPTION_KEY=$(openssl rand -hex 32)
agent-browser --session-name secure open https://app.example.com

# 管理保存的状态
agent-browser state list
agent-browser state show myapp-default.json
agent-browser state clear myapp
agent-browser state clean --older-than 7

Iframe 内容会自动内联到快照中。Iframe 内的引用带有框架上下文，因此你可以直接与它们交互。

agent-browser open https://example.com/checkout
agent-browser snapshot -i
# @e1 [heading] "Checkout"
# @e2 [Iframe] "payment-frame"
#   @e3 [input] "Card number"
#   @e4 [input] "Expiry"
#   @e5 [button] "Pay"

# 直接交互——无需切换框架
agent-browser fill @e3 "4111111111111111"
agent-browser fill @e4 "12/28"
agent-browser click @e5

# 要将快照限定到一个 iframe：
agent-browser frame @e2
agent-browser snapshot -i         # 仅 iframe 内容
agent-browser frame main          # 返回主框架

agent-browser open https://example.com/products
agent-browser snapshot -i
agent-browser get text @e5           # 获取特定元素文本
agent-browser get text body > page.txt  # 获取所有页面文本

# JSON 输出用于解析
agent-browser snapshot -i --json
agent-browser get text @e1 --json

agent-browser --session site1 open https://site-a.com
agent-browser --session site2 open https://site-b.com

agent-browser --session site1 snapshot -i
agent-browser --session site2 snapshot -i

agent-browser session list

连接到现有的 Chrome

# 自动发现启用了远程调试的正在运行的 Chrome
agent-browser --auto-connect open https://example.com
agent-browser --auto-connect snapshot

# 或者使用显式的 CDP 端口
agent-browser --cdp 9222 snapshot

自动连接通过 DevToolsActivePort、常见调试端口（9222, 9229）发现 Chrome，如果基于 HTTP 的 CDP 发现失败，则回退到直接的 WebSocket 连接。

配色方案（深色模式）

# 通过标志持久化深色模式（适用于所有页面和新标签页）
agent-browser --color-scheme dark open https://example.com

# 或者通过环境变量
AGENT_BROWSER_COLOR_SCHEME=dark agent-browser open https://example.com

# 或者在会话期间设置（对后续命令保持有效）
agent-browser set media dark

视口和响应式测试

# 设置自定义视口大小（默认为 1280x720）
agent-browser set viewport 1920 1080
agent-browser screenshot desktop.png

# 测试移动端宽度布局
agent-browser set viewport 375 812
agent-browser screenshot mobile.png

# Retina/HiDPI：相同的 CSS 布局，2 倍像素密度
# 截图保持逻辑视口大小，但内容以更高 DPI 渲染
agent-browser set viewport 1920 1080 2
agent-browser screenshot retina.png

# 设备模拟（一步设置视口 + 用户代理）
agent-browser set device "iPhone 14"
agent-browser screenshot device.png

scale 参数（第三个参数）设置 window.devicePixelRatio 而不改变 CSS 布局。在测试视网膜渲染或捕获更高分辨率截图时使用它。

可视化浏览器（调试）

agent-browser --headed open https://example.com
agent-browser highlight @e1          # 高亮元素
agent-browser inspect                # 为活动页面打开 Chrome DevTools
agent-browser record start demo.webm # 录制会话
agent-browser profiler start         # 启动 Chrome DevTools 性能分析
agent-browser profiler stop trace.json # 停止并保存性能分析文件（路径可选）

使用 AGENT_BROWSER_HEADED=1 通过环境变量启用可视化模式。浏览器扩展在可视化和无头模式下都有效。

本地文件（PDF、HTML）

# 使用 file:// URL 打开本地文件
agent-browser --allow-file-access open file:///path/to/document.pdf
agent-browser --allow-file-access open file:///path/to/page.html
agent-browser screenshot output.png

iOS 模拟器（移动端 Safari）

# 列出可用的 iOS 模拟器
agent-browser device list

# 在特定设备上启动 Safari
agent-browser -p ios --device "iPhone 16 Pro" open https://example.com

# 与桌面端相同的工作流程 - 快照、交互、重新快照
agent-browser -p ios snapshot -i
agent-browser -p ios tap @e1          # 点击（click 的别名）
agent-browser -p ios fill @e2 "text"
agent-browser -p ios swipe up         # 移动端特定手势

# 截图
agent-browser -p ios screenshot mobile.png

# 关闭会话（关闭模拟器）
agent-browser -p ios close

要求： 安装 Xcode 的 macOS，Appium（npm install -g appium && appium driver install xcuitest）

