AI SDK

ai-sdk.dev ↗

TypeScript toolkit for building AI apps and agents with multiple model providers

SI Score
75/100
Pricing
Not confirmed
Free plan
Not confirmed
Sign-up required
Not confirmed

Ask SI about AI SDK

Answers use saved listing facts and recorded sources.
Homepage screenshot
Screenshot of the AI SDK homepage
SI REVIEWBased on the site's own pages, in a directory managed by people

What it does

The AI SDK is an open source TypeScript toolkit from Vercel for building AI applications and agents. It provides a unified API for generating text, structured objects and tool calls, framework-agnostic hooks for chat and generative interfaces, and an abstraction for running agent harnesses. It works with React, Next.js, Vue, Svelte, Node.js and other frameworks.

The documentation lists three primary surfaces. AI SDK Core is a unified API for text, structured objects, tool calls and agents. AI SDK UI is a set of framework-agnostic hooks for chat and generative interfaces. AI SDK Harnesses provides a uniform API for running established agent harnesses with HarnessAgent. Supported providers named on the docs page include Vercel AI Gateway, OpenAI, Anthropic, Google Generative AI, xAI Grok, Azure, Amazon Bedrock, Groq, Fal AI, DeepInfra, Google Vertex AI, Mistral, Together.ai, Cohere, Fireworks, DeepSeek, Cerebras, Perplexity, Luma AI and Baseten. Installation starts with npm install ai. Starter templates cover a chatbot, an internal knowledge base with RAG, multi-modal chat, semantic image search and natural language PostgreSQL queries. Frameworks shown include Next.js, Nuxt, SvelteKit and Solid. The full documentation is also available in Markdown at ai-sdk.dev/llms.txt for use with language models. Source code is hosted on GitHub.

Best for
Building chat and generative user interfacesGenerating text, structured objects and tool callsRunning agent harnessesSwitching between model providers