Tencent / BrowserSkill

查看原文 / View Original 编辑 / Edit

Tencent / BrowserSkill

BrowserSkill Let AI agents use your browser without interrupting your work. BrowserSkill 让 AI 智能体能够使用你的浏览器，且不会打断你的工作。

BrowserSkill connects Cursor, Claude Code, Codex, OpenClaw, CodeBuddy, WorkBuddy, Pi, Hermes Agent, DeepSeek Harness, and other AI agents to your already logged-in browser. Need the agent to touch a tab you already have open? It must borrow that tab explicitly, return it when the task is done, and leave the rest of your browser alone. BrowserSkill 将 Cursor、Claude Code、Codex、OpenClaw、CodeBuddy、WorkBuddy、Pi、Hermes Agent、DeepSeek Harness 以及其他 AI 智能体连接到你已登录的浏览器。如果需要智能体操作你已打开的标签页，它必须明确申请“借用”该标签页，任务完成后归还，并保持浏览器其余部分不受干扰。

BrowserSkill Advantages

BrowserSkill 的优势

  • Reuse real login state: Agents can work with sites you are already signed into, without separate test accounts. 复用真实登录状态： 智能体可以直接操作你已登录的网站，无需额外的测试账号。
  • Keep working uninterrupted: browser tasks run in a separate, visible Agent Window, so you can keep using your own browser. 工作不中断： 浏览器任务在独立的、可见的“智能体窗口”中运行，因此你可以继续使用自己的浏览器。
  • Support any Agent: any Agent that can call a shell can use BrowserSkill through the bsk CLI, with no lock-in to a specific model, Agent framework, or harness. 支持任何智能体： 任何能够调用 Shell 的智能体都可以通过 bsk 命令行工具使用 BrowserSkill，无需绑定特定的模型、智能体框架或工具集。
  • Built-in human-in-loop: when a task hits captcha, login, confirmation dialogs, or other human-only steps, the Agent can ask you to take over and then continue afterwards. 内置人机协作（Human-in-loop）： 当任务遇到验证码、登录、确认弹窗或其他仅限人类操作的步骤时，智能体可以请求你接管，并在你操作完成后继续执行。

Capture a long image in Quick actions → Full-page screenshot, or let an Agent use bsk screenshot --session <id> --full-page --out page.png. See the full-page screenshot guide for page support, cancellation and export. 你可以通过“快速操作”→“全页截图”捕获长图，或者让智能体使用 bsk screenshot --session <id> --full-page --out page.png 命令。有关页面支持、取消和导出的详细信息，请参阅全页截图指南。

Runtime Environment

运行环境

BrowserSkill has two local runtime pieces: the bsk CLI/daemon and the browser extension. BrowserSkill 包含两个本地运行组件：bsk 命令行/守护进程以及浏览器扩展程序。

Runtime Support 运行支持

  • Operating systems: macOS (Apple Silicon and Intel), Linux (x64 and ARM64), Windows x64 操作系统： macOS (Apple Silicon 和 Intel)、Linux (x64 和 ARM64)、Windows x64
  • Browsers: Chrome and Microsoft Edge are supported; other Chromium-based browsers are expected to work when they support unpacked Chromium extensions; Firefox is planned. 浏览器： 支持 Chrome 和 Microsoft Edge；其他基于 Chromium 的浏览器在支持解压后的 Chromium 扩展时通常也能正常工作；Firefox 支持计划中。

Quick Start

快速开始

Using an agent sandbox that reaps background processes after each command? Follow the sandboxed agent setup to keep the daemon in a persistent host environment and connect with a shared BSK_HOME plus BSK_AUTO_START=0. Ordinary local use keeps automatic startup by default. 如果你使用的智能体沙箱会在每条命令后清理后台进程，请按照“沙箱智能体设置”进行操作，将守护进程保持在持久的主机环境中，并使用共享的 BSK_HOME 和 BSK_AUTO_START=0 进行连接。普通的本地使用默认开启自动启动。

Install with your Agent (recommended) 通过智能体安装（推荐）

Already using Cursor, Claude Code, Codex, or another shell-capable agent? Just copy this one line and send it to your agent — it will install the CLI and skill for you, then walk you through loading the extension: 已经在用 Cursor、Claude Code、Codex 或其他支持 Shell 的智能体了吗？只需复制下面这一行发送给你的智能体，它就会为你安装 CLI 和技能，并引导你加载扩展程序：

Set up browser-skill on this machine by following https://raw.githubusercontent.com/Tencent/BrowserSkill/main/AGENT_INSTALL.md

Manual install 手动安装

Install the CLI, then install the extension from the Chrome Web Store or Edge Add-ons. 安装 CLI，然后从 Chrome 网上应用店或 Edge 加载项安装扩展程序。

1. Install the bsk CLI 1. 安装 bsk CLI

  • macOS / Linux (recommended — installs to ~/.local/bin): curl -fsSL https://raw.githubusercontent.com/Tencent/BrowserSkill/main/install.sh | sh export PATH="${BSK_INSTALL_DIR:-$HOME/.local/bin}:$PATH"
  • Windows (PowerShell — installs to ~/.local/bin): irm https://raw.githubusercontent.com/Tencent/BrowserSkill/main/install.ps1 | iex

The export makes the CLI available in the current Unix shell. A running agent may need the same PATH setting in each shell call, or the installed binary’s absolute path. Restart the agent if it retains an old PATH after installation. Verify the binary in the terminal or agent environment that will use it: bsk --version export 命令使 CLI 在当前的 Unix Shell 中可用。正在运行的智能体可能需要在每次 Shell 调用中设置相同的 PATH，或者使用已安装二进制文件的绝对路径。如果智能体在安装后仍保留旧的 PATH，请重启智能体。在终端或将要使用它的智能体环境中验证二进制文件：bsk --version

2. Install the browser extension 2. 安装浏览器扩展

Install BrowserSkill from your browser’s store: 从你的浏览器商店安装 BrowserSkill：

On other Chromium-based browsers, install the Chrome Web Store build. 在其他基于 Chromium 的浏览器上，请安装 Chrome 网上应用店的版本。

3. Install the skill 3. 安装技能

BrowserSkill ships a skill that teaches your agent harness how to use bsk. For these harnesses, install it in one step: Cursor, Claude Code, Codex, OpenClaw, CodeBuddy, WorkBuddy, Pi, Hermes Agent. BrowserSkill 提供了一个技能包，用于教你的智能体工具集如何使用 bsk。对于上述工具集，可以通过一步安装：

bsk install-skill

Use Space to select the Agent harness you want to install into, then press Enter to install the skill. Run bsk install-skill --list to see internal variants and install paths. 使用空格键选择要安装到的智能体工具集，然后按回车键安装技能。运行 bsk install-skill --list 查看内部变体和安装路径。

4. Verify the connection 4. 验证连接

Run bsk doctor and follow its hints. Open the extension popup and confirm it is connected. Explain any warnings and resolve failures before testing browser use. Doctor can pass with no skill installed (N/A); verify skill discovery separately. Start a new Agent session, confirm browser-skill is available in the harness, and ask it to open https://example.com and summarize. 运行 bsk doctor 并按照提示操作。打开扩展程序弹出窗口并确认已连接。在测试浏览器使用前，请解释任何警告并解决故障。即使未安装技能（N/A），Doctor 也可以通过检查；请单独验证技能发现情况。开启一个新的智能体对话，确认 browser-skill 在工具集中可用，并要求它打开 https://example.com 并进行总结。

← 返回新闻列表 / Back to news list