Skip to content

shoegazerstella/broski

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

    ____                  __   _
   / __ )_________  _____/ /__(_)
  / __  / ___/ __ \/ ___/ //_/ /
 / /_/ / /  / /_/ (__  ) ,< / /
/_____/_/   \____/____/_/|_/_/

     your browser automation pal 🤙

broski 🤖

Open-source browser automation platform with a visual workflow builder. Built on agent-browser, broski makes it easy to create, manage, and execute browser automation workflows without writing code.

Broski Demo

What is broski?

Broski provides a web-based UI for building browser automation workflows. Create agents that can:

  • Navigate websites and fill forms
  • Click buttons and interact with elements
  • Extract data from pages
  • Take screenshots and monitor changes
  • Test web applications end-to-end

Perfect for:

  • 🧪 QA Engineers - Automated UI testing without code
  • 🤖 AI Agent Developers - Browser automation for AI agents
  • 🔧 No-code Users - Visual workflow builder for browser tasks
  • 📊 Monitoring - Track website changes and availability

Quick Start

# One-command setup
./setup.sh

# Start the app
./start-broski.sh

# Visit http://localhost:3000

That's it! The app runs in demo mode (no database required). Create projects, build workflows, and watch your browser execute them live.

Features

✅ Available Now

  • Visual Workflow Builder - Create automation steps with a clean UI
  • 20+ Templates - Pre-built workflows for common tasks
  • Live Execution - Watch browser automation happen in real-time
  • Screenshot Capture - Automatic screenshots during execution
  • Project Organization - Organize agents by project
  • Demo Mode - No setup required, uses localStorage

🚧 Coming Soon

  • AI Template Generation - Describe your workflow in natural language, get a complete agent
  • Drag & Drop Builder - Visual editor with step reordering
  • Scheduling - Run agents on cron schedules
  • Webhooks & API - Trigger agents programmatically
  • Cloud Execution - Run agents in Vercel Sandboxes
  • Team Collaboration - Share agents and templates with your team

Tech Stack

  • Frontend: Next.js 15, React 19, TypeScript, Tailwind CSS
  • Automation: agent-browser (Chromium-based)
  • Storage: localStorage (demo) / Supabase (planned)
  • Components: shadcn/ui

Project Structure

broski/
├── broski/              # Next.js web application
│   ├── src/app/        # Pages and API routes
│   ├── src/components/ # React components
│   └── src/lib/        # Storage, templates, action blocks
├── agent-browser/      # Git submodule (automation engine)
├── setup.sh           # Installation script
├── start-broski.sh    # Start script
└── CLAUDE.md          # AI development guide

How It Works

  1. Create a Project - Organize related automation agents
  2. Build a Workflow - Use templates or create custom command sequences
  3. Execute - Run in headed mode to watch the browser work
  4. Review Results - View logs, screenshots, and execution history

Example workflow:

open https://example.com
wait 2000
fill #search "test query"
press Enter
wait-for .results
screenshot results.png

Contributing

We welcome contributions! Here's how you can help:

🐛 Report Issues

Found a bug? Open an issue with:

  • Steps to reproduce
  • Expected vs actual behavior
  • Screenshots if applicable

💡 Request Features

Have an idea? Start a discussion or open an issue with the enhancement label.

🔧 Submit Pull Requests

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Make your changes
  4. Test thoroughly (run existing agents to ensure they still work)
  5. Commit with clear messages (git commit -m 'Add amazing feature')
  6. Push to your fork (git push origin feature/amazing-feature)
  7. Open a Pull Request

Development Setup:

cd broski
pnpm dev        # Start dev server
pnpm build      # Test production build
pnpm lint       # Check code style

📖 Improve Documentation

  • Fix typos or unclear sections
  • Add examples and use cases
  • Write tutorials or guides

🎨 Design Contributions

  • UI/UX improvements
  • New component designs
  • Branding assets

Roadmap

Phase 1: Core Platform

  • Visual workflow builder
  • Template library
  • Live execution monitoring
  • Project management

Phase 2: AI & Automation (In Progress)

  • AI-powered template generation from natural language
  • Advanced drag-and-drop builder
  • Scheduled execution
  • Webhook triggers

Phase 3: Cloud & Scale

  • Supabase integration for multi-user support
  • Cloud execution via Vercel Sandboxes
  • Advanced analytics and reporting
  • Performance optimizations

Phase 4: Collaboration

  • Team workspaces
  • Shared template marketplace
  • Access control and permissions
  • Audit logs

See ARCHITECTURE.md for detailed technical design.

Documentation

License

MIT (coming soon)

Support

  • 💬 Discussions: Ask questions and share ideas
  • 🐛 Issues: Report bugs or request features
  • 📧 Contact: Create an issue for support

Built with ❤️ using agent-browser

About

Visual browser automation for humans. Create web scraping, testing, and monitoring workflows with a drag-and-drop UI — then watch Chromium do the work live.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages