Browser Automation · Public

agent-browser

Browser automation project for web operations, testing, extraction, and permission-boundary checks.

Browser automationWeb tasksTest accountsCookie boundariesPermission control

Best fitDevelopers who need AI-assisted web tasks, browser testing, page extraction, or structured web operations.

Check whether this project matches your task before installing it.

What it can doBrowser automation task planning, permission boundaries, recovery steps, and acceptance checks

Review the portable capability path.

Before continuingVerify in a sandbox

Do not treat a preview pack as a proven local install.

GitHub snapshot33k stars

2.0k forks · 106 contributors

Official first step Read manual preview Source repository

Publication status · 2026-05-25

What is agent-browser?

agent-browser supports browser task automation, web operations, or web data workflows.
Best fit: Developers who need AI-assisted web tasks, browser testing, page extraction, or structured web operations.
Not for: Not for workflows that cannot isolate browser state, account permissions, cookies, or real user data.
Capability added to an AI workflow: Browser automation task planning, permission boundaries, recovery steps, and acceptance checks
First safe verification step: Verify one minimal web task with an isolated browser profile and test account first.
Verification state: source, Quick Start, and sandbox install checks are recorded as passed.
Top risk: The main risk is misusing browser state, account permissions, cookies, or real data during automation.
Evidence base: https://github.com/vercel-labs/agent-browser, https://github.com/vercel-labs/agent-browser#readme, Human Manual, Pitfall Log

Quick decision

Use this section to decide whether the project is worth a deeper read.

Best forDevelopers who need AI-assisted web tasks, browser testing, page extraction, or structured web operations.

Match the project to your task before installing it.

CapabilityBrowser automation task planning, permission boundaries, recovery steps, and acceptance checks

Browser automation project for web operations, testing, extraction, and permission-boundary checks.

Repositoryvercel-labs/agent-browser

33k stars · 2.0k forks

What it can do

Translate the upstream project into concrete capabilities the user can judge before installing.

Introduction to Agent Browser

Related topics: Installation Guide, Architecture Overview

Source: https://github.com/vercel-labs/agent-browser / Human Manual

Installation Guide

Related topics: Introduction to Agent Browser

Sources: [AGENTS.md](https://github.com/vercel-labs/agent-browser/blob/main/AGENTS.md)

Element References System

Related topics: State Inspection Commands, Interaction Commands

Sources: [skill-data/core/references/snapshot-refs.md]()

Architecture Overview

Related topics: Daemon and CDP Protocol, Introduction to Agent Browser

Sources: [cli/src/native/mod.rs]()

Daemon and CDP Protocol

Related topics: Architecture Overview, Browser Engine Integration

Sources: [cli/src/native/actions.rs](cli/src/native/actions.rs)

Sources: https://github.com/vercel-labs/agent-browser, Human Manual, Project Pack evidence, and downstream validation signals.

Community Discussion Evidence

Project-level external discussion stays visible on the detail page, not only inside the manual.

Stars33k stars

Forks2.0k forks

Contributors106 contributors

Licenseunknown

Community Discussion Evidence

12 source-linked items

Review these external discussions before using agent-browser with real data or production workflows. They are review inputs, not standalone proof that the project is production-ready.

01
`--cdp` eval/open silently target a secondary execution context when Chr
github / github_issue
02
Feature: `network throttle` for emulating slow connections / per-URL del
github / github_issue
03
Orphaned headless Chrome Helpers spin at high CPU under agent-browser-ch
github / github_issue
04
snapshot -s <selector> produces duplicate elements when AX tree contains
github / github_issue
05
Support XDG Base Directory paths for agent-browser state, config, and in
github / github_issue
06
After failed close, subsequent open reports success but returns stale co
github / github_issue
07
Chrome 147.0 crashes with "trap int3" when running in docker
github / github_issue
08
`--auto-connect` fails too quickly when Chrome asks for remote debugging
github / github_issue
09
High LLM turn count due to frequent `snapshot` calls when using `agent-b
github / github_issue
10
Support enabling WebAuthn for passkey authentication with a virtual auth
github / github_issue
11
Feature Request: Chrome Extension-based Connection for Seamless Login St
github / github_issue
12
Detected: Trojan:Win32/Posilod.EB!cl
GitHub / issue

How to start

Only source-backed commands are shown here. Verify them in an isolated environment first.

Try the prompt first

Test the workflow without installing the upstream project.

preview

Read the Human Manual

Understand inputs, outputs, limits, and failure modes.

manual

Take context to your AI host

Use the compiled assets in your preferred AI environment.

context

Run sandbox verification

Confirm install commands and rollback before using a primary environment.

verify

npm install -g agent-browser

Official start command · https://github.com/vercel-labs/agent-browser#readme · verified: yes

Human Manual

The English page must expose the real manual, not a short placeholder.

8+ sections · Human Manual

agent-browser Manual

Agent Browser serves as a bridge between AI agents and web browsers, enabling autonomous web navigation, interaction, and data extraction. It is compatible with a wide range of AI agent pl...

Open the full manual

agent-browser Human Manual
Table of Contents
Introduction to Agent Browser
Related Pages
Overview
Architecture
Core Concepts
Accessibility-Tree Snapshots

Introduction to Agent Browser

Related topics: Installation Guide, Architecture Overview

Source: https://github.com/vercel-labs/agent-browser / Human Manual

Installation Guide

Related topics: Introduction to Agent Browser

Sources: [AGENTS.md](https://github.com/vercel-labs/agent-browser/blob/main/AGENTS.md)

Element References System

Related topics: State Inspection Commands, Interaction Commands

Sources: [skill-data/core/references/snapshot-refs.md]()

Architecture Overview

Related topics: Daemon and CDP Protocol, Introduction to Agent Browser

Sources: [cli/src/native/mod.rs]()

Daemon and CDP Protocol

Related topics: Architecture Overview, Browser Engine Integration

Sources: [cli/src/native/actions.rs](cli/src/native/actions.rs)

AI Context Pack and portable assets

After deciding to continue, take the project context into your own AI host.

Complete pack plus user-owned assets

These files are planning and verification assets for Claude Code, Codex, Gemini, Cursor, ChatGPT, and other AI hosts.

Download complete pack Read Human Manual

BundleComplete Project Pack AssetAI Context Pack AssetBoundary & Risk Card AssetHuman Manual AssetPitfall Log AssetPrompt Preview AssetQuick Start ManifestPROJECT_PACK.json

Preflight checks

Treat this page as a planning asset, not proof that your local environment is ready.

The manual is generated from source-linked project files and Doramagic validation signals.
Community evidence warnings stay visible instead of being converted into marketing claims.
This English page is indexable because the locale quality gate passed and explicit English index approval is enabled.
Use the upstream repository as the final authority for installation commands, license, and version-specific behavior.

Pitfall Log and verification risks

Doramagic surfaces high-risk items before users treat a candidate capability as verified.

high

Review upstream issue

The source signal needs review before production use.

high

Review upstream issue

The source signal needs review before production use.

high

Review upstream issue

The source signal needs review before production use.

high

Review upstream issue

The source signal needs review before production use.

high

Review upstream issue

Developers may expose sensitive permissions or credentials: Dashboard privileged POST routes should reject cross-origin requests

high

Review upstream issue

Developers may expose sensitive permissions or credentials: `--auto-connect` fails too quickly when Chrome asks for remote debugging permission

high

Review upstream issue

The source signal needs review before production use.

medium

Review upstream issue

Developers may fail before the first successful local run: After failed close, subsequent open reports success but returns stale content from prior URL