真实设备： 如果预先配置好，可以与物理 iOS 设备配合使用。使用 --device "<UDID>"，其中 UDID 来自 xcrun xctrace list devices。

所有安全功能都是可选的。默认情况下，agent-browser 对导航、操作或输出不施加任何限制。

内容边界（推荐用于 AI 代理）

启用 --content-boundaries 可以将页面来源的输出包装在标记中，帮助 LLM 区分工具输出和不受信任的页面内容：

export AGENT_BROWSER_CONTENT_BOUNDARIES=1
agent-browser snapshot
# 输出：
# --- AGENT_BROWSER_PAGE_CONTENT nonce=<hex> origin=https://example.com ---
# [无障碍功能树]
# --- END_AGENT_BROWSER_PAGE_CONTENT nonce=<hex> ---

限制导航到受信任的域名。通配符如 *.example.com 也匹配裸域名 example.com。对非允许域名的子资源请求、WebSocket 和 EventSource 连接也会被阻止。请包含你的目标页面所依赖的 CDN 域名：

export AGENT_BROWSER_ALLOWED_DOMAINS="example.com,*.example.com"
agent-browser open https://example.com        # 允许
agent-browser open https://malicious.com       # 阻止

使用策略文件来限制破坏性操作：

export AGENT_BROWSER_ACTION_POLICY=./policy.json

示例 policy.json：

{ "default": "deny", "allow": ["navigate", "snapshot", "click", "scroll", "wait", "get"] }

身份验证保险库操作（auth login 等）绕过操作策略，但域名白名单仍然适用。

防止大页面导致上下文泛滥：

export AGENT_BROWSER_MAX_OUTPUT=50000

差异比较（验证更改）

执行操作后使用 diff snapshot 来验证其是否产生了预期效果。这将当前的无障碍功能树与会话中上次拍摄的快照进行比较。

# 典型工作流程：快照 -> 操作 -> 差异比较
agent-browser snapshot -i          # 拍摄基线快照
agent-browser click @e2            # 执行操作
agent-browser diff snapshot        # 查看发生了什么变化（自动与上次快照比较）

用于视觉回归测试或监控：

# 保存基线截图，稍后比较
agent-browser screenshot baseline.png
# ... 时间流逝或发生更改 ...
agent-browser diff screenshot --baseline baseline.png

# 比较暂存环境与生产环境
agent-browser diff url https://staging.example.com https://prod.example.com --screenshot

diff snapshot 输出使用 + 表示添加，- 表示删除，类似于 git diff。diff screenshot 生成一个差异图像，其中更改的像素以红色高亮显示，并附带一个不匹配百分比。

超时和慢速页面

默认超时时间为 25 秒。这可以通过 AGENT_BROWSER_DEFAULT_TIMEOUT 环境变量（以毫秒为单位的值）覆盖。对于慢速网站或大型页面，请使用显式等待，而不是依赖默认超时：

# 等待网络活动稳定（最适合慢速页面）
agent-browser wait --load networkidle

# 等待特定元素出现
agent-browser wait "#content"
agent-browser wait @e1

# 等待特定的 URL 模式（重定向后有用）
agent-browser wait --url "**/dashboard"

# 等待 JavaScript 条件
agent-browser wait --fn "document.readyState === 'complete'"

# 作为最后手段，等待固定时长（毫秒）
agent-browser wait 5000

当处理持续慢速的网站时，在 open 之后使用 wait --load networkidle 以确保页面在拍摄快照之前完全加载。如果特定元素渲染缓慢，请直接使用 wait <selector> 或 wait @ref 等待它。

会话管理和清理

当同时运行多个代理或自动化时，始终使用命名会话以避免冲突：

# 每个代理获得自己独立的会话
agent-browser --session agent1 open site-a.com
agent-browser --session agent2 open site-b.com

# 检查活动会话
agent-browser session list

完成后始终关闭浏览器会话，以避免进程泄漏：

agent-browser close                    # 关闭默认会话
agent-browser --session agent1 close   # 关闭特定会话

如果之前的会话没有正确关闭，守护进程可能仍在运行。在开始新工作之前，使用 agent-browser close 来清理它。

要在不活动一段时间后自动关闭守护进程（适用于临时/CI 环境）：

AGENT_BROWSER_IDLE_TIMEOUT_MS=60000 agent-browser open example.com

引用生命周期（重要）

当页面更改时，引用（@e1、@e2 等）会失效。在以下操作后务必重新快照：

点击链接或按钮进行导航
表单提交
动态内容加载（下拉菜单、模态框）

agent-browser click @e5              # 导航到新页面
agent-browser snapshot -i            # 必须重新快照
agent-browser click @e1              # 使用新的引用

