使用浏览器使用的CLI实现浏览器自动化
使用browser-use CLI实现浏览器自动化
The
command provides fast, persistent browser automation. It maintains browser sessions across commands, enabling complex multi-step workflows.
命令可实现快速、持久的浏览器自动化。它能在多个命令间维持浏览器会话，支持复杂的多步骤工作流。
Before using this skill,
must be installed and configured. Run diagnostics to verify:
使用此技能前，必须安装并配置
。运行诊断命令以验证：
- Navigate: - Opens URL (starts browser if needed)
- Inspect: - Returns clickable elements with indices
- Interact: Use indices from state to interact (,
browser-use input 3 "text"
- Verify: or to confirm actions
- Repeat: Browser stays open between commands
- 导航： - 打开指定URL（如需则启动浏览器）
- 检查： - 返回可点击元素及其索引
- 交互：使用state命令返回的索引进行交互（如 、
browser-use input 3 "text"
- 验证：通过 或 确认操作结果
- 重复操作：浏览器会在命令之间保持打开状态
bash
browser-use --browser chromium open <url> # Default: headless Chromium
browser-use --browser chromium --headed open <url> # Visible Chromium window
browser-use --browser real open <url> # Real Chrome (no profile = fresh)
browser-use --browser real --profile "Default" open <url> # Real Chrome with your login sessions
browser-use --browser remote open <url> # Cloud browser
- chromium: Fast, isolated, headless by default
- real: Uses a real Chrome binary. Without , uses a persistent but empty CLI profile at
~/.config/browseruse/profiles/cli/
- remote: Cloud-hosted browser with proxy support
bash
browser-use --browser chromium open <url> # 默认：无头模式Chromium
browser-use --browser chromium --headed open <url> # 可见的Chromium窗口
browser-use --browser real open <url> # 真实Chrome浏览器（无配置文件则为全新会话）
browser-use --browser real --profile "Default" open <url> # 使用您的登录会话的真实Chrome浏览器
browser-use --browser remote open <url> # 云端浏览器
- chromium：快速、隔离，默认无头模式
- real：使用真实Chrome二进制文件。若未指定，则使用位于
~/.config/browseruse/profiles/cli/
- remote：支持代理的云端托管浏览器
browser-use open <url> # Navigate to URL
browser-use back # Go back
browser-use scroll down # Scroll down (--amount N for pixels)
browser-use open <url> # 导航至指定URL
browser-use back # 返回上一页
browser-use scroll down # 向下滚动（使用--amount N指定像素数）
Page State (always run state first to get element indices)
页面状态（请先运行state命令获取元素索引）
browser-use state # Get URL, title, clickable elements
browser-use screenshot # Take screenshot (base64)
browser-use screenshot path.png # Save screenshot to file
browser-use state # 获取URL、标题和可点击元素
browser-use screenshot # 截取屏幕截图（返回base64格式）
browser-use screenshot path.png # 将屏幕截图保存至指定文件
Interactions (use indices from state)
交互操作（使用state命令返回的索引）
browser-use click <index> # Click element
browser-use type "text" # Type into focused element
browser-use input <index> "text" # Click element, then type
browser-use keys "Enter" # Send keyboard keys
browser-use select <index> "option" # Select dropdown option
browser-use click <index> # 点击指定元素
browser-use type "text" # 在焦点元素中输入文本
browser-use input <index> "text" # 点击元素后输入文本
browser-use keys "Enter" # 发送键盘按键
browser-use select <index> "option" # 选择下拉菜单选项
browser-use eval "document.title" # Execute JavaScript
browser-use get text <index> # Get element text
browser-use get html --selector "h1" # Get scoped HTML
browser-use eval "document.title" # 执行JavaScript代码
browser-use get text <index> # 获取元素文本内容
browser-use get html --selector "h1" # 获取指定选择器的HTML内容
browser-use wait selector "h1" # Wait for element
browser-use wait text "Success" # Wait for text
browser-use wait selector "h1" # 等待元素出现
browser-use wait text "Success" # 等待文本出现
browser-use sessions # List active sessions
browser-use close # Close current session
browser-use close --all # Close all sessions
browser-use sessions # 列出所有活跃会话
browser-use close # 关闭当前会话
browser-use close --all # 关闭所有会话
browser-use -b remote run "task" # Run agent in cloud (async by default)
browser-use task status <id> # Check cloud task progress
browser-use -b remote run "task" # 在云端运行Agent（默认异步执行）
browser-use task status <id> # 检查云端任务进度
bash
