NEVER TRAINED ON · PRIVATE BY DEFAULT · BUILT BY MOZILLA

GITHUB

Integration vercel-ai-sdk

Give Vercel AI SDK the web without giving up your privacy.

Cited answers, clean Markdown, matching JSON, and browser tasks for the Vercel AI SDK, as drop-in AI SDK tools.

@tabstack/ai

"which runtimes shipped web search?"

ollama.com/blog

docs.openwebui.com

 

ANSWER

Two runtimes shipped it.

ollama.com/blogdocs.openwebui.com2 cited

Why Vercel AI SDK

Tabstack, inside Vercel AI SDK.

@tabstack/ai adds Tabstack to the Vercel AI SDK as typed tool() definitions. Pass them to generateText or streamText and your app gets cited research, clean page content, matching JSON, and browser tasks.

one question

post /research

query: "which runtimes…"
mode: "balanced"
one cited answer

First call

Start with a current question.

Vercel AI SDK makes the call, and Tabstack handles the web. Research searches live sources, reads the pages, and returns a cited answer, so your agent gets the findings without running every search itself.

app.tsTypeScript
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";
import { tabstackTools } from "@tabstack/ai";

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools: tabstackTools,
  stopWhen: stepCountIs(5),
  prompt: "What are Vercel's pricing plans and how do they compare?",
});

console.log(text);

Tools

Five tools, one key.

tabstackTools is keyed by tool name. Pass all five, or pick the ones a call should reach.

ToolReturns
research_questionA cited answer from multiple live sources
extract_page_contentA page as clean Markdown
extract_structured_dataJSON matching a schema you define
generate_structured_dataA page transformed into the JSON you describe
automate_browser_taskA completed browser task, from plain-language steps

START FREE

Install it where you already build.

Start with 10,000 free credits. No credit card required.

curl -fsSL https://tabstack.ai/install.sh | sh