# vercel/ai

The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents

Repository: https://github.com/vercel/ai
Canonical: https://ross.abutalabs.com/products/ai
Homepage: https://ai-sdk.dev
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: artificial-intelligence, javascript, language-model, llm, openai, react, svelte, typescript, vercel, nextjs, vue, generative-ai, generative-ui, anthropic, gemini
Last push: 2026-08-27T00:13:18+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 85
- inputs: {"age_days": 1198, "days_push": 7, "days_rel": 7, "gap_med": 0.0, "n_releases_24m": 14675}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 26432, forks 5025 (observed 2026-08-28T04:11:46.941037+00:00)

## What it is
The AI SDK is a TypeScript toolkit from Vercel for building AI-powered applications and agents, providing a unified API for text generation, structured data, tool calling, and streaming across 100+ models from multiple providers. It includes framework-agnostic UI hooks for building chat and generative interfaces with React, Next.js, Vue, Svelte, and Node.js.

## Use cases
- build a chatbot with streaming responses in nextjs
- call openai anthropic and gemini models through one unified api
- build ai agents with tool calling in typescript
- generate structured data from llm responses
- add a chat interface to a react or vue app
- switch llm providers with one line of code
- integrate model context protocol mcp tools
- build generative ui components powered by llms

## When to choose
- you are building ai features in a typescript or javascript app
- you want provider-agnostic llm integration with streaming and fallbacks
- you need chat or generative ui hooks for react, next.js, vue, or svelte
- you are building agents with tool calling and workflow patterns

## When to avoid
- you work primarily in python and want a mature sdk (the python version is still in beta)
- you need direct low-level control over a single provider's api
- you are building a non-javascript application

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, agent-framework, rag, prompt-engineering, mcp, chatbot, sdk, streaming, web-framework
- domain: artificial-intelligence, large-language-models, chatbots, web-development, frontend, developer-tools
- platform: browser, cross-platform
- tags: ai-sdk, vercel, nextjs, react, vue, svelte, multi-provider, generative-ui, tool-calling, streaming, ai-agents, nodejs, typescript, web-server

## Member repositories
- vercel/ai (main) score 92

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:46.941037+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:55:52.373635+00:00, confidence not recorded.
  - readme: https://github.com/vercel/ai (fetched 2026-08-28T04:11:46.941037+00:00, sha 0f1402baf022)
  - homepage: https://ai-sdk.dev (fetched 2026-08-29T07:52:30.469279+00:00, sha 2f570e285a01)
  - site_page: https://ai-sdk.dev/docs (fetched 2026-08-29T07:52:30.472575+00:00, sha 6dcfa7274970)
- Data as of 2026-08-30T08:39:29.467469+00:00.