browser-use open <url> # Navigate to URL
browser-use back # Go back in history
browser-use scroll down # Scroll down
browser-use scroll up # Scroll up
browser-use scroll down --amount 1000 # Scroll by specific pixels (default: 500)
browser-use switch <tab> # Switch to tab by index
browser-use close-tab # Close current tab
browser-use close-tab <tab> # Close specific tab
bash
browser-use open <url> # 导航至指定URL
browser-use back # 返回历史记录上一页
browser-use scroll down # 向下滚动
browser-use scroll up # 向上滚动
browser-use scroll down --amount 1000 # 滚动指定像素数（默认：500）
browser-use switch <tab> # 通过索引切换标签页
browser-use close-tab # 关闭当前标签页
browser-use close-tab <tab> # 关闭指定索引的标签页
bash
browser-use state # Get URL, title, and clickable elements
browser-use screenshot # Take screenshot (outputs base64)
browser-use screenshot path.png # Save screenshot to file
browser-use screenshot --full path.png # Full page screenshot
bash
browser-use state # 获取URL、标题和可点击元素
browser-use screenshot # 截取屏幕截图（输出base64格式）
browser-use screenshot path.png # 将屏幕截图保存至指定文件
browser-use screenshot --full path.png # 截取整页屏幕截图
bash
browser-use click <index> # Click element
browser-use type "text" # Type text into focused element
browser-use input <index> "text" # Click element, then type text
browser-use keys "Enter" # Send keyboard keys
browser-use keys "Control+a" # Send key combination
browser-use select <index> "option" # Select dropdown option
browser-use hover <index> # Hover over element (triggers CSS :hover)
browser-use dblclick <index> # Double-click element
browser-use rightclick <index> # Right-click element (context menu)
bash
browser-use click <index> # 点击指定元素
browser-use type "text" # 在焦点元素中输入文本
browser-use input <index> "text" # 点击元素后输入文本
browser-use keys "Enter" # 发送键盘按键
browser-use keys "Control+a" # 发送组合按键
browser-use select <index> "option" # 选择下拉菜单选项
browser-use hover <index> # 悬停在元素上（触发CSS :hover效果）
browser-use dblclick <index> # 双击元素
browser-use rightclick <index> # 右键点击元素（打开上下文菜单）
JavaScript & Data
JavaScript与数据处理
bash
browser-use eval "document.title" # Execute JavaScript, return result
browser-use get title # Get page title
browser-use get html # Get full page HTML
browser-use get html --selector "h1" # Get HTML of specific element
browser-use get text <index> # Get text content of element
browser-use get value <index> # Get value of input/textarea
browser-use get attributes <index> # Get all attributes of element
browser-use get bbox <index> # Get bounding box (x, y, width, height)
bash
browser-use eval "document.title" # 执行JavaScript代码并返回结果
browser-use get title # 获取页面标题
browser-use get html # 获取完整页面HTML
browser-use get html --selector "h1" # 获取指定选择器的元素HTML
browser-use get text <index> # 获取元素文本内容
browser-use get value <index> # 获取输入框/文本域的值
browser-use get attributes <index> # 获取元素的所有属性
browser-use get bbox <index> # 获取元素的边界框（x、y、宽度、高度）
bash
browser-use cookies get # Get all cookies
browser-use cookies get --url <url> # Get cookies for specific URL
browser-use cookies set <name> <value> # Set a cookie
browser-use cookies set name val --domain .example.com --secure --http-only
browser-use cookies set name val --same-site Strict # SameSite: Strict, Lax, or None
browser-use cookies set name val --expires 1735689600 # Expiration timestamp
browser-use cookies clear # Clear all cookies
browser-use cookies clear --url <url> # Clear cookies for specific URL
browser-use cookies export <file> # Export all cookies to JSON file
browser-use cookies export <file> --url <url> # Export cookies for specific URL
browser-use cookies import <file> # Import cookies from JSON file
bash
browser-use cookies get # 获取所有Cookie
browser-use cookies get --url <url> # 获取指定URL的Cookie
browser-use cookies set <name> <value> # 设置Cookie
browser-use cookies set name val --domain .example.com --secure --http-only
browser-use cookies set name val --same-site Strict # SameSite属性：Strict、Lax或None
