#2020th of 24 in Agent frameworks and SDKs

ai

Provider-agnostic TypeScript toolkit for text, structured output, agents and chat UIs

Documentation ↗ Website ↗ Repository on GitHub ↗

Stars: 27.2k
License: custom license
Last commit: Oct 2026
Last release: Oct 2026
Language: TypeScript

Missed the latest GitHub check; these facts may be older.

Vercel is hiring: 90 open roles

Overview

The AI SDK is a TypeScript library with one API for generating text and structured data across model providers such as OpenAI, Anthropic and Google. It includes a ToolLoopAgent for tool-calling agents and UI hooks (useChat) for React, Svelte, Vue and Angular. Model strings route through the Vercel AI Gateway by default, or you can install per-provider @ai-sdk packages.

Who it is for: TypeScript developers building LLM apps, agents and chat UIs

Strengths

Single generateText API across OpenAI, Anthropic, Google and other providers
Typed structured output via Output.object with Zod schemas
UI hooks for React, Svelte, Vue and Angular, with Next.js route helpers
Direct provider packages available, so the Vercel gateway is optional

Weaknesses

TypeScript and JavaScript only; requires Node.js 22+
Default model-string path goes through the Vercel AI Gateway, a hosted service
Library only: no hosted UI, no model serving, no local inference of its own
License is not stated in the README; detection reports NOASSERTION

What it needs

no GPU
Needs Node.js 22+, Vercel AI Gateway or provider API keys
Models: OpenAI, Anthropic, Google

Also in Agent frameworks and SDKs

See all 24

Also in Agent frameworks and SDKs
Rank	Project	Score
1	ppt-masterAgent skill that turns documents into natively editable PowerPoint decks Live demo ↗ (opens in a new tab)62.1k starsMIT	91 out of 100
2	langchainPython framework for building LLM agents and apps from interoperable components147.8k starsMIT	88 out of 100
3	browser-usePython library that lets an LLM agent control a web browser Live demo ↗ (opens in a new tab)118k starsMIT	88 out of 100
#4	tradingagentsLangGraph multi-agent framework simulating a trading firm to analyze tickers Live demo ↗ (opens in a new tab)111.2k starsApache-2.0	87 out of 100
#5	crewaiPython framework for multi-agent workflows with role-based Crews and event-driven Flows59.7k starsMIT	81 out of 100

How to choose

Pick by language first (Python or TypeScript), then by how much the framework hides.
Check how it handles tool errors and retries; that is where agents break in production.
Look for tracing hooks so you can see each step later.

Health

Releases: Not checked
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

custom license Custom terms

Use it at work: Check
Change it and rebrand it: Check
Sell it or host it for others: Check

Your part: GitHub could not match these terms to a standard license. Read the license before you use it at work, rebrand it or host it for others.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#20 of 24 in Agent frameworks and SDKs on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/vercel/ai.svg)](https://archestack.com/best-of-ai/projects/ai/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-ai/ai/" title="ai on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Open-Source AI on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with ai filled in.