Website | Documentation | Discord | Twitter

Open source browser automation library for AI agents

Browserable allows you to build browser agents that can navigate sites, fill out forms, clicking buttons and extract information. It is currently at 90.4% on the Web Voyager benchmarks.

Quick start

The fastest way to get started is to run the npx command. This will guide you through the setup process and ensure you have all required dependencies.

npx browserable

Visit http://localhost:2001 to set your LLM and Remote Browser API Keys to start using.

Manual setup

Clone the repository:

git clone https://github.com/browserable/browserable.git
cd browserable

Pre-requisites:

• Install Docker
• Install Docker Compose

Start the development environment:

cd deployment
docker-compose -f docker-compose.dev.yml up

Set your API keys:

• Open Browserable admin dashboard: http://localhost:2001/dash/@admin/settings.
• Set API key of any one LLM provider (Gemini/ Open AI/ Claude).
• Sign up for a free plan with any one remote browser provider (Hyperbrowser/ Steel).
• Set the API key of the remote browser provider in your Browserable admin dashboard.

Services

Once running, you'll have access to the following services:

Service	URL/Port	Description
UI Server	http://localhost:2001	Main user interface
Documentation	http://localhost:2002	Local documentation
Tasks Server	http://localhost:2003	Task management API
MongoDB	27017	Database
MongoDB Express UI	http://localhost:3300	Database management
Redis	6379	Caching and queues
MinIO API	http://localhost:9000	Object storage API
MinIO Console	http://localhost:9001	Object storage UI
DB Studio	http://localhost:8000	Database management

JavaScript SDK

Install the SDK using npm:

npm install browserable-js

Or using yarn:

yarn add browserable-js

Here’s a simple example to get you started:

import { Browserable } from 'browserable-js';

// Initialize the SDK
const browserable = new Browserable({
  apiKey: 'your-api-key'
});

// Create and run a task
async function runTask() {
  const createResult = await browserable.createTask({
    task: 'Find the top trending GitHub repos of the day.',
    agents: ['BROWSER_AGENT']
  });

  // Wait for task completion
  const result = await browserable.waitForRun(taskId);
  console.log('Results:', result.data);
}

Demos

Task: On amazon.com search for a yoga mat at least 6mm thick, non-slip, eco-friendly, and under $50.

Task: On arxiv.org locate the latest paper within the 'Nonlinear Sciences - Chaotic Dynamics' category, summarize the abstract, and note the submission date.

Task: On coursera.com find a beginner-level online course about '3d printing' which lasts 1-3 months, and is provided by a renowned university.

Configuration options

Browserable offers configuration options for:

• LLM Providers
• Storage Solutions
• Database Systems
• Remote Browsers
• Custom Functions

For a complete list of environment variables and their configurations, see Environment Variables Documentation.

Documentation

See browserable.ai/docs for full documentation, or you can check the REST API reference/ JS SDK guide.

Contributing

Browserable is an open-source and self-hostable project. We welcome contributions! 💛

Here's how you can help:

1. Fork the repository.
2. Create your feature branch (git checkout -b feature/AmazingFeature).
3. Commit your changes (git commit -m 'Added AmazingFeature').
4. Push to the branch (git push origin feature/AmazingFeature).
5. Open a pull request.

Support

Questions/ feedback? Join Discord.

Acknowledgments

Some amazing open source projects Browserable wouldn't have been possible without: bull, mongo-express, Stagehand, Supabase.