browser-use cookies set name val --expires 1735689600 # 过期时间戳
browser-use cookies clear # 清除所有Cookie
browser-use cookies clear --url <url> # 清除指定URL的Cookie
browser-use cookies export <file> # 将所有Cookie导出至JSON文件
browser-use cookies export <file> --url <url> # 导出指定URL的Cookie至JSON文件
browser-use cookies import <file> # 从JSON文件导入Cookie
bash
browser-use wait selector "h1" # Wait for element to be visible
browser-use wait selector ".loading" --state hidden # Wait for element to disappear
browser-use wait selector "#btn" --state attached # Wait for element in DOM
browser-use wait text "Success" # Wait for text to appear
browser-use wait selector "h1" --timeout 5000 # Custom timeout in ms
bash
browser-use wait selector "h1" # 等待元素可见
browser-use wait selector ".loading" --state hidden # 等待元素消失
browser-use wait selector "#btn" --state attached # 等待元素加入DOM
browser-use wait text "Success" # 等待文本出现
browser-use wait selector "h1" --timeout 5000 # 自定义超时时间（毫秒）
bash
browser-use python "x = 42" # Set variable
browser-use python "print(x)" # Access variable (outputs: 42)
browser-use python "print(browser.url)" # Access browser object
browser-use python --vars # Show defined variables
browser-use python --reset # Clear Python namespace
browser-use python --file script.py # Execute Python file
The Python session maintains state across commands. The
object provides:
- , , — page info
- , — navigation
- , ,
browser.input(index, text)
- ,
browser.scroll(direction, amount)
- , — utilities
bash
browser-use python "x = 42" # 设置变量
browser-use python "print(x)" # 访问变量（输出：42）
browser-use python "print(browser.url)" # 访问browser对象
browser-use python --vars # 显示已定义的变量
browser-use python --reset # 清除Python命名空间
browser-use python --file script.py # 执行Python文件
Python会话会在命令之间维持状态。
对象提供以下功能：
- 、、 — 页面信息
- 、 — 导航操作
- 、、
browser.input(index, text)
- 、
browser.scroll(direction, amount)
- 、 — 实用工具
Remote Mode Options
远程模式选项
When using
, additional options are available:
browser-use -b remote run "task" --llm gpt-4o
browser-use -b remote run "task" --llm claude-sonnet-4-20250514
browser-use -b remote run "task" --llm gpt-4o
browser-use -b remote run "task" --llm claude-sonnet-4-20250514
Proxy configuration (default: us)
代理配置（默认：美国）
browser-use -b remote run "task" --proxy-country uk
browser-use -b remote run "task" --proxy-country uk
browser-use -b remote run "task 1" --keep-alive # Keep session alive after task
browser-use -b remote run "task 2" --session-id abc-123 # Reuse existing session
browser-use -b remote run "task 1" --keep-alive # 任务完成后保持会话活跃
browser-use -b remote run "task 2" --session-id abc-123 # 复用现有会话
browser-use -b remote run "task" --flash # Fast execution mode
browser-use -b remote run "task" --wait # Wait for completion (default: async)
browser-use -b remote run "task" --flash # 快速执行模式
browser-use -b remote run "task" --wait # 等待任务完成（默认：异步）
browser-use -b remote run "task" --thinking # Extended reasoning mode
browser-use -b remote run "task" --no-vision # Disable vision (enabled by default)
browser-use -b remote run "task" --thinking # 扩展推理模式
browser-use -b remote run "task" --no-vision # 禁用视觉功能（默认启用）
Using a cloud profile (create session first, then run with --session-id)
使用云端配置文件（先创建会话，再使用--session-id运行任务）
browser-use session create --profile <cloud-profile-id> --keep-alive
browser-use session create --profile <cloud-profile-id> --keep-alive
→ returns session_id
→ 返回session_id
browser-use -b remote run "task" --session-id <session-id>
browser-use -b remote run "task" --session-id <session-id>
browser-use -b remote run "task" --start-url
https://example.com # Start from specific URL
browser-use -b remote run "task" --allowed-domain example.com # Restrict navigation (repeatable)
browser-use -b remote run "task" --metadata key=value # Task metadata (repeatable)
browser-use -b remote run "task" --skill-id skill-123 # Enable skills (repeatable)
