{"repo":"vercel-labs/tersa","free":true,"listed":false,"github":"https://github.com/vercel-labs/tersa","clone":"git clone https://github.com/vercel-labs/tersa.git","description":"Tersa is an open source canvas for building AI workflows.","language":"TypeScript","stars":1038,"topics":["ai","aisdk","anthropic","canvas","openai"],"license":"MIT","category":"ai-agents","readme_excerpt":"Tersa A visual AI playground. Drag, drop, connect and run nodes to build AI workflows powered by the Vercel AI SDK Gateway. Features - Visual Workflow Builder : Create AI workflows by connecting nodes in a drag-and-drop canvas - Multi-Model Support : Access text, image and video models from 25+ providers through Vercel AI SDK Gateway - Cost Indicators : See relative pricing across models at a glance - Reasoning Extraction : View model reasoning for supported providers - Streaming Responses : Real-time text generation with streaming support - Local Storage : Canvas state persists in the browser automatically Technologies - Next.js 15 with App Router and Turbopack - React 19 - Vercel AI SDK with AI SDK Gateway - Vercel Blob for media storage - ReactFlow for the visual canvas - TipTap for rich text editing - Tailwind CSS for styling - shadcn/ui, Kibo UI and Radix UI for UI components Getting Started Prerequisites - Node.js (v20+) - PNPM package manager Installation 1. Clone the repository 2. Install dependencies 3. Create a .env.local file with your AI SDK Gateway credentials and any provider API keys you want to use. 4. Run the development server 5. Open http://localhost:3000 in your browser Usage 1. Add nodes to the canvas using the toolbar 2. Connect nodes by dragging from one node's output to another's input 3. Select a model from any supported provider 4. Run your workflow to process data through the AI models License This project is licensed under the MIT License - see the","default_branch":null,"files":null,"tree":[],"storefront":"/r/vercel-labs","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/vercel-labs/tersa/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}