标注截图（视觉模式）

使用 --annotate 拍摄带有编号标签覆盖在交互元素上的截图。每个标签 [N] 映射到引用 @eN。这也会缓存引用，因此你可以立即与元素交互，而无需单独的快照。

agent-browser screenshot --annotate
# 输出包括图像路径和图例：
#   [1] @e1 button "Submit"
#   [2] @e2 link "Home"
#   [3] @e3 textbox "Email"
agent-browser click @e2              # 使用标注截图中的引用进行点击

在以下情况下使用标注截图：

页面有未标记的图标按钮或纯视觉元素
你需要验证视觉布局或样式
存在画布或图表元素（对文本快照不可见）
你需要关于元素位置的空间推理

语义定位器（引用的替代方案）

当引用不可用或不可靠时，使用语义定位器：

agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"
agent-browser find role button click --name "Submit"
agent-browser find placeholder "Search" type "query"
agent-browser find testid "submit-btn" click

JavaScript 评估（eval）

使用 eval 在浏览器上下文中运行 JavaScript。Shell 引用可能会破坏复杂的表达式——使用 --stdin 或 -b 来避免问题。

# 简单表达式使用常规引用即可
agent-browser eval 'document.title'
agent-browser eval 'document.querySelectorAll("img").length'

# 复杂的 JS：使用 --stdin 和 heredoc（推荐）
agent-browser eval --stdin <<'EVALEOF'
JSON.stringify(
  Array.from(document.querySelectorAll("img"))
    .filter(i => !i.alt)
    .map(i => ({ src: i.src.split("/").pop(), width: i.width }))
)
EVALEOF

# 替代方案：base64 编码（避免所有 shell 转义问题）
agent-browser eval -b "$(echo -n 'Array.from(document.querySelectorAll("a")).map(a => a.href)' | base64)"

为什么这很重要： 当 shell 处理你的命令时，内部的双引号、! 字符（历史扩展）、反引号和 $() 都可能在 JavaScript 到达 agent-browser 之前破坏它。--stdin 和 -b 标志完全绕过了 shell 解释。

单行，无嵌套引号 -> 常规的 eval 'expression' 使用单引号即可
嵌套引号、箭头函数、模板字面量或多行 -> 使用 eval --stdin <<'EVALEOF'
程序化/生成的脚本 -> 使用 eval -b 配合 base64

在项目根目录创建 agent-browser.json 用于持久化设置：

{
  "headed": true,
  "proxy": "http://localhost:8080",
  "profile": "./browser-data"
}

优先级（从低到高）：~/.agent-browser/config.json < ./agent-browser.json < 环境变量 < CLI 标志。使用 --config <path> 或 AGENT_BROWSER_CONFIG 环境变量指定自定义配置文件（如果缺失/无效则退出并报错）。所有 CLI 选项都映射到驼峰式键（例如，--executable-path -> "executablePath"）。布尔标志接受 true/false 值（例如，--headed false 会覆盖配置）。用户和项目配置的扩展会被合并，而不是替换。

参考文档	何时使用
references/commands.md	包含所有选项的完整命令参考
references/snapshot-refs.md	引用生命周期、失效规则、故障排除
references/session-management.md	并行会话、状态持久化、并发抓取
references/authentication.md	登录流程、OAuth、2FA 处理、状态重用
references/video-recording.md	用于调试和文档记录的录制工作流程
references/profiling.md	用于性能分析的 Chrome DevTools 性能分析
references/proxy-support.md	代理配置、地理测试、轮换代理

浏览器引擎选择

使用 --engine 选择本地浏览器引擎。默认为 chrome。

# 使用 Lightpanda（快速无头浏览器，需要单独安装）
agent-browser --engine lightpanda open example.com

# 通过环境变量
export AGENT_BROWSER_ENGINE=lightpanda
agent-browser open example.com

# 使用自定义二进制路径
agent-browser --engine lightpanda --executable-path /path/to/lightpanda open example.com

chrome (默认) -- 通过 CDP 使用 Chrome/Chromium
lightpanda -- 通过 CDP 使用 Lightpanda 无头浏览器（比 Chrome 快 10 倍，内存少 10 倍）

Lightpanda 不支持 --extension、--profile、--state 或 --allow-file-access。从 https://lightpanda.io/docs/open-source/installation 安装 Lightpanda。

模板	描述
templates/form-automation.sh	带验证的表单填充
templates/authenticated-session.sh	登录一次，重用状态
templates/capture-workflow.sh	带截图的内容提取

./templates/form-automation.sh https://example.com/form
./templates/authenticated-session.sh https://app.example.com/login
./templates/capture-workflow.sh https://example.com ./output

🇺🇸English

Browser Automation with agent-browser

The CLI uses Chrome/Chromium via CDP directly. Install via npm i -g agent-browser, brew install agent-browser, or cargo install agent-browser. Run agent-browser install to download Chrome. Run agent-browser upgrade to update to the latest version.

