Home/Browserable
Browserable logo icon

Browserable

Browserable is an MIT-licensed, self-hostable JavaScript browser-agent library for navigation, form completion, information extraction, and task APIs.

Visit website
Browserable open-source JavaScript browser agent library

Product overview

What is Browserable?

Browserable is an open-source, self-hostable JavaScript library for building AI agents that execute tasks in a web browser. Agents can navigate websites, fill forms, extract information, track task status, and return results. The project is released under the MIT license and can run locally or on infrastructure controlled by the development team.

Browserable provides a JavaScript SDK and REST API for embedding browser tasks into applications. Its self-hosted development stack runs through Docker Compose and includes an administration interface, task service, browser infrastructure, databases, queues, and object storage. Developers can customize language models, remote browser providers, and tools rather than being tied to one model or browser vendor.

How to Use Browserable

  1. Install and start the local stack with npx browserable; Docker and Docker Compose are required.
  2. Open the local administration interface and configure the language-model API key.
  3. Create and test a browser task from the interface.
  4. Retrieve a Browserable API key from settings.
  5. Integrate task creation, status monitoring, and result retrieval through the REST API or browserable-js SDK.
  6. Customize the agent, tools, model, or remote browser provider for the target application.

Core Features

  • Browser task agents: Navigate websites, complete forms, and extract information.
  • Open-source self-hosting: Runs under the MIT license on developer-controlled infrastructure.
  • JavaScript SDK: Provides a typed integration path for JavaScript and TypeScript applications.
  • REST API: Creates and manages tasks, monitors execution, and retrieves results.
  • Provider flexibility: Supports customization of models and browser infrastructure.
  • Local administration: Includes an interface for configuring, testing, and managing agents.

Use Cases

  • Structured research: Agents search websites and return information matching detailed criteria.
  • Form automation: Applications submit repetitive browser forms from a task description.
  • Commerce research: Agents evaluate products against price and feature requirements.
  • Academic discovery: Workflows locate papers and summarize specified information.
  • Embedded web automation: Developers expose browser tasks inside a JavaScript application.

Frequently Asked Questions

Is Browserable open source?

Yes. Its documentation identifies the project as MIT licensed and self-hostable.

What is required for the quickstart?

The quickstart checks for Node.js, npm, Docker, and Docker Compose before starting the service stack.

Can Browserable be integrated without its UI?

Yes. Developers can use the REST API or JavaScript SDK.

Back to product directory

Related products

OpenAI Codex is an AI coding product for delegating scoped repository tasks and reviewing the resulting changes.

Claude Code is Anthropic’s AI coding product for iterative repository work through supported development surfaces.

Gemini CLI is Google’s open-source AI agent for terminal workflows and local development tasks.

Newsletter

Keep up with useful AI products

Get a concise selection of new products, practical use cases, and builder updates.