Browsor Agent

AI agent that automates any repetitive browser task from screen recordings

How To Use • API Integrations • License

How To Use

To clone and run this application, you'll need Git and Node.js (which comes with npm) installed on your computer. You'll also need API keys for the integrated services. From your command line:

# Clone this repository
$ git clone https://github.com/hireshb/junction-ai-hack

# Go into the repository
$ cd junction-ai-hack

# Install dependencies
$ npm install

# Set up environment variables
$ cp .env.example .env.local
# Add your API keys to .env.local:
# OPENAI_API_KEY=your_openai_api_key_here
# TWELVELABS_API_KEY=your_twelvelabs_api_key_here
# HYPERBROWSER_API_KEY=your_hyperbrowser_api_key_here

# Run the development server
$ npm run dev

Open http://localhost:3000 with your browser to see the result.

Note You'll need valid API keys for TwelveLabs, OpenAI, and Hyperbrowser to use the full functionality.

API Integrations

This application integrates with several powerful AI and automation services:

🎥 TwelveLabs

• Get Started: Sign up at TwelveLabs for your API key

🧠 OpenAI

• Get Started: Obtain your API key from OpenAI Platform

🌐 Hyperbrowser

• Get Started: Sign up at Hyperbrowser for your API key

Demo

1. Upload a screen recording of a workflow you want to automate (or use the default one)
2. Add optional context to guide the AI analysis (for customising the workflow)
3. Click "Run Agent" to start the three-stage process:
   • 📹 Video analysis (TwelveLabs)
   • 📝 Step generation (OpenAI GPT-4o)
   • 🤖 Browser automation (Hyperbrowser Agent)

Contributing

Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

---

GitHub @hireshb  ·  Twitter @hiresh_b