Provider-agnostic TypeScript toolkit for streaming, tool calls and chat UIs.
The AI SDK is Vercel's open-source TypeScript library for calling LLMs and building chat interfaces and agents on top of them. It puts one interface over the different provider APIs, so moving from one model vendor to another is a change of model, not a rewrite.
It has three parts. AI SDK Core has functions such as generateText and streamText, schema-checked structured output, tool calling, and a ToolLoopAgent class that runs the model-and-tools loop with stopping conditions. Providers are separate packages (@ai-sdk/openai, @ai-sdk/anthropic and many more) that implement a shared specification; a plain model string like anthropic/<model> goes through Vercel AI Gateway unless you set a different default provider. AI SDK UI has hooks (useChat, useCompletion, useObject) for React, Vue, Svelte, Angular and SolidJS. A third surface runs existing agent harnesses such as Claude Code and Codex. Core runs in Node.js and Deno as well as inside Next.js, Nuxt and SvelteKit.
The UI hooks handle streamed messages and loading and error state, and they read a documented stream protocol, so the backend can be written in another language, such as Python with FastAPI. Agents can connect to MCP servers over HTTP. It is a library with no hosted service required: it deploys wherever your JavaScript runs, and the Gateway is optional.
It is a toolkit, not a full agent platform: storing chat history is something you implement around useChat and streamText. The migration guides list four major versions, 4.0 through 7.0, and APIs prefixed experimental_ can change in any release.
2 tools, from its own code, website and Product Hunt page.
4 makers' products, each linked to the source that shows it, and 193 open-source projects that declare it in their code.
onlookOpen-source visual editor for React apps: designers edit the UI and the changes are writ…“• TypeScript-first, ergonomic API with excellent Next.js integration; streaming and tool calling are rock solid. • Consistent abstractions across multiple model providers (great with OpenRouter) minimize vendor lock-in and churn. • Clear docs and examples reduce boilerplate and accelerate iteration; fewer edge-case failures in production.”
AI SDK & Agent FrameworkMaker says so +1 · source ↗“AI SDK made super simple to integrate all the different models into our app. Its the best sdk for build ai apps right now.”
AI SDK & Agent FrameworkMaker says so · source ↗
QuartrGo beyond numbers“Used for multi-agent orchestration, state management, debugging, and structured artifact streaming for our AI application.”
AI SDK & Agent FrameworkMaker says so · source ↗“I liked it because its a unified TypeScript SDK for building AI apps. Helped building Zyntax Agent.”
AI SDK & Agent FrameworkMaker says so · source ↗Open source: a project that declares AI SDK as a dependency in its public code — verifiable, but not necessarily a live product.
5 makers on why they use AI SDK, in their own words on Product Hunt.
• TypeScript-first, ergonomic API with excellent Next.js integration; streaming and tool calling are rock solid. • Consistent abstractions across multiple model providers (great with OpenRouter) minimize vendor lock-in and churn. • Clear docs and examples reduce boilerplate and accelerate iteration; fewer edge-case failures in production.
onlookSep 2026 ↗• TypeScript-first, ergonomic API with excellent Next.js integration; streaming and tool calling are rock solid. • Consistent abstractions across multiple model providers (great with OpenRouter) minimize vendor lock-in and churn. • Clear docs and examples reduce boilerplate and accelerate iteration; fewer edge-case failures in production.
onlookAug 2025 ↗Used for multi-agent orchestration, state management, debugging, and structured artifact streaming for our AI application.
QuartrSep 2026 ↗AI SDK made super simple to integrate all the different models into our app. Its the best sdk for build ai apps right now.
I liked it because its a unified TypeScript SDK for building AI apps. Helped building Zyntax Agent.
Themes that recur in makers' words and Hacker News comments, each linked to what it summarises, with how Product Hunt tags its reviews.
Public pull requests on GitHub since Oct 2024 whose title says "X to Y" — real code changes moving a project from one tool to another, by developers in general. Open a row to see the pull requests.
LangChain → AI SDK4 PRsAI SDK → LangChain3 PRsYes. The UI hooks support React, Svelte, Vue.js, Angular and SolidJS, and AI SDK Core also runs in plain Node.js or Deno with no UI framework. source ↗
Yes. useChat reads a documented stream protocol (Server-Sent Events with the x-vercel-ai-ui-message-stream: v1 header), so any backend that emits it works; the docs link a FastAPI example. source ↗
No. Plain model strings use Vercel AI Gateway as the default global provider, but you can set your own default, such as the OpenAI provider, or pass provider instances to call vendors directly. source ↗
No. You write the load and save functions around useChat and streamText; the guide stores messages in files as an example and says to use a database in a real app. source ↗
Breaking changes to stable APIs only come in major versions, which ship with migration guides and codemods where possible. APIs prefixed experimental_ can change in any release, so pin the exact version if you use them. source ↗
Yes. The MCP client connects over HTTP (recommended for production), SSE or stdio, which is for local servers only, and gives the model the server's tools. source ↗
Yes — it is free, open-source software.
Open source, and you can self-host it. source ↗
No llms.txt, official MCP server or CLI found yet.
4 makers' products we track, each with a source, and 193 open-source projects declare it in their code. source ↗
Next.js
Vercel
Mastra
LlamaIndex
OpenAI Agents SDK
Pydantic AI
Claude Agent SDK
LangGraph
CrewAI