Core Workflow

Every browser automation follows this pattern:

Navigate : agent-browser open <url>
Snapshot : agent-browser snapshot -i (get element refs like @e1, @e2)
Interact : Use refs to click, fill, select
Re-snapshot : After navigation or DOM changes, get fresh refs

agent-browser open https://example.com/form

agent-browser snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"

agent-browser fill @e1 "user@example.com"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i  # Check result

Command Chaining

Commands can be chained with && in a single shell invocation. The browser persists between commands via a background daemon, so chaining is safe and more efficient than separate calls.

# Chain open + wait + snapshot in one call
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i

# Chain multiple interactions
agent-browser fill @e1 "user@example.com" && agent-browser fill @e2 "password123" && agent-browser click @e3

# Navigate and capture
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser screenshot page.png

When to chain: Use && when you don't need to read the output of an intermediate command before proceeding (e.g., open + wait + screenshot). Run commands separately when you need to parse the output first (e.g., snapshot to discover refs, then interact using those refs).

Handling Authentication

When automating a site that requires login, choose the approach that fits:

Option 1: Import auth from the user's browser (fastest for one-off tasks)

# Connect to the user's running Chrome (they're already logged in)
agent-browser --auto-connect state save ./auth.json
# Use that auth state
agent-browser --state ./auth.json open https://app.example.com/dashboard

State files contain session tokens in plaintext -- add to .gitignore and delete when no longer needed. Set AGENT_BROWSER_ENCRYPTION_KEY for encryption at rest.

Option 2: Persistent profile (simplest for recurring tasks)

# First run: login manually or via automation
agent-browser --profile ~/.myapp open https://app.example.com/login
# ... fill credentials, submit ...

# All future runs: already authenticated
agent-browser --profile ~/.myapp open https://app.example.com/dashboard

Option 3: Session name (auto-save/restore cookies + localStorage)

agent-browser --session-name myapp open https://app.example.com/login
# ... login flow ...
agent-browser close  # State auto-saved

# Next time: state auto-restored
agent-browser --session-name myapp open https://app.example.com/dashboard

Option 4: Auth vault (credentials stored encrypted, login by name)

echo "$PASSWORD" | agent-browser auth save myapp --url https://app.example.com/login --username user --password-stdin
agent-browser auth login myapp

auth login navigates with load and then waits for login form selectors to appear before filling/clicking, which is more reliable on delayed SPA login screens.

Option 5: State file (manual save/load)

# After logging in:
agent-browser state save ./auth.json
# In a future session:
agent-browser state load ./auth.json
agent-browser open https://app.example.com/dashboard

See references/authentication.md for OAuth, 2FA, cookie-based auth, and token refresh patterns.

Essential Commands

# Navigation
agent-browser open <url>              # Navigate (aliases: goto, navigate)
agent-browser close                   # Close browser

# Snapshot
agent-browser snapshot -i             # Interactive elements with refs (recommended)
agent-browser snapshot -i -C          # Include cursor-interactive elements (divs with onclick, cursor:pointer)
agent-browser snapshot -s "#selector" # Scope to CSS selector

# Interaction (use @refs from snapshot)
agent-browser click @e1               # Click element
agent-browser click @e1 --new-tab     # Click and open in new tab
agent-browser fill @e2 "text"         # Clear and type text
agent-browser type @e2 "text"         # Type without clearing
agent-browser select @e1 "option"     # Select dropdown option
agent-browser check @e1               # Check checkbox
agent-browser press Enter             # Press key
agent-browser keyboard type "text"    # Type at current focus (no selector)
agent-browser keyboard inserttext "text"  # Insert without key events
agent-browser scroll down 500         # Scroll page
agent-browser scroll down 500 --selector "div.content"  # Scroll within a specific container

# Get information
agent-browser get text @e1            # Get element text
agent-browser get url                 # Get current URL
agent-browser get title               # Get page title
agent-browser get cdp-url             # Get CDP WebSocket URL