browser-use -b remote run "task" --secret key=value # Secret metadata (repeatable)
browser-use -b remote run "task" --start-url
https://example.com # 从指定URL开始
browser-use -b remote run "task" --allowed-domain example.com # 限制导航域名（可重复指定）
browser-use -b remote run "task" --metadata key=value # 任务元数据（可重复指定）
browser-use -b remote run "task" --skill-id skill-123 # 启用技能（可重复指定）
browser-use -b remote run "task" --secret key=value # 保密元数据（可重复指定）
Structured output and evaluation
结构化输出与评估
browser-use -b remote run "task" --structured-output '{"type":"object"}' # JSON schema for output
browser-use -b remote run "task" --judge # Enable judge mode
browser-use -b remote run "task" --judge-ground-truth "expected answer"
browser-use -b remote run "task" --structured-output '{"type":"object"}' # 输出JSON schema
browser-use -b remote run "task" --judge # 启用评估模式
browser-use -b remote run "task" --judge-ground-truth "expected answer"
bash
browser-use task list # List recent tasks
browser-use task list --limit 20 # Show more tasks
browser-use task list --status finished # Filter by status (finished, stopped)
browser-use task list --session <id> # Filter by session ID
browser-use task list --json # JSON output
browser-use task status <task-id> # Get task status (latest step only)
browser-use task status <task-id> -c # All steps with reasoning
browser-use task status <task-id> -v # All steps with URLs + actions
browser-use task status <task-id> --last 5 # Last N steps only
browser-use task status <task-id> --step 3 # Specific step number
browser-use task status <task-id> --reverse # Newest first
browser-use task stop <task-id> # Stop a running task
browser-use task logs <task-id> # Get task execution logs
bash
browser-use task list # 列出近期任务
browser-use task list --limit 20 # 显示更多任务
browser-use task list --status finished # 按状态筛选（已完成、已停止）
browser-use task list --session <id> # 按会话ID筛选
browser-use task list --json # 以JSON格式输出
browser-use task status <task-id> # 获取任务状态（仅最新步骤）
browser-use task status <task-id> -c # 获取包含推理过程的所有步骤
browser-use task status <task-id> -v # 获取包含URL和操作的所有步骤
browser-use task status <task-id> --last 5 # 获取最近N个步骤
browser-use task status <task-id> --step 3 # 获取指定步骤
browser-use task status <task-id> --reverse # 按最新顺序显示步骤
browser-use task stop <task-id> # 停止运行中的任务
browser-use task logs <task-id> # 获取任务执行日志
Cloud Session Management
云端会话管理
bash
browser-use session list # List cloud sessions
browser-use session list --limit 20 # Show more sessions
browser-use session list --status active # Filter by status
browser-use session list --json # JSON output
browser-use session get <session-id> # Get session details + live URL
browser-use session get <session-id> --json
browser-use session stop <session-id> # Stop a session
browser-use session stop --all # Stop all active sessions
browser-use session create # Create with defaults
browser-use session create --profile <id> # With cloud profile
browser-use session create --proxy-country uk # With geographic proxy
browser-use session create --start-url https://example.com
browser-use session create --screen-size 1920x1080
browser-use session create --keep-alive
browser-use session create --persist-memory
browser-use session share <session-id> # Create public share URL
browser-use session share <session-id> --delete # Delete public share
bash
browser-use session list # 列出云端会话
browser-use session list --limit 20 # 显示更多会话
browser-use session list --status active # 按状态筛选
browser-use session list --json # 以JSON格式输出
browser-use session get <session-id> # 获取会话详情和实时URL
browser-use session get <session-id> --json
browser-use session stop <session-id> # 停止指定会话
browser-use session stop --all # 停止所有活跃会话
browser-use session create # 使用默认设置创建会话
browser-use session create --profile <id> # 使用云端配置文件创建会话
browser-use session create --proxy-country uk # 使用指定地区代理创建会话
