The AI SDK is built for the web. Streaming text to a React component, tool calls, structured output and generative UI are the first class ideas, and it works the same in Next.js, Svelte and Vue.
Reach for it when
- Your app is TypeScript and the agent lives in the product
- You want streaming UI without writing the plumbing
- You are deploying to the edge
Look elsewhere when
- Your stack is Python
- You need long running agent loops on a server
What the lessons will cover
- 01Install and setup
- 02generateText and streamText
- 03Tools
- 04Structured output
- 05useChat in React
- 06Generative UI
- 07Agents and loops
- 08Deploying
Others in vendor sdk
Google ADK
OpenAI Agents SDKOpenAI's own agent loop, with handoffs and guardrails.
Claude Agent SDKClaude Code as a library you can run yourself.
Semantic KernelMicrosoft's SDK for wiring models into real applications.Common questions
Is Vercel AI SDK free to use?
Vercel AI SDK is open source and free to run yourself. You still pay whichever model provider you point it at, and this tutorial is free with no signup.
Do I need to know Python to use Vercel AI SDK?
No. Vercel AI SDK is a TypeScript library, so JavaScript or TypeScript is what you need.
When should I not use Vercel AI SDK?
Your stack is Python. You need long running agent loops on a server.
Lessons for Vercel AI SDK are being written. Meanwhile the LangGraph tutorial covers the same ground: state, tools, loops, memory and human approval. Most of it carries straight over.
Start the LangGraph tutorial →