# Wait
agent-browser wait @e1                # Wait for element
agent-browser wait --load networkidle # Wait for network idle
agent-browser wait --url "**/page"    # Wait for URL pattern
agent-browser wait 2000               # Wait milliseconds
agent-browser wait --text "Welcome"    # Wait for text to appear (substring match)
agent-browser wait --fn "!document.body.innerText.includes('Loading...')"  # Wait for text to disappear
agent-browser wait "#spinner" --state hidden  # Wait for element to disappear

# Downloads
agent-browser download @e1 ./file.pdf          # Click element to trigger download
agent-browser wait --download ./output.zip     # Wait for any download to complete
agent-browser --download-path ./downloads open <url>  # Set default download directory

# Network
agent-browser network requests                 # Inspect tracked requests
agent-browser network route "**/api/*" --abort  # Block matching requests
agent-browser network har start                # Start HAR recording
agent-browser network har stop ./capture.har   # Stop and save HAR file

# Viewport & Device Emulation
agent-browser set viewport 1920 1080          # Set viewport size (default: 1280x720)
agent-browser set viewport 1920 1080 2        # 2x retina (same CSS size, higher res screenshots)
agent-browser set device "iPhone 14"          # Emulate device (viewport + user agent)

# Capture
agent-browser screenshot              # Screenshot to temp dir
agent-browser screenshot --full       # Full page screenshot
agent-browser screenshot --annotate   # Annotated screenshot with numbered element labels
agent-browser screenshot --screenshot-dir ./shots  # Save to custom directory
agent-browser screenshot --screenshot-format jpeg --screenshot-quality 80
agent-browser pdf output.pdf          # Save as PDF

# Clipboard
agent-browser clipboard read                      # Read text from clipboard
agent-browser clipboard write "Hello, World!"     # Write text to clipboard
agent-browser clipboard copy                      # Copy current selection
agent-browser clipboard paste                     # Paste from clipboard

# Diff (compare page states)
agent-browser diff snapshot                          # Compare current vs last snapshot
agent-browser diff snapshot --baseline before.txt    # Compare current vs saved file
agent-browser diff screenshot --baseline before.png  # Visual pixel diff
agent-browser diff url <url1> <url2>                 # Compare two pages
agent-browser diff url <url1> <url2> --wait-until networkidle  # Custom wait strategy
agent-browser diff url <url1> <url2> --selector "#main"  # Scope to element

Batch Execution

Execute multiple commands in a single invocation by piping a JSON array of string arrays to batch. This avoids per-command process startup overhead when running multi-step workflows.

echo '[
  ["open", "https://example.com"],
  ["snapshot", "-i"],
  ["click", "@e1"],
  ["screenshot", "result.png"]
]' | agent-browser batch --json

# Stop on first error
agent-browser batch --bail < commands.json

Use batch when you have a known sequence of commands that don't depend on intermediate output. Use separate commands or && chaining when you need to parse output between steps (e.g., snapshot to discover refs, then interact).

Common Patterns

Form Submission

agent-browser open https://example.com/signup
agent-browser snapshot -i
agent-browser fill @e1 "Jane Doe"
agent-browser fill @e2 "jane@example.com"
agent-browser select @e3 "California"
agent-browser check @e4
agent-browser click @e5
agent-browser wait --load networkidle

Authentication with Auth Vault (Recommended)

# Save credentials once (encrypted with AGENT_BROWSER_ENCRYPTION_KEY)
# Recommended: pipe password via stdin to avoid shell history exposure
echo "pass" | agent-browser auth save github --url https://github.com/login --username user --password-stdin

# Login using saved profile (LLM never sees password)
agent-browser auth login github

# List/show/delete profiles
agent-browser auth list
agent-browser auth show github
agent-browser auth delete github

auth login waits for username/password/submit selectors before interacting, with a timeout tied to the default action timeout.

