Playwright Agent

🚀 AgentKit Browser Automation Framework

An advanced browser automation framework built on AgentKit, leveraging a multi-agent system for intelligent web navigation and task execution.

🚀 Quick Start

Dependencies

• Node.js (v14 or higher)
• npm or yarn
• OpenAI API key (for GPT models)

Installation

1. Clone the repository:

git clone https://github.com/tmahesh/playwright-agent.git
cd playwright-agent

2. Install the dependencies:

npm install

3. Set up environment variables:

cp .env.sample .env
# Edit the .env file with your OpenAI API key and other configurations

4. Run the following commands in different terminals: index.ts, playwright-mcp, inngest-cli

npx @playwright/mcp@latest --port 8931

npx tsx index.ts

npx inngest-cli@latest dev --no-discovery -u http://localhost:3000/api/inngest -v

✨ Features

• Intelligent Task Planning: Break down complex tasks into manageable steps.
• State Management: Track browser states and operation results.
• Error Handling: Robust error handling and recovery mechanisms.
• Event System: Comprehensive event logging and monitoring.
• Flexible Action System: An extensible action registry to support custom behaviors.
• Validation Framework: Built - in validation features to confirm task completion.
• Memory Management: Maintain operation context and history.

📚 Documentation

Overview

This project implements a multi - agent system based on AgentKit for browser automation. Different agents work together to achieve the following goals:

• Plan and decompose tasks
• Navigate web pages
• Perform browser operations
• Validate results

Architecture (To be determined)

The system consists of four specialized agents:

1. Planning Agent

   • Decompose tasks into executable steps
   • Create detailed execution plans
   • Determine task completion criteria

2. Navigation Agent

   • Determine the next action
   • Manage state transitions
   • Handle action execution
   • Provide detailed logs and feedback

3. Browser Agent

   • Perform browser automation operations
   • Interact with web elements
   • Handle page navigation
   • Manage browser states

4. Validation Agent

   • Validate task completion
   • Verify results
   • Handle error situations
   • Provide success/failure feedback

🤝 Contribution Guidelines

1. Fork and clone the repository.
2. Create a feature branch.
3. Commit your changes.
4. Push to the branch.
5. Create a pull request.