devtools

browserless: Automate Browser Tasks

Name: browserless: Automate Browser Tasks
Author: microlinkhq

Automate browser tasks with a production-ready API.

advanced⏱ 1-2 hours💵 Free + LLM API costs (if used with AI models like those in Claude API)

1,832 stars91 forksJavaScriptGuide quality 8/10Updated 9/6/2026100% free · open source

What it is

Control headless Chrome/Chromium to automate tasks like screenshots and text extraction.

Real use case example

"A solo developer uses Browserless to create an automated PDF report for her customers, taking a 30-minute task down to 5 minutes: first, she writes a Python script using Puppeteer; next, she adds Browserless to automate the Chrome browser; finally, she runs the script to generate the report and shares it with her customers."

Best insideCodex CLICursorClaude Desktop

When to use it

•When you need to automate browser interactions for web scraping or data extraction
•When you want to generate screenshots or PDFs of web pages programmatically
•When you need to integrate browser automation into your application or workflow

Ready-to-paste prompt

curl -X POST localhost:3000/screenshot --data-urlencode 'url=https://example.com&width=1920&height=1080' > screenshot.png

Heads up: Make sure you have Docker installed and running on your system, as browserless is designed to be run as a Docker container

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/browserless && curl -fsSL https://workflowstacks.com/api/skills/browserless/claude-skill -o ~/.claude/skills/browserless/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How browserless: Automate Browser Tasks works

Codeflow

Free to inspect

Browserless: Automate Browser Tasks is a medium JavaScript project (~7.7k lines across 89 code files, plus 40 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, MIT license, has a test suite.

Size

Medium codebase

~7.7k lines · 89 code files · ~1 h to skim

Setup

One-command install

Installs like a normal app. Reading the code is optional.

Runs on

Node.js

No API keys detected

JavaScript 99%HTML 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
package.json
Dependencies and the commands it exposes
3
packages/browserless/README.md
Inside packages/browserless/ — the main logic begins here

What's in each folder

packages/browserless/Core code — the actual logic18 files

packages/cli/Command-line entry points18 files

packages/function/Backend / API9 files

docs/Documentation2 files

packages/screenshot/Package37 files

packages/capture/Package25 files

packages/ai/Package20 files

packages/goto/Package20 files

READMEHas testsDocumentedCI checksMIT licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/browserless && curl -fsSL https://workflowstacks.com/api/skills/browserless/claude-skill -o ~/.claude/skills/browserless/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

microlinkhq

Language

JavaScript