Authentication with State Persistence

# Login once and save state
agent-browser open https://app.example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "$USERNAME"
agent-browser fill @e2 "$PASSWORD"
agent-browser click @e3
agent-browser wait --url "**/dashboard"
agent-browser state save auth.json

# Reuse in future sessions
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboard

Session Persistence

# Auto-save/restore cookies and localStorage across browser restarts
agent-browser --session-name myapp open https://app.example.com/login
# ... login flow ...
agent-browser close  # State auto-saved to ~/.agent-browser/sessions/

# Next time, state is auto-loaded
agent-browser --session-name myapp open https://app.example.com/dashboard

# Encrypt state at rest
export AGENT_BROWSER_ENCRYPTION_KEY=$(openssl rand -hex 32)
agent-browser --session-name secure open https://app.example.com

# Manage saved states
agent-browser state list
agent-browser state show myapp-default.json
agent-browser state clear myapp
agent-browser state clean --older-than 7

Working with Iframes

Iframe content is automatically inlined in snapshots. Refs inside iframes carry frame context, so you can interact with them directly.

agent-browser open https://example.com/checkout
agent-browser snapshot -i
# @e1 [heading] "Checkout"
# @e2 [Iframe] "payment-frame"
#   @e3 [input] "Card number"
#   @e4 [input] "Expiry"
#   @e5 [button] "Pay"

# Interact directly — no frame switch needed
agent-browser fill @e3 "4111111111111111"
agent-browser fill @e4 "12/28"
agent-browser click @e5

# To scope a snapshot to one iframe:
agent-browser frame @e2
agent-browser snapshot -i         # Only iframe content
agent-browser frame main          # Return to main frame

Data Extraction

agent-browser open https://example.com/products
agent-browser snapshot -i
agent-browser get text @e5           # Get specific element text
agent-browser get text body > page.txt  # Get all page text

# JSON output for parsing
agent-browser snapshot -i --json
agent-browser get text @e1 --json

Parallel Sessions

agent-browser --session site1 open https://site-a.com
agent-browser --session site2 open https://site-b.com

agent-browser --session site1 snapshot -i
agent-browser --session site2 snapshot -i

agent-browser session list

Connect to Existing Chrome

# Auto-discover running Chrome with remote debugging enabled
agent-browser --auto-connect open https://example.com
agent-browser --auto-connect snapshot

# Or with explicit CDP port
agent-browser --cdp 9222 snapshot

Auto-connect discovers Chrome via DevToolsActivePort, common debugging ports (9222, 9229), and falls back to a direct WebSocket connection if HTTP-based CDP discovery fails.

Color Scheme (Dark Mode)

# Persistent dark mode via flag (applies to all pages and new tabs)
agent-browser --color-scheme dark open https://example.com

# Or via environment variable
AGENT_BROWSER_COLOR_SCHEME=dark agent-browser open https://example.com

# Or set during session (persists for subsequent commands)
agent-browser set media dark

Viewport & Responsive Testing

# Set a custom viewport size (default is 1280x720)
agent-browser set viewport 1920 1080
agent-browser screenshot desktop.png

# Test mobile-width layout
agent-browser set viewport 375 812
agent-browser screenshot mobile.png

# Retina/HiDPI: same CSS layout at 2x pixel density
# Screenshots stay at logical viewport size, but content renders at higher DPI
agent-browser set viewport 1920 1080 2
agent-browser screenshot retina.png

# Device emulation (sets viewport + user agent in one step)
agent-browser set device "iPhone 14"
agent-browser screenshot device.png

The scale parameter (3rd argument) sets window.devicePixelRatio without changing CSS layout. Use it when testing retina rendering or capturing higher-resolution screenshots.

Visual Browser (Debugging)

agent-browser --headed open https://example.com
agent-browser highlight @e1          # Highlight element
agent-browser inspect                # Open Chrome DevTools for the active page
agent-browser record start demo.webm # Record session
agent-browser profiler start         # Start Chrome DevTools profiling
agent-browser profiler stop trace.json # Stop and save profile (path optional)

Use AGENT_BROWSER_HEADED=1 to enable headed mode via environment variable. Browser extensions work in both headed and headless mode.

Local Files (PDFs, HTML)

# Open local files with file:// URLs
agent-browser --allow-file-access open file:///path/to/document.pdf
agent-browser --allow-file-access open file:///path/to/page.html
agent-browser screenshot output.png

iOS Simulator (Mobile Safari)

# List available iOS simulators
agent-browser device list

# Launch Safari on a specific device
agent-browser -p ios --device "iPhone 16 Pro" open https://example.com

# Same workflow as desktop - snapshot, interact, re-snapshot
agent-browser -p ios snapshot -i
agent-browser -p ios tap @e1          # Tap (alias for click)
agent-browser -p ios fill @e2 "text"
agent-browser -p ios swipe up         # Mobile-specific gesture

# Take screenshot
agent-browser -p ios screenshot mobile.png

# Close session (shuts down simulator)
agent-browser -p ios close

Requirements: macOS with Xcode, Appium (npm install -g appium && appium driver install xcuitest)

Real devices: Works with physical iOS devices if pre-configured. Use --device "<UDID>" where UDID is from xcrun xctrace list devices.