browser-use session create --start-url https://example.com
browser-use session create --screen-size 1920x1080
browser-use session create --keep-alive
browser-use session create --persist-memory
browser-use session share <session-id> # 创建公共共享URL
browser-use session share <session-id> --delete # 删除公共共享链接
bash
browser-use tunnel <port> # Start tunnel (returns URL)
browser-use tunnel <port> # Idempotent - returns existing URL
browser-use tunnel list # Show active tunnels
browser-use tunnel stop <port> # Stop tunnel
browser-use tunnel stop --all # Stop all tunnels
bash
browser-use tunnel <port> # 启动隧道（返回访问URL）
browser-use tunnel <port> # 幂等操作 - 返回已存在的URL
browser-use tunnel list # 显示所有活跃隧道
browser-use tunnel stop <port> # 停止指定端口的隧道
browser-use tunnel stop --all # 停止所有隧道
bash
browser-use sessions # List active sessions
browser-use close # Close current session
browser-use close --all # Close all sessions
bash
browser-use sessions # 列出所有活跃会话
browser-use close # 关闭当前会话
browser-use close --all # 关闭所有会话
bash
browser-use -b real profile list # List local Chrome profiles
browser-use -b real profile cookies "Default" # Show cookie domains in profile
bash
browser-use -b real profile list # 列出本地Chrome配置文件
browser-use -b real profile cookies "Default" # 显示配置文件中的Cookie域名
bash
browser-use -b remote profile list # List cloud profiles
browser-use -b remote profile list --page 2 --page-size 50
browser-use -b remote profile get <id> # Get profile details
browser-use -b remote profile create # Create new cloud profile
browser-use -b remote profile create --name "My Profile"
browser-use -b remote profile update <id> --name "New"
browser-use -b remote profile delete <id>
bash
browser-use -b remote profile list # 列出云端配置文件
browser-use -b remote profile list --page 2 --page-size 50
browser-use -b remote profile get <id> # 获取云端配置文件详情
browser-use -b remote profile create # 创建新的云端配置文件
browser-use -b remote profile create --name "My Profile"
browser-use -b remote profile update <id> --name "New"
browser-use -b remote profile delete <id>
bash
browser-use profile sync --from "Default" --domain github.com # Domain-specific
browser-use profile sync --from "Default" # Full profile
browser-use profile sync --from "Default" --name "Custom Name" # With custom name
bash
browser-use profile sync --from "Default" --domain github.com # 按域名同步
browser-use profile sync --from "Default" # 完整配置文件同步
browser-use profile sync --from "Default" --name "Custom Name" # 使用自定义名称同步
bash
browser-use server logs # View server logs
bash
browser-use server logs # 查看服务器日志
Exposing Local Dev Servers
暴露本地开发服务器
Use when you have a local dev server and need a cloud browser to reach it.
Core workflow: Start dev server → create tunnel → browse the tunnel URL remotely.
当您有本地开发服务器，需要让云端浏览器访问时使用此工作流。
核心流程：启动开发服务器 → 创建隧道 → 远程浏览隧道URL。
1. Start your dev server
1. 启动本地开发服务器
npm run dev & # localhost:3000
npm run dev & # 运行在localhost:3000
2. Expose it via Cloudflare tunnel
2. 通过Cloudflare隧道暴露服务
3. Now the cloud browser can reach your local server
3. 现在云端浏览器可以访问您的本地服务器了
browser-use --browser remote open
https://abc.trycloudflare.com
browser-use state
browser-use screenshot
**Note:** Tunnels are independent of browser sessions. They persist across `browser-use close` and can be managed separately. Cloudflared must be installed — run `browser-use doctor` to check.
browser-use --browser remote open
https://abc.trycloudflare.com
browser-use state
browser-use screenshot
**注意**：隧道独立于浏览器会话，即使运行`browser-use close`也会保持活跃，可单独管理。必须安装Cloudflared — 运行`browser-use doctor`检查是否已安装。
Authenticated Browsing with Profiles
使用配置文件进行认证浏览
Use when a task requires browsing a site the user is already logged into (e.g. Gmail, GitHub, internal tools).
Core workflow: Check existing profiles → ask user which profile and browser mode → browse with that profile. Only sync cookies if no suitable profile exists.
