站内导读

中文

定位:agent-browser 是 Vercel Labs 用 Rust 写的 CLI,让 AI agent 在 shell 里逐条命令操作浏览器,适合把网页任务拆成小步执行的场景。

核心能力

  • snapshot 把页面输出为紧凑文本,每个可交互元素带一个 @e1 形式的 ref。
  • 浏览器进程在命令之间保持打开,每一步只是一次短小的 shell 调用。
  • 除 ref 外还支持 CSS 选择器、文本、XPath 与 find role button 这类语义定位。
  • 点击目标隐藏、禁用、在视口外或被弹窗遮挡时直接报错,不会返回成功。

适用人群:需要在脚本或 agent 循环里做浏览器自动化的开发者。需有 Node.js 环境,首次运行要下载 Chrome for Testing,Linux 另需系统依赖。

注意:页面跳转或 DOM 变化后 ref 失效,需重新 snapshot。

README · 详细文档

来源 · 查看原文

agent-browser

Browser automation for AI agents: open pages, read them as an accessibility tree, and act on elements from the shell.

Vercel Labs Product npm version: agent-browser License: Apache-2.0 npm downloads per month: agent-browser skills.sh

agent-browser is a native Rust CLI that gives an AI agent a browser it can drive one command at a time. snapshot returns the page as compact text with a ref such as @e1 for each element. The agent acts on a ref, reads the page again to check the result, and repeats. The browser stays open between commands, so each step is one short shell call.

Install

npm install -g agent-browser
agent-browser install           # download Chrome for Testing (first time only)
  • Homebrew: brew install agent-browser, then agent-browser install.
  • Linux: agent-browser install --with-deps also installs the browser's system libraries.
  • No install: npx agent-browser open example.com.

Project installs, building from source, upgrade, and doctor are covered in Installation.

Quick start

agent-browser open example.com
agent-browser snapshot -i       # interactive elements, each with a ref
agent-browser click @e1         # act on a ref from that snapshot
agent-browser get url           # check the result
agent-browser close

The snapshot for example.com:

- link "Learn more" [ref=e1]
  • Refs describe the page at the time of the snapshot. After navigation or a DOM change, take a new snapshot before using refs again.
  • CSS selectors, text, XPath, and semantic locators also work, for example agent-browser find role button click --name "Submit". See Selectors.
  • A click fails, instead of reporting success, when the target is hidden, disabled, outside the viewport, or covered by another element such as a consent banner. Dismiss the covering element, take a new snapshot, and retry.

The full walkthrough is in the quick start.

How it works

The CLI sends each command to a background daemon that starts on the first command and controls the browser over the Chrome DevTools Protocol. Each --session gets its own daemon and browser. By default, the daemon closes a headless browser and exits after one hour without commands, saving state first when session persistence is configured.

Chrome for Testing is the default browser. You can also attach to a running Chrome with --cdp or --auto-connect (CDP mode), select the Lightpanda or Obscura engine with --engine, drive Mobile Safari in the iOS Simulator, or use a cloud browser provider such as Browserbase, Browserless, Browser Use, Kernel, or AgentCore.

For AI agents

The CLI ships skills that match its version:

agent-browser skills get core                 # the core loop, refs, waiting, and common workflows
agent-browser skills get core --ref commands  # one reference, such as the full command list
agent-browser skills get core --full          # adds the full command reference and templates
agent-browser skills list                     # specialized skills: electron, slack, dogfood, and more

Install the discovery skill into an agent harness from skills.sh:

npx skills add vercel-labs/agent-browser

The installed skill is a thin stub that tells the agent to load agent-browser skills get core, so its instructions always match the installed CLI. Or add this to your AGENTS.md:

Use `agent-browser` for browser automation. Before the first use, run
`agent-browser skills get core` and follow it.

For MCP clients, agent-browser mcp starts an MCP server over stdio. See MCP server.

Commands

Run agent-browser --help for the full list, or agent-browser <command> --help for one command.

GroupCommandsDocs
Navigate and readopen, back, forward, reload, read, snapshot, get, isCore, Snapshots
Interactclick, dblclick, fill, type, press, keyboard, hover, focus, select, check, uncheck, scroll, drag, upload, mouse, findCore, Find elements
WaitwaitWait
Capturescreenshot, pdf, record, download, diffRecording, Diffing, Files
Page and network statecookies, storage, network, set, clipboard, eval, pushstateNetwork, Settings
Tabs, frames, and dialogstab, frame, dialogTabs and frames
Debug and performanceconsole, errors, highlight, inspect, trace, profiler, vitals, react, a11yDebugging, Profiler, React
Sessions and authsession, state, auth, profiles, confirm, denySessions, Security
Agents and integrationsskills, mcp, webmcp, flow, chat, batch, pluginSkills, WebMCP, Plugins
Observestream, dashboardStreaming, Dashboard
Setupinstall, upgrade, doctor, connect, closeInstallation

Flags, environment variables, and agent-browser.json are documented in Configuration.

Platforms

Native binaries ship for macOS (ARM64, x64), Linux (ARM64, x64, glibc and musl), and Windows (x64). The npm package picks the right binary for the host.

Development

Building from source requires Node.js 24 or later, pnpm 11 or later, and Rust:

pnpm install
pnpm build:source               # builds the dashboard and the native CLI
pnpm link --global
agent-browser install

Run the Rust checks from cli/:

cargo fmt -- --check
cargo clippy
cargo test
cargo test e2e -- --ignored --test-threads=1   # launches real headless Chrome

AGENTS.md lists the files to update with each change, the docs checks, and the release process.

Documentation

License

Apache-2.0

相关项目 · GitHub 热门

查看全部「GitHub 热门」项目 →