Security

All security features are opt-in. By default, agent-browser imposes no restrictions on navigation, actions, or output.

Content Boundaries (Recommended for AI Agents)

Enable --content-boundaries to wrap page-sourced output in markers that help LLMs distinguish tool output from untrusted page content:

export AGENT_BROWSER_CONTENT_BOUNDARIES=1
agent-browser snapshot
# Output:
# --- AGENT_BROWSER_PAGE_CONTENT nonce=<hex> origin=https://example.com ---
# [accessibility tree]
# --- END_AGENT_BROWSER_PAGE_CONTENT nonce=<hex> ---

Domain Allowlist

Restrict navigation to trusted domains. Wildcards like *.example.com also match the bare domain example.com. Sub-resource requests, WebSocket, and EventSource connections to non-allowed domains are also blocked. Include CDN domains your target pages depend on:

export AGENT_BROWSER_ALLOWED_DOMAINS="example.com,*.example.com"
agent-browser open https://example.com        # OK
agent-browser open https://malicious.com       # Blocked

Action Policy

Use a policy file to gate destructive actions:

export AGENT_BROWSER_ACTION_POLICY=./policy.json

Example policy.json:

{ "default": "deny", "allow": ["navigate", "snapshot", "click", "scroll", "wait", "get"] }

Auth vault operations (auth login, etc.) bypass action policy but domain allowlist still applies.

Output Limits

Prevent context flooding from large pages:

export AGENT_BROWSER_MAX_OUTPUT=50000

Diffing (Verifying Changes)

Use diff snapshot after performing an action to verify it had the intended effect. This compares the current accessibility tree against the last snapshot taken in the session.

# Typical workflow: snapshot -> action -> diff
agent-browser snapshot -i          # Take baseline snapshot
agent-browser click @e2            # Perform action
agent-browser diff snapshot        # See what changed (auto-compares to last snapshot)

For visual regression testing or monitoring:

# Save a baseline screenshot, then compare later
agent-browser screenshot baseline.png
# ... time passes or changes are made ...
agent-browser diff screenshot --baseline baseline.png

# Compare staging vs production
agent-browser diff url https://staging.example.com https://prod.example.com --screenshot

diff snapshot output uses + for additions and - for removals, similar to git diff. diff screenshot produces a diff image with changed pixels highlighted in red, plus a mismatch percentage.

Timeouts and Slow Pages

The default timeout is 25 seconds. This can be overridden with the AGENT_BROWSER_DEFAULT_TIMEOUT environment variable (value in milliseconds). For slow websites or large pages, use explicit waits instead of relying on the default timeout:

# Wait for network activity to settle (best for slow pages)
agent-browser wait --load networkidle

# Wait for a specific element to appear
agent-browser wait "#content"
agent-browser wait @e1

# Wait for a specific URL pattern (useful after redirects)
agent-browser wait --url "**/dashboard"

# Wait for a JavaScript condition
agent-browser wait --fn "document.readyState === 'complete'"

# Wait a fixed duration (milliseconds) as a last resort
agent-browser wait 5000

When dealing with consistently slow websites, use wait --load networkidle after open to ensure the page is fully loaded before taking a snapshot. If a specific element is slow to render, wait for it directly with wait <selector> or wait @ref.

Session Management and Cleanup

When running multiple agents or automations concurrently, always use named sessions to avoid conflicts:

# Each agent gets its own isolated session
agent-browser --session agent1 open site-a.com
agent-browser --session agent2 open site-b.com

# Check active sessions
agent-browser session list

Always close your browser session when done to avoid leaked processes:

agent-browser close                    # Close default session
agent-browser --session agent1 close   # Close specific session

If a previous session was not closed properly, the daemon may still be running. Use agent-browser close to clean it up before starting new work.

To auto-shutdown the daemon after a period of inactivity (useful for ephemeral/CI environments):

AGENT_BROWSER_IDLE_TIMEOUT_MS=60000 agent-browser open example.com

Ref Lifecycle (Important)

Refs (@e1, @e2, etc.) are invalidated when the page changes. Always re-snapshot after:

Clicking links or buttons that navigate
Form submissions
Dynamic content loading (dropdowns, modals)

agent-browser click @e5 # Navigates to new page agent-browser snapshot -i # MUST re-snapshot agent-browser click @e1 # Use new refs

Annotated Screenshots (Vision Mode)

Use --annotate to take a screenshot with numbered labels overlaid on interactive elements. Each label [N] maps to ref @eN. This also caches refs, so you can interact with elements immediately without a separate snapshot.