Before browsing an authenticated site, the agent MUST:
- Ask the user whether to use real (local Chrome) or remote (cloud) browser
- List available profiles for that mode
- Ask which profile to use
- If no profile has the right cookies, offer to sync (see below)
当任务需要访问用户已登录的网站（如Gmail、GitHub、内部工具）时使用此工作流。
核心流程：检查现有配置文件 → 询问用户使用哪种浏览器模式和配置文件 → 使用该配置文件浏览。仅当没有合适的配置文件时才同步Cookie。
在浏览需要认证的网站前，Agent必须：
- 询问用户使用**real（本地Chrome）还是remote（云端）**浏览器模式
- 列出该模式下的可用配置文件
- 询问用户使用哪个配置文件
- 如果没有配置文件包含所需Cookie，提供同步选项（见下文）
Step 1: Check existing profiles
步骤1：检查现有配置文件
Option A: Local Chrome profiles (--browser real)
选项A：本地Chrome配置文件（--browser real模式）
browser-use -b real profile list
browser-use -b real profile list
→ Default: Person 1 (user@gmail.com)
→ Default: Person 1 (user@gmail.com)
→ Profile 1: Work (work@company.com)
→ Profile 1: Work (work@company.com)
Option B: Cloud profiles (--browser remote)
选项B：云端配置文件（--browser remote模式）
browser-use -b remote profile list
browser-use -b remote profile list
→ abc-123: "Chrome - Default (github.com)"
→ abc-123: "Chrome - Default (github.com)"
→ def-456: "Work profile"
→ def-456: "Work profile"
Step 2: Browse with the chosen profile
步骤2：使用选定的配置文件浏览
Real browser — uses local Chrome with existing login sessions
真实浏览器模式 — 使用本地Chrome的现有登录会话
Cloud browser — uses cloud profile with synced cookies
云端浏览器模式 — 使用已同步Cookie的云端配置文件
browser-use --browser remote --profile abc-123 open
https://github.com
The user is already authenticated — no login needed.
**Note:** Cloud profile cookies can expire over time. If authentication fails, re-sync cookies from the local Chrome profile.
browser-use --browser remote --profile abc-123 open
https://github.com
用户已处于认证状态 — 无需再次登录。
**注意**：云端配置文件的Cookie可能会过期。如果认证失败，请从本地Chrome配置文件重新同步Cookie。
Step 3: Syncing cookies (only if needed)
步骤3：同步Cookie（仅在需要时）
If the user wants to use a cloud browser but no cloud profile has the right cookies, sync them from a local Chrome profile.
Before syncing, the agent MUST:
- Ask which local Chrome profile to use
- Ask which domain(s) to sync — do NOT default to syncing the full profile
- Confirm before proceeding
Check what cookies a local profile has:
bash
browser-use -b real profile cookies "Default"
如果用户想使用云端浏览器，但没有云端配置文件包含所需Cookie，可从本地Chrome配置文件同步。
在同步前，Agent必须：
- 询问用户使用哪个本地Chrome配置文件
- 询问需要同步的域名 — 请勿默认同步完整配置文件
- 获得用户确认后再执行
检查本地配置文件包含的Cookie：
bash
browser-use -b real profile cookies "Default"
→ youtube.com: 23
→ youtube.com: 23
→ google.com: 18
→ google.com: 18
→ github.com: 2
→ github.com: 2
**Domain-specific sync (recommended):**
```bash
browser-use profile sync --from "Default" --domain github.com
**按域名同步（推荐）**：
```bash
browser-use profile sync --from "Default" --domain github.com
Creates new cloud profile: "Chrome - Default (github.com)"
创建新的云端配置文件："Chrome - Default (github.com)"
Only syncs github.com cookies
仅同步github.com的Cookie
**Full profile sync (use with caution):**
```bash
browser-use profile sync --from "Default"
**完整配置文件同步（谨慎使用）**：
```bash
browser-use profile sync --from "Default"
Syncs ALL cookies — includes sensitive data, tracking cookies, every session token
同步所有Cookie — 包含敏感数据、跟踪Cookie和所有会话令牌
Only use when the user explicitly needs their entire browser state.
**Fine-grained control (advanced):**
```bash
仅当用户明确需要完整浏览器状态时使用此方式。
**细粒度控制（高级）**：
```bash
Export cookies to file, manually edit, then import
将Cookie导出至文件，手动编辑后再导入
browser-use --browser real --profile "Default" cookies export /tmp/cookies.json
browser-use --browser remote --profile <id> cookies import /tmp/cookies.json
**Use the synced profile:**
```bash
browser-use --browser remote --profile <id> open https://github.com
browser-use --browser real --profile "Default" cookies export /tmp/cookies.json
browser-use --browser remote --profile <id> cookies import /tmp/cookies.json
**使用已同步的配置文件**：
```bash
browser-use --browser remote --profile <id> open https://github.com
Running Subagents
运行子Agent
Use cloud sessions to run autonomous browser agents in parallel.
