AI Web Operator: Browser Automation, an Open Source Implementation of OpenAI Operator

General Introduction

AI Web Operator is an open source AI browser manipulation tool designed to simplify the user experience in the browser by integrating multiple AI technologies and SDKs. Built on Browserbase and the Vercel AI SDK, the tool supports a variety of Large Language Models (LLMs), such as Anthropic AI Web Operator is a flexible and scalable solution for developers, researchers, and users interested in AI technology, with simple configuration and installation that allows users to quickly get up and running with the tool, automating browser operations, persistent session management, and more.

Function List

• Automated Browser Operations: Automate browser operations by integrating with the Browserbase API.
• Persistent Session Management: Support for persistent sessions to keep a history of tasks.
• Multi-model support: Compatible with a variety of Large Language Models (LLMs) such as Anthropic Claude.
• Efficient development environment: Based on the Vercel AI SDK, it provides an efficient development and runtime environment.
• Open source and scalable: Fully open source, the user can be based on the demand for secondary development and expansion.

Using Help

Installation process

1. clone warehouse::

   git clone https://github.com/CognosysAI/browser.git
cd browser

2. Installation of dependencies: Use pnpm to install the dependencies:

   pnpm install

3. Configuring Environment Variables: Creation .env.local file and add the following:

   BROWSERBASE_API_KEY=your_key_here
BROWSERBASE_PROJECT_ID=your_key_here
ANTHROPIC_API_KEY=your_key_here
UPSTASH_REDIS_REST_URL=optional_redis_url
UPSTASH_REDIS_REST_TOKEN=optional_redis_token

4. Starting the Development Server::

   pnpm run dev

Open your browser to access http://localhost:3000The

Function Operation Guide

1. Automated Browser Operations::
   • After configuring the Browserbase API key and project ID, users can automate browser operations such as page navigation, form filling, etc. through API calls.
2. Persistent Session Management::
   • By configuring Upstash Redis, users can implement persistent session management and keep a history of tasks for subsequent operations.
3. Multi-model support::
   • After configuring the Anthropic API key, users can invoke a variety of large-scale language models for natural language processing tasks.
4. Efficient development environment::
   • Based on the Vercel AI SDK, it provides an efficient development and runtime environment that supports rapid iteration and deployment.