agent-browser screenshot --annotate
# Output includes the image path and a legend:
#   [1] @e1 button "Submit"
#   [2] @e2 link "Home"
#   [3] @e3 textbox "Email"
agent-browser click @e2              # Click using ref from annotated screenshot

Use annotated screenshots when:

The page has unlabeled icon buttons or visual-only elements
You need to verify visual layout or styling
Canvas or chart elements are present (invisible to text snapshots)
You need spatial reasoning about element positions

Semantic Locators (Alternative to Refs)

When refs are unavailable or unreliable, use semantic locators:

agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"
agent-browser find role button click --name "Submit"
agent-browser find placeholder "Search" type "query"
agent-browser find testid "submit-btn" click

JavaScript Evaluation (eval)

Use eval to run JavaScript in the browser context. Shell quoting can corrupt complex expressions -- use --stdin or -b to avoid issues.

# Simple expressions work with regular quoting
agent-browser eval 'document.title'
agent-browser eval 'document.querySelectorAll("img").length'

# Complex JS: use --stdin with heredoc (RECOMMENDED)
agent-browser eval --stdin <<'EVALEOF'
JSON.stringify(
  Array.from(document.querySelectorAll("img"))
    .filter(i => !i.alt)
    .map(i => ({ src: i.src.split("/").pop(), width: i.width }))
)
EVALEOF

# Alternative: base64 encoding (avoids all shell escaping issues)
agent-browser eval -b "$(echo -n 'Array.from(document.querySelectorAll("a")).map(a => a.href)' | base64)"

Why this matters: When the shell processes your command, inner double quotes, ! characters (history expansion), backticks, and $() can all corrupt the JavaScript before it reaches agent-browser. The --stdin and -b flags bypass shell interpretation entirely.

Rules of thumb:

Single-line, no nested quotes -> regular eval 'expression' with single quotes is fine
Nested quotes, arrow functions, template literals, or multiline -> use eval --stdin <<'EVALEOF'
Programmatic/generated scripts -> use eval -b with base64

Configuration File

Create agent-browser.json in the project root for persistent settings:

{
  "headed": true,
  "proxy": "http://localhost:8080",
  "profile": "./browser-data"
}

Priority (lowest to highest): ~/.agent-browser/config.json < ./agent-browser.json < env vars < CLI flags. Use --config <path> or AGENT_BROWSER_CONFIG env var for a custom config file (exits with error if missing/invalid). All CLI options map to camelCase keys (e.g., --executable-path -> "executablePath"). Boolean flags accept true/false values (e.g., --headed false overrides config). Extensions from user and project configs are merged, not replaced.

Deep-Dive Documentation

Reference	When to Use
references/commands.md	Full command reference with all options
references/snapshot-refs.md	Ref lifecycle, invalidation rules, troubleshooting
references/session-management.md	Parallel sessions, state persistence, concurrent scraping
references/authentication.md	Login flows, OAuth, 2FA handling, state reuse
references/video-recording.md	Recording workflows for debugging and documentation
references/profiling.md	Chrome DevTools profiling for performance analysis

Browser Engine Selection

Use --engine to choose a local browser engine. The default is chrome.

# Use Lightpanda (fast headless browser, requires separate install)
agent-browser --engine lightpanda open example.com

# Via environment variable
export AGENT_BROWSER_ENGINE=lightpanda
agent-browser open example.com

# With custom binary path
agent-browser --engine lightpanda --executable-path /path/to/lightpanda open example.com

Supported engines:

chrome (default) -- Chrome/Chromium via CDP
lightpanda -- Lightpanda headless browser via CDP (10x faster, 10x less memory than Chrome)

Lightpanda does not support --extension, --profile, --state, or --allow-file-access. Install Lightpanda from https://lightpanda.io/docs/open-source/installation.

Ready-to-Use Templates

Template	Description
templates/form-automation.sh	Form filling with validation
templates/authenticated-session.sh	Login once, reuse state
templates/capture-workflow.sh	Content extraction with screenshots

./templates/form-automation.sh https://example.com/form
./templates/authenticated-session.sh https://app.example.com/login
./templates/capture-workflow.sh https://example.com ./output

Weekly Installs

323

Repository

everyinc/compou…g-plugin

GitHub Stars

11.0K

First Seen

Jan 21, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

opencode291

gemini-cli288

codex284

github-copilot270

cursor268

amp245

xdrop 文件传输脚本：Bun 环境下安全上传下载工具，支持加密分享

20,700 周安装