Core workflow: Launch task(s) with
→ poll with
→ collect results → clean up sessions.
- Session = Agent: Each cloud session is a browser agent with its own state
- Task = Work: Jobs given to an agent; an agent can run multiple tasks sequentially
- Session lifecycle: Once stopped, a session cannot be revived — start a new one
使用云端会话并行运行自主浏览器Agent。
核心流程：使用
命令启动任务 → 使用
轮询进度 → 收集结果 → 清理会话。
- 会话 = Agent：每个云端会话是一个独立状态的浏览器Agent
- 任务 = 工作：分配给Agent的任务；一个Agent可按顺序运行多个任务
- 会话生命周期：会话停止后无法恢复 — 需启动新会话
Single task (async by default — returns immediately)
单个任务（默认异步执行 — 立即返回）
browser-use -b remote run "Search for AI news and summarize top 3 articles"
browser-use -b remote run "搜索AI新闻并总结top3文章"
→ task_id: task-abc, session_id: sess-123
→ task_id: task-abc, session_id: sess-123
Parallel tasks — each gets its own session
并行任务 — 每个任务使用独立会话
browser-use -b remote run "Research competitor A pricing"
browser-use -b remote run "调研竞争对手A的定价"
→ task_id: task-1, session_id: sess-a
→ task_id: task-1, session_id: sess-a
browser-use -b remote run "Research competitor B pricing"
browser-use -b remote run "调研竞争对手B的定价"
→ task_id: task-2, session_id: sess-b
→ task_id: task-2, session_id: sess-b
browser-use -b remote run "Research competitor C pricing"
browser-use -b remote run "调研竞争对手C的定价"
→ task_id: task-3, session_id: sess-c
→ task_id: task-3, session_id: sess-c
Sequential tasks in same session (reuses cookies, login state, etc.)
同一会话中的顺序任务（复用Cookie、登录状态等）
browser-use -b remote run "Log into example.com" --keep-alive
browser-use -b remote run "登录example.com" --keep-alive
→ task_id: task-1, session_id: sess-123
→ task_id: task-1, session_id: sess-123
browser-use task status task-1 # Wait for completion
browser-use -b remote run "Export settings" --session-id sess-123
browser-use task status task-1 # 等待任务完成
browser-use -b remote run "导出设置" --session-id sess-123
→ task_id: task-2, session_id: sess-123 (same session)
→ task_id: task-2, session_id: sess-123（同一会话）
Managing & Stopping
管理与停止任务
bash
browser-use task list --status finished # See completed tasks
browser-use task stop task-abc # Stop a task (session may continue if --keep-alive)
browser-use session stop sess-123 # Stop an entire session (terminates its tasks)
browser-use session stop --all # Stop all sessions
bash
browser-use task list --status finished # 查看已完成任务
browser-use task stop task-abc # 停止指定任务（若使用--keep-alive，会话会继续存在）
browser-use session stop sess-123 # 停止整个会话（终止所有关联任务）
browser-use session stop --all # 停止所有会话
Task status is designed for token efficiency. Default output is minimal — only expand when needed:
| Mode | Flag | Tokens | Use When |
|---|
| Default | (none) | Low | Polling progress |
| Compact | | Medium | Need full reasoning |
| Verbose | | High | Debugging actions |
任务状态设计为高效节省Token。默认输出简洁 — 仅在需要时展开：
| 模式 | 参数 | Token消耗 | 使用场景 |
|---|
| 默认 | 无 | 低 | 轮询进度 |
| 简洁 | | 中 | 需要完整推理过程 |
| 详细 | | 高 | 调试操作 |
For long tasks (50+ steps)
长任务（50+步骤）
browser-use task status <id> -c --last 5 # Last 5 steps only
browser-use task status <id> -v --step 10 # Inspect specific step
**Live view**: `browser-use session get <session-id>` returns a live URL to watch the agent.
**Detect stuck tasks**: If cost/duration in `task status` stops increasing, the task is stuck — stop it and start a new agent.
**Logs**: `browser-use task logs <task-id>` — only available after task completes.
browser-use task status <id> -c --last 5 # 仅查看最近5个步骤
browser-use task status <id> -v --step 10 # 检查指定步骤
**实时查看**：`browser-use session get <session-id>` 返回可观看Agent操作的实时URL。
**检测停滞任务**：如果`task status`中的成本/时长停止增加，说明任务已停滞 — 停止任务并启动新Agent。
**日志**：`browser-use task logs <task-id>` — 仅在任务完成后可用。
| Option | Description |
|---|
| Use named session (default: "default") |
| Browser mode: chromium, real, remote |
| Show browser window (chromium mode) |
| Browser profile (local name or cloud ID). Works with , , etc. — does NOT work with (use instead) |
| Output as JSON |
| Run as MCP server via stdin/stdout |
Session behavior: All commands without
use the same "default" session. The browser stays open and is reused across commands. Use
to run multiple browsers in parallel.
| 选项 | 描述 |
|---|
| 使用命名会话（默认："default"） |
| 浏览器模式：chromium、real、remote |
| 显示浏览器窗口（仅chromium模式） |
| 浏览器配置文件（本地名称或云端ID）。适用于、等命令 — 不适用于命令（请使用替代） |
| 以JSON格式输出 |
| 通过标准输入/输出以MCP服务器模式运行 |
会话行为：所有未指定
的命令均使用同一个"default"会话。浏览器会保持打开状态并在命令间复用。使用
可并行运行多个浏览器。
- Always run first to see available elements and their indices
- Use for debugging to see what the browser is doing
- Sessions persist — the browser stays open between commands
- Use for programmatic parsing
- Python variables persist across commands within a session
- CLI aliases: , , and all work identically to
- 始终先运行：查看可用元素及其索引
- 使用调试：查看浏览器的实际操作
- 会话会持久化：浏览器在命令之间保持打开状态
- 使用：便于程序解析输出
- Python变量会持久化：在同一会话中，命令间的变量会保留
- CLI别名：、和与功能完全相同
Run diagnostics first:
Browser won't start?
bash
browser-use close --all # Close all sessions
browser-use --headed open <url> # Try with visible window
Element not found?
bash
browser-use state # Check current elements
browser-use scroll down # Element might be below fold
browser-use state # Check again
Session issues?
bash
browser-use sessions # Check active sessions
browser-use close --all # Clean slate
browser-use open <url> # Fresh start
Session reuse fails after :
If you stop a task and try to reuse its session, the new task may get stuck at "created" status. Create a new session instead:
bash
browser-use session create --profile <profile-id> --keep-alive
browser-use -b remote run "new task" --session-id <new-session-id>
Task stuck at "started": Check cost with
— if not increasing, the task is stuck. View live URL with
, then stop and start a new agent.
Sessions persist after tasks complete: Tasks finishing doesn't auto-stop sessions. Run
browser-use session stop --all
to clean up.
首先运行诊断：
浏览器无法启动？
bash
browser-use close --all # 关闭所有会话
browser-use --headed open <url> # 尝试使用可见窗口启动
找不到元素？
bash
browser-use state # 检查当前元素列表
browser-use scroll down # 元素可能在视图外
browser-use state # 再次检查
会话问题？
bash
browser-use sessions # 检查活跃会话
browser-use close --all # Clean slate
browser-use open <url> # 重新开始
停止任务后会话复用失败：
如果停止任务后尝试复用会话，新任务可能会卡在"created"状态。请创建新会话：
bash
browser-use session create --profile <profile-id> --keep-alive
browser-use -b remote run "新任务" --session-id <new-session-id>
任务卡在"started"状态：使用
检查成本 — 如果成本停止增加，说明任务已停滞。使用
查看实时URL，然后停止任务并启动新Agent。
任务完成后会话仍存在：任务完成不会自动停止会话。运行
browser-use session stop --all
清理会话。
Always close the browser when done:
bash
browser-use close # Close browser session
browser-use session stop --all # Stop cloud sessions (if any)
browser-use tunnel stop --all # Stop tunnels (if any)
使用完成后请务必关闭浏览器：
bash
browser-use close # 关闭浏览器会话
browser-use session stop --all # 停止云端会话（如有）
browser-use tunnel stop --all # 停止隧道（如有）