Agent Browser
OfficialFreeAutomate browser tasks with a fast CLI.
Free · Opens the source repo
What Agent Browser does
Agent Browser is a command-line interface (CLI) designed for automating browser interactions, making it a powerful tool for developers and designers who need to streamline their web-based workflows. Built on a fast native Rust foundation, it utilizes Chrome/Chromium via the Chrome DevTools Protocol (CDP), allowing for reliable and efficient browser automation without relying on additional libraries like Playwright or Puppeteer. This skill is particularly useful for tasks that involve navigating web pages, filling out forms, clicking buttons, taking screenshots, and scraping data from websites.
The CLI offers specialized skills that extend its capabilities beyond standard web pages. Users can automate interactions with Electron desktop applications such as VS Code and Slack, perform exploratory testing and QA, and even run browser automation in Vercel Sandbox microVMs or AWS Bedrock AgentCore cloud browsers. This flexibility makes Agent Browser suitable for a variety of scenarios, whether you're testing web apps, logging into sites, or reviewing application quality.
With features like accessibility-tree snapshots and compact element references, Agent Browser ensures reliable interactions with web elements. The tool also supports session management, state persistence, and video recording, which can be invaluable for debugging and documentation purposes. The observability dashboard enhances user experience by providing real-time insights into session status and traffic, all while maintaining a secure environment.
Overall, Agent Browser is ideal for developers and designers looking to automate repetitive browser tasks efficiently. Its command-line nature and robust feature set make it a valuable addition to any toolkit focused on web automation and testing.
When to use it
Use Agent Browser when you need to automate tasks such as navigating websites, filling forms, or testing web applications.
When not to use it
This tool may not be suitable for simple one-off tasks that do not require automation or for users unfamiliar with command-line interfaces.
What you can build with it
Automating Form Submissions
Use Agent Browser to fill out and submit forms automatically, saving time during testing or data entry.
Testing Web Applications
Leverage Agent Browser to navigate through web applications and perform automated tests, ensuring functionality and performance.
Scraping Data from Websites
Utilize the scraping capabilities of Agent Browser to extract data from web pages efficiently for analysis or reporting.
How to install Agent Browser
View source1. Install with the skills CLI
npx skills add vercel-labs/agent-browser/agent-browser --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by vercel-labsagent-browser
Fast browser automation CLI for AI agents. Chrome/Chromium via CDP with accessibility-tree snapshots and compact @eN element refs.
Install: npm i -g agent-browser && agent-browser install
Start here
This file is a discovery stub, not the usage guide. Before running any agent-browser command, load the actual workflow content from the CLI:
agent-browser skills get core # start here — workflows, common patterns, troubleshooting
agent-browser skills get core --full # include full command reference and templates
The CLI serves skill content that always matches the installed version, so instructions never go stale. The content in this stub cannot change between releases, which is why it just points at skills get core.
Specialized skills
Load a specialized skill when the task falls outside browser web pages:
agent-browser skills get electron # Electron desktop apps (VS Code, Slack, Discord, Figma, ...)
agent-browser skills get slack # Slack workspace automation
agent-browser skills get dogfood # Exploratory testing / QA / bug hunts
agent-browser skills get derive-client # Record a HAR, derive a standalone API client for a site
agent-browser skills get vercel-sandbox # agent-browser inside Vercel Sandbox microVMs
agent-browser skills get agentcore # AWS Bedrock AgentCore cloud browsers
Run agent-browser skills list to see everything available on the installed version.
Why agent-browser
- Fast native Rust CLI, not a Node.js wrapper
- Works with any AI agent (Cursor, Claude Code, Codex, Continue, Windsurf, etc.)
- Chrome/Chromium via CDP with no Playwright or Puppeteer dependency
- Accessibility-tree snapshots with element refs for reliable interaction
- Sessions, authentication vault, state persistence, video recording
- Specialized skills for Electron apps, Slack, exploratory testing, cloud providers
Observability Dashboard
The dashboard runs independently of browser sessions on port 4848 and can also be opened through a proxied or forwarded URL such as https://dashboard.agent-browser.localhost. Agents should stay on the dashboard origin: session tabs, status, and stream traffic are proxied internally, so session ports do not need to be exposed.
Frequently asked questions about Agent Browser
Similar skills
Spring Boot Testing
Master testing techniques for Spring Boot 4 applications.
GitHub Issues
Manage GitHub issues efficiently with MCP tools.
Geofeed Tuner
Optimize your IP geolocation feeds in CSV format.
Batch Files
Master Windows batch scripting for automation and task management.
Adobe Illustrator Scripting
Automate your Illustrator workflows with ExtendScript.
Plugin Structure
Create and organize Claude Code plugins effectively.