Skip to content
Back to search

agent-browser

MarketplaceWorks with Claude CodeGitHub

Browser automation for AI agents

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/vercel-labs/agent-browser with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/vercel-labs/agent-browser'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/vercel-labs-agent-browser/badge.svg)](/listings/vercel-labs-agent-browser)

HTML

<a href="/listings/vercel-labs-agent-browser"><img src="/api/listings/vercel-labs-agent-browser/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Global Installation (recommended)

Installs the native Rust binary:

npm install -g agent-browser
agent-browser install  # Download Chrome from Chrome for Testing (first time only)

Project Installation (local dependency)

For projects that want to pin the version in `package.json`:

npm install agent-browser
agent-browser install

Then use via `package.json` scripts or by invoking `agent-browser` directly.

Homebrew (macOS)

brew install agent-browser
agent-browser install  # Download Chrome from Chrome for Testing (first time only)

Cargo (Rust)

cargo install agent-browser
agent-browser install  # Download Chrome from Chrome for Testing (first time only)

From Source

Requires Node.js 24+, pnpm 11+, and Rust.

git clone https://github.com/vercel-labs/agent-browser
cd agent-browser
pnpm install
pnpm build
pnpm build:native   # Requires Rust (https://rustup.rs)
pnpm link --global  # Makes agent-browser available globally
agent-browser install

Linux Dependencies

On Linux, install system dependencies:

agent-browser install --with-deps

This exits nonzero if the package manager cannot install every required browser library.

Updating

Upgrade to the latest version:

agent-browser upgrade

Detects your installation method (npm, Homebrew, or Cargo) and runs the appropriate update command automatically.

Requirements

- **Chrome** - Run `agent-browser install` to download Chrome from [Chrome for Testing](https://developer.chrome.com/blog/chrome-for-testing/) (Google's official automation channel). Existing Chrome, Brave, Playwright, and Puppeteer installations are detected automatically. No Playwright or Node.js required for the daemon. - **Node.js 24+ and pnpm 11+** - Only needed when building from source. - **Rust** - Only needed when building from source (see From Source above).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 19 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  3. "name": "agent-browser",
  4. "description": "Browser automation for AI agents",
  5. "owner": {
  6. "name": "Vercel",
  7. "email": "support@vercel.com"
  8. },
  9. "plugins": [
  10. {
  11. "name": "agent-browser",
  12. "description": "Automates browser interactions for web testing, form filling, screenshots, and data extraction",
  13. "source": "./",
  14. "strict": false,
  15. "skills": ["./skills/agent-browser"],
  16. "category": "development"
  17. }
  18. ]
  19. }
README.md · README · 138 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # agent-browser
  2. Browser automation for AI agents: open pages, read them as an accessibility tree, and act on elements from the shell.
  3. <p>
  4. <a href="https://vercel.com/labs#labs-products"><img alt="Vercel Labs Product" src="https://img.shields.io/badge/LABS-PRODUCT-0a0a0a.svg?style=for-the-badge&amp;logo=Vercel&amp;labelColor=000000" height="28"></a>
  5. <a href="https://www.npmjs.com/package/agent-browser"><img alt="npm version: agent-browser" src="https://img.shields.io/npm/v/agent-browser.svg?style=for-the-badge&amp;labelColor=000000" height="28"></a>
  6. <a href="https://github.com/vercel-labs/agent-browser/blob/main/LICENSE"><img alt="License: Apache-2.0" src="https://img.shields.io/github/license/vercel-labs/agent-browser.svg?style=for-the-badge&amp;labelColor=000000" height="28"></a>
  7. <a href="https://www.npmjs.com/package/agent-browser"><img alt="npm downloads per month: agent-browser" src="https://img.shields.io/npm/dm/agent-browser.svg?style=for-the-badge&amp;labelColor=000000&amp;label=npm%20downloads" height="28"></a>
  8. <a href="https://skills.sh/vercel-labs/agent-browser"><img alt="skills.sh" src="https://skills.sh/b/vercel-labs/agent-browser?style=for-the-badge" height="28"></a>
  9. </p>
  10. 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.
  11. ## Install
  12. ```bash
  13. npm install -g agent-browser
  14. agent-browser install # download Chrome for Testing (first time only)
  15. ```
  16. - **Homebrew:** `brew install agent-browser`, then `agent-browser install`.
  17. - **Linux:** `agent-browser install --with-deps` also installs the browser's system libraries.
  18. - **No install:** `npx agent-browser open example.com`.
  19. Project installs, building from source, `upgrade`, and `doctor` are covered in [Installation](https://agent-browser.dev/installation).
  20. ## Quick start
  21. ```bash
  22. agent-browser open example.com
  23. agent-browser snapshot -i # interactive elements, each with a ref
  24. agent-browser click @e1 # act on a ref from that snapshot
  25. agent-browser get url # check the result
  26. agent-browser close
  27. ```
  28. The snapshot for `example.com`:
  29. ```
  30. - link "Learn more" [ref=e1]
  31. ```
  32. - Refs describe the page at the time of the snapshot. After navigation or a DOM change, take a new snapshot before using refs again.
  33. - CSS selectors, text, XPath, and semantic locators also work, for example `agent-browser find role button click --name "Submit"`. See [Selectors](https://agent-browser.dev/selectors).
  34. - 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.
  35. The full walkthrough is in the [quick start](https://agent-browser.dev/quick-start).
  36. ## How it works
  37. 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](https://agent-browser.dev/sessions) is configured.
  38. Chrome for Testing is the default browser. You can also attach to a running Chrome with `--cdp` or `--auto-connect` ([CDP mode](https://agent-browser.dev/cdp-mode)), select the [Lightpanda](https://agent-browser.dev/engines/lightpanda) or [Obscura](https://agent-browser.dev/engines/obscura) engine with `--engine`, drive Mobile Safari in the [iOS Simulator](https://agent-browser.dev/ios), or use a cloud browser provider such as [Browserbase](https://agent-browser.dev/providers/browserbase), [Browserless](https://agent-browser.dev/providers/browserless), [Browser Use](https://agent-browser.dev/providers/browser-use), [Kernel](https://agent-browser.dev/providers/kernel), or [AgentCore](https://agent-browser.dev/providers/agentcore).
  39. ## For AI agents
  40. The CLI ships skills that match its version:
  41. ```bash
  42. agent-browser skills get core # the core loop, refs, waiting, and common workflows
  43. agent-browser skills get core --ref commands # one reference, such as the full command list
  44. agent-browser skills get core --full # adds the full command reference and templates
  45. agent-browser skills list # specialized skills: electron, slack, dogfood, and more
  46. ```
  47. Install the discovery skill into an agent harness from [skills.sh](https://skills.sh/vercel-labs/agent-browser):
  48. ```bash
  49. npx skills add vercel-labs/agent-browser
  50. ```
  51. 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`:
  52. ```markdown
  53. Use `agent-browser` for browser automation. Before the first use, run
  54. `agent-browser skills get core` and follow it.
  55. ```
  56. For MCP clients, `agent-browser mcp` starts an MCP server over stdio. See [MCP server](https://agent-browser.dev/commands#mcp-server).
  57. ## Commands
  58. Run `agent-browser --help` for the full list, or `agent-browser <command> --help` for one command.
  59. | Group | Commands | Docs |
  60. |---|---|---|
  61. | Navigate and read | `open`, `back`, `forward`, `reload`, `read`, `snapshot`, `get`, `is` | [Core](https://agent-browser.dev/commands#core), [Snapshots](https://agent-browser.dev/snapshots) |
  62. | Interact | `click`, `dblclick`, `fill`, `type`, `press`, `keyboard`, `hover`, `focus`, `select`, `check`, `uncheck`, `scroll`, `drag`, `upload`, `mouse`, `find` | [Core](https://agent-browser.dev/commands#core), [Find elements](https://agent-browser.dev/commands#find-elements) |
  63. | Wait | `wait` | [Wait](https://agent-browser.dev/commands#wait) |
  64. | Capture | `screenshot`, `pdf`, `record`, `download`, `diff` | [Recording](https://agent-browser.dev/recording), [Diffing](https://agent-browser.dev/diffing), [Files](https://agent-browser.dev/files) |
  65. | Page and network state | `cookies`, `storage`, `network`, `set`, `clipboard`, `eval`, `pushstate` | [Network](https://agent-browser.dev/network), [Settings](https://agent-browser.dev/commands#settings) |
  66. | Tabs, frames, and dialogs | `tab`, `frame`, `dialog` | [Tabs and frames](https://agent-browser.dev/commands#tabs-frames) |
  67. | Debug and performance | `console`, `errors`, `highlight`, `inspect`, `trace`, `profiler`, `vitals`, `react`, `a11y` | [Debugging](https://agent-browser.dev/debugging), [Profiler](https://agent-browser.dev/profiler), [React](https://agent-browser.dev/react) |
  68. | Sessions and auth | `session`, `state`, `auth`, `profiles`, `confirm`, `deny` | [Sessions](https://agent-browser.dev/sessions), [Security](https://agent-browser.dev/security) |
  69. | Agents and integrations | `skills`, `mcp`, `webmcp`, `flow`, `chat`, `batch`, `plugin` | [Skills](https://agent-browser.dev/skills), [WebMCP](https://agent-browser.dev/webmcp), [Plugins](https://agent-browser.dev/plugins) |
  70. | Observe | `stream`, `dashboard` | [Streaming](https://agent-browser.dev/streaming), [Dashboard](https://agent-browser.dev/dashboard) |
  71. | Setup | `install`, `upgrade`, `doctor`, `connect`, `close` | [Installation](https://agent-browser.dev/installation) |
  72. Flags, environment variables, and `agent-browser.json` are documented in [Configuration](https://agent-browser.dev/configuration).
  73. ## Platforms
  74. 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.
  75. ## Development
  76. Building from source requires Node.js 24 or later, pnpm 11 or later, and Rust:
  77. ```bash
  78. pnpm install
  79. pnpm build:source # builds the dashboard and the native CLI
  80. pnpm link --global
  81. agent-browser install
  82. ```
  83. Run the Rust checks from `cli/`:
  84. ```bash
  85. cargo fmt -- --check
  86. cargo clippy
  87. cargo test
  88. cargo test e2e -- --ignored --test-threads=1 # launches real headless Chrome
  89. ```
  90. [AGENTS.md](AGENTS.md) lists the files to update with each change, the docs checks, and the release process.
  91. ## Documentation
  92. - [agent-browser.dev](https://agent-browser.dev): introduction, guides, and reference
  93. - [Commands](https://agent-browser.dev/commands) and [Configuration](https://agent-browser.dev/configuration)
  94. - [Security](https://agent-browser.dev/security): the auth vault, domain allowlists, action policies, and content boundaries
  95. - [Next.js and Vercel](https://agent-browser.dev/next) and [eve](https://agent-browser.dev/eve): running agent-browser in Vercel Sandbox and eve agents
  96. - [Changelog](CHANGELOG.md)
  97. ## License
  98. Apache-2.0

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.