PluginStackWhat it does
Vercel's provider-agnostic TypeScript toolkit for building AI apps and agents. It works with Next.js, React, Svelte, Vue, Angular and Node.js, and its UI hooks cover React, Svelte and Vue. One API covers OpenAI, Anthropic, Google and many more providers, either through Vercel AI Gateway (the default) or each provider's own package. Apache-2.0.
Who it's for
Web developers adding chat, streaming or agent features to a JavaScript or TypeScript app. The SDK is free; AI Gateway is a pay-as-you-go Vercel service with a limited free tier, or you can use your own provider keys through the provider packages.
How to set it up
Needs Node.js 22+. Install:
bashnpm install aiTo call providers directly instead of through AI Gateway, add their packages:
bashnpm install @ai-sdk/openai @ai-sdk/anthropic @ai-sdk/googleFor React chat UIs:
bashnpm install @ai-sdk/reactUsing Claude Code or Cursor? Add the AI SDK skill to your repo:
bashnpx skills add vercel/ai
Check the official AI SDK docs for the latest steps.
Example prompts
Add a streaming chat page to my Next.js app using the AI SDK and useChat.Give this AI SDK agent a tool that searches our product database.Switch this generateText call from OpenAI to Anthropic.Demo
Demo coming soon
A short walkthrough of AI SDK in action.
More Agent Frameworks
- CrewAI
CrewAI
A Python framework for multi-agent automation. Crews are teams of role-based agents that work together on a task; Flows are event-driven workflows with state and branching that can call crews. The CLI scaffolds projects, which are JSON-first by default. MIT licensed.
- LangChain
LangGraph
A low-level framework for building long-running, stateful agents as graphs. It provides durable execution (agents resume after failures), human-in-the-loop interrupts and short- and long-term memory. It works on its own or with LangChain and LangSmith. A JS version (LangGraph.js) is also available. MIT licensed.
- Mastra
Mastra
A TypeScript framework for AI apps and agents. It includes model routing across 40+ providers, agents with tools, graph-based workflows with suspend/resume, memory and RAG, MCP server authoring, evals and observability, plus a local Studio UI. Apache-2.0, except code in ee/ folders, which uses an enterprise license.
- OpenAI
OpenAI Agents SDK
A lightweight Python framework for building agents and multi-agent workflows. It covers agents with tools and handoffs, guardrails, human-in-the-loop, sessions, tracing, sandbox agents and voice/realtime agents. It works with OpenAI's APIs and, per the README, 100+ other LLMs. A JS/TS version exists too. MIT licensed.
- Pydantic
Pydantic AI
A typed Python agent framework from the Pydantic team. You define agents with typed outputs and tools, and switching model providers is a one-string change. Companion packages add a harness for long-running agents (files, shell, sub-agents) and Pydantic Evals for testing. MIT licensed.