AI-Powered Workflow Automation Platform
Build, automate, and scale your workflows with visual node-based editor and AI capabilities.
Lumos.ai is a modern, open-source workflow automation platform that empowers you to create sophisticated automation workflows through an intuitive visual interface. Similar to n8n and Zapier, but with AI-first approach and built on cutting-edge technology.
Whether you're automating business processes, integrating APIs, or building complex data pipelines, Lumos.ai provides the tools you need with the flexibility of code when you need it.
- Visual Workflow Builder: Drag-and-drop interface powered by React Flow for intuitive workflow creation
- AI-Powered: Built-in AI capabilities with Google AI SDK integration
- Developer-First: Built with TypeScript, tRPC, and modern web technologies
- Self-Hosted: Full control over your data and deployments
- Extensible: Easy to add custom nodes and integrations
- Real-Time: Background job processing with Inngest
-
Visual Workflow Editor
- Intuitive node-based interface
- Real-time workflow visualization
- Drag-and-drop node connections
- Mini-map and zoom controls
-
Trigger Nodes
- Manual triggers for on-demand execution
- HTTP request triggers
- Scheduled triggers (coming soon)
- Webhook support (coming soon)
-
Execution Nodes
- HTTP requests
- Data transformations (coming soon)
- AI operations (coming soon)
- Custom code execution (coming soon)
-
User Management
- Secure authentication with Better Auth
- Email/password and OAuth support
- Session management
- Role-based access control (coming soon)
-
Workflow Management
- Create, edit, and delete workflows
- Version control (coming soon)
- Workflow templates (coming soon)
- Import/export workflows (coming soon)
-
Execution History
- Track all workflow executions
- Detailed execution logs
- Error tracking and debugging
- Performance metrics (coming soon)
-
Credentials Management
- Secure credential storage
- Reusable across workflows
- Multiple authentication methods
- Encrypted at rest
Lumos.ai is built with modern, production-ready technologies:
- Next.js 15 - React framework with App Router
- React 19 - UI library
- TypeScript - Type safety
- Tailwind CSS - Styling
- React Flow - Workflow visualization
- Radix UI - Accessible components
- Jotai - State management
- tRPC - End-to-end typesafe APIs
- Prisma - Database ORM
- PostgreSQL - Database
- Better Auth - Authentication
- Inngest - Background jobs
- Google AI SDK - AI capabilities
- Vercel AI SDK - AI orchestration
- Node.js 20+ and npm/pnpm/yarn
- PostgreSQL database
- Google AI API key (optional, for AI features)
-
Clone the repository
git clone https://github.com/VINODvoid/lumos.ai.git cd lumos.ai -
Install dependencies
npm install # or pnpm install # or yarn install
-
Set up environment variables
Create a
.envfile in the root directory:# Database DATABASE_URL="postgresql://user:password@localhost:5432/lumos" # Auth BETTER_AUTH_SECRET="your-secret-key" BETTER_AUTH_URL="http://localhost:3000" # Google AI (optional) GOOGLE_AI_API_KEY="your-google-ai-key" # Inngest INNGEST_EVENT_KEY="your-inngest-key" INNGEST_SIGNING_KEY="your-inngest-signing-key" # Sentry (optional) SENTRY_DSN="your-sentry-dsn"
-
Set up the database
npx prisma generate npx prisma db push
-
Run the development server
npm run dev
Open http://localhost:3000 in your browser.
- Create an account - Sign up at
/signup - Create your first workflow - Navigate to workflows and click "New Workflow"
- Add nodes - Click the "+" button to add trigger and execution nodes
- Connect nodes - Drag connections between nodes to build your workflow
- Execute - Run your workflow and view execution results
lumos.ai/
├── prisma/
│ └── schema.prisma # Database schema
├── src/
│ ├── app/ # Next.js app directory
│ │ ├── (auth)/ # Authentication pages
│ │ ├── (dashboard)/ # Dashboard pages
│ │ └── api/ # API routes
│ ├── components/ # Shared components
│ │ └── ui/ # UI component library
│ ├── features/ # Feature modules
│ │ ├── auth/ # Authentication
│ │ ├── editor/ # Workflow editor
│ │ ├── executions/ # Execution nodes
│ │ ├── triggers/ # Trigger nodes
│ │ └── workflows/ # Workflow management
│ ├── hooks/ # Custom React hooks
│ ├── lib/ # Utility libraries
│ ├── trpc/ # tRPC setup and routers
│ └── inngest/ # Background job functions
├── .env # Environment variables
├── package.json
└── tsconfig.json
# Start development server with Turbopack
npm run dev
# Build for production
npm run build
# Start production server
npm run start
# Lint code
npm run lint
# Format code
npm run formatTo add a new node type:
- Define the node type in
prisma/schema.prisma - Create node component in
src/features/[category]/components/ - Register node in
src/config/node-components.ts - Add node logic to execution engine
# Create a migration
npx prisma migrate dev --name your_migration_name
# Apply migrations
npx prisma migrate deploy
# Reset database (development only)
npx prisma migrate resetThe easiest way to deploy Lumos.ai is using Vercel:
- Push your code to GitHub
- Import project in Vercel
- Configure environment variables
- Deploy
# Build image
docker build -t lumos-ai .
# Run container
docker run -p 3000:3000 lumos-aiRequirements:
- Node.js 20+ runtime
- PostgreSQL database
- Reverse proxy (nginx/caddy) for HTTPS
npm run build
npm run start| Variable | Description | Required |
|---|---|---|
DATABASE_URL |
PostgreSQL connection string | Yes |
BETTER_AUTH_SECRET |
Secret key for authentication | Yes |
BETTER_AUTH_URL |
Application URL | Yes |
GOOGLE_AI_API_KEY |
Google AI API key | No |
INNGEST_EVENT_KEY |
Inngest event key | Yes |
INNGEST_SIGNING_KEY |
Inngest signing key | Yes |
SENTRY_DSN |
Sentry error tracking DSN | No |
We welcome contributions! Here's how you can help:
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
- Follow TypeScript best practices
- Write meaningful commit messages
- Add tests for new features
- Update documentation as needed
- Use Biome for code formatting
Note: Lumos.ai is currently under active development. Many features are still being built and refined.
- Core workflow execution engine
- Additional trigger types (Webhooks, Schedules, Email)
- More execution nodes (Database, File operations, Transformations)
- AI-powered node suggestions
- Error handling and retry mechanisms
- Workflow testing and debugging tools
- Workflow templates library
- Team collaboration features
- Advanced debugging tools
- API for programmatic workflow management
- Marketplace for custom nodes
- Real-time workflow monitoring dashboard
- Workflow versioning and rollback
- Mobile app for monitoring
- Webhook integrations
- Data transformation nodes
- Conditional logic nodes
- Loop and iteration support
- Documentation: Coming soon
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- Discord: Coming soon
This project is licensed under the MIT License - see the LICENSE file for details.
Built with inspiration from:
Special thanks to all the open-source projects that make Lumos.ai possible.
Made with ❤️ by the Lumos.ai team