A visual AI playground. Tersa is an open source canvas for building AI workflows. Drag, drop connect and run nodes to build your own workflows powered by various industry-leading AI models.
- Visual Workflow Builder: Create AI workflows by connecting nodes in an intuitive drag-and-drop interface
- Multiple AI Models: Seamlessly integrate with leading AI models from various providers
- Multimedia Processing: Process images, text, audio, and video content through your workflows
- Automatic Saving: Changes are automatically saved to your projects
- Cloud Storage: All workflows are securely stored in Supabase with Row Level Security enabled
- Modern UI: Clean, responsive interface built with Next.js, React, and Tailwind CSS
- Next.js 15 with App Router and Turbopack
- React 19
- Supabase for authentication and data storage
- Vercel AI SDK for AI model integration
- ReactFlow for the visual canvas
- TipTap for rich text editing
- Drizzle ORM for database queries
- Tailwind CSS for styling
- shadcn/ui, Kibo UI and Radix UI for accessible UI components
- Node.js (v20+)
- PNPM package manager
- Supabase account and project
- Supabase CLI installed
- Stripe CLI installed
-
Clone the repository
git clone https://github.com/haydenbleasel/tersa.git cd tersa
-
Install dependencies
pnpm install
-
Create a
.env.local
file in the root directory with your environment variables. Check thelib/env.ts
file for all the variables you need to set. -
Run the development server
pnpm dev
-
Open http://localhost:3000 in your browser
- Login or create an account
- Create a new project or open an existing one
- Add nodes to your canvas by clicking the toolbar buttons
- Connect nodes by dragging from one node's output to another node's input
- Configure node settings as needed
- Run your workflow to process data through the AI models
This project is licensed under the MIT License - see the LICENSE file for details.
Made with ❤️ and 🤖 by Hayden Bleasel.