Smart browser task agent - describe what you want done in natural language and it completes automatically. PREFERRED tool for multi-step browser operations like searching, form filling, and data extraction.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
推荐优先使用 - 这是浏览器操作的首选工具。
基于 browser-use 开源项目实现。
browser_task(
task="要完成的任务描述",
max_steps=15 # 可选，默认 15
)
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
| task | string | 是 | 任务描述，用自然语言描述你想完成的操作 |
| max_steps | integer | 否 | 最大执行步骤数，默认 15 |
browser_task(task="打开百度搜索福建福州天气")
browser_task(task="打开 example.com 的注册页面，填写用户名 test123")
browser_task(task="打开 GitHub 首页，获取今日热门项目的名称")
browser_task(task="打开百度搜索福建福州，截图保存")
系统提供多条路径操作网站和浏览器，按场景选择最可靠的方案：
| 场景 | 推荐工具 | 说明 |
|---|---|---|
| 目标网站有 opencli adapter | opencli_run（最可靠） | 确定性命令 + JSON 输出，复用 Chrome 登录态 |
| 需要登录但无 adapter | browser_task → 手动组合 | 先尝试 browser_task，失败则用 click/type 手动操作 |
| 仅需读取网页内容 | web_fetch | 最快最省资源，无需浏览器 |
| 仅需搜索 | web_search | DuckDuckGo 直接搜索 |
| 复杂多步浏览器交互 | browser_task | 适合登录、填表、筛选等 |
| 单步浏览器操作 | browser_navigate/browser_click 等 | 精确控制单个操作 |
| 操作用户已登录的 Chrome | call_mcp_tool("chrome-devtools", ...) | 需用户 Chrome 开启调试端口 |
决策顺序：opencli_run（有 adapter 时）→ web_fetch/web_search（只读时）→ browser_task → 手动 browser_click/type 组合 → chrome-devtools MCP。
仅在以下情况使用 browser_navigate、browser_click 等细粒度工具：
browser_task 执行失败需要手动介入browser_screenshot）{
"success": true,
"result": {
"task": "打开百度搜索福建福州",
"steps_taken": 5,
"final_result": "搜索完成，已显示福建福州相关结果",
"message": "任务完成: 打开百度搜索福建福州"
}
}
如果想让 OpenAkita 操作你已打开的 Chrome 页面，需要以调试模式启动 Chrome：
Windows:
"C:\Program Files\Google\Chrome\Application\chrome.exe" --remote-debugging-port=9222
macOS:
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222
Linux:
google-chrome --remote-debugging-port=9222
启动后，OpenAkita 会自动检测并连接，可以操作你已打开的标签页。
browser_screenshot - 单独截图browser_navigate - 单独导航deliver_artifacts - 发送结果给用户No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Record important information to long-term memory for learning user preferences, successful patterns, and error lessons. When you need to remember user preferences, save successful patterns, or record lessons from errors.
The English summary is being prepared. Showing the original description.
Click page elements by CSS selector or text content. When you need to click buttons, links, or select options. PREREQUISITE - must use browser_navigate to open target page first.
The English summary is being prepared. Showing the original description.
Extract page content and element text from current webpage. When you need to read page information, get element values, scrape data, or verify page content.
The English summary is being prepared. Showing the original description.
List all open browser tabs with their index, URL and title. When you need to check what pages are open, manage multiple tabs, or find a specific tab to switch to.
The English summary is being prepared. Showing the original description.
Navigate browser to specified URL to open a webpage. When you need to open webpages or start web automation. PREREQUISITE - must call before browser_click/type operations. Auto-starts browser if not running.
The English summary is being prepared. Showing the original description.
Open new browser tab and navigate to URL (keeps current page open). When you need to open additional page without closing current, or multi-task across pages. PREREQUISITE - must confirm browser is running first.
The English summary is being prepared. Showing the original description.