Now live: Research API streaming

The developer hub
for You.com

Search, Contents, and Research APIs designed to ground your AI in the open web. Docs, SDKs, a monthly challenge, and the showcase — all in one place.

Trusted by builders atLinearNotionCursorReplitGranola

The platform

Three APIs. One mental model.

Pick the right primitive for the job — or compose all three.

Browse the full docs
Real-time web grounding

Search API

Sub-second web results with snippets, links, and metadata. Built for RAG.

await you.search({
  query: "latest react 19 features",
  freshness: "week",
});
Quickstart
Full-page extraction

Contents API

Clean, parsed page contents from any URL. Markdown, structured, ready to embed.

await you.contents({
  urls: ["https://example.com/post"],
  format: "markdown",
});
Quickstart
Multi-step deep research

Research API

Autonomous research pipeline with streaming intermediate steps and citations.

for await (const step of you.research({
  prompt: "Compare RAG vs fine-tuning",
})) console.log(step);
Quickstart

SDKs

Official, typed, edge-ready.

$ npm i @youdotcom/sdk
$ pip install youdotcom

WebFinds · Live demo

Only the results that match your criteria.

Describe what you're looking for in plain English. WebFinds extracts a checklist of criteria from your query, searches the live web, verifies each result against that checklist, and pulls out the fields that matter — into a spreadsheet you can save, share, and export.

Pulls 25 results, judges each against your criteria with an LLM, and extracts the columns you ask for. Saves as a Set. ~5–10s.
Examples
Criteria:YC-backeddev tools categoryfounded after 2022has free tier
What are criteria?

Criteria are the binary checks each result must pass to be marked Verified. We auto-extract them from your query — edit, remove, or add your own.

Columns are extracted by the LLM from each result's title and snippet. Empty cells (n/a) mean the value couldn't be confidently determined.

Columns:FoundedPricing

Live playground

Try the Search API
in your browser.

Your API key never touches a third-party log — requests proxy through this origin and are forwarded to You.com directly.

response.json
// Run a query to see the response.
// Results stream in real-time.
April 2026 · Searchbuilders Challenge

Build a research agent for a niche you love

Use the Research API to build an autonomous agent that does deep research on a topic you care about — vintage synths, pro cycling, mycology, your call. Bonus points for surprising the judges.

Prize

$5,000 cash + featured Showcase spot

Deadline

0d0hremaining

Past winners

Mar 2026scholar-grepby Aditi R.
$5k
Feb 2026trendscoutby Lukas M.
$5k
Jan 2026papercrawlby Yuki T.
$5k

Submit your build

Open to anyone. Submissions reviewed weekly.

Events

Build with us, in person.

Integration clinics, meetups, and the occasional hack night.

Clinic
Apr 30, 6:21 AM

Integration Clinic: Search API Deep Dive

Live walkthrough of building production-grade Search API integrations. Bring your code, leave with answers.

Virtual (Zoom)
Meetup
May 7, 6:21 AM

Searchbuilders SF Meetup

In-person meetup with the You.com team and Bay Area developers building search-powered products.

San Francisco, CA
Office Hours
May 14, 6:21 AM

Research API Office Hours

Drop-in session to ask the engineering team anything about the Research API.

Virtual (Discord)
Hackathon
May 23, 6:21 AM

Hack Night: Build with You.com

4-hour virtual hack night. Prizes for the most creative API integration.

Virtual

Blog

From the engineers
who built it.

View all posts →
Apr 20, 2026·8 min read

Shipping the Research API: lessons from a year of multi-step retrieval

How we went from prototype to production with a multi-step research pipeline that handles 10M queries/day.

Sarah Chen, Staff Engineer

Apr 11, 2026·11 min read

Grounding LLMs with the Search API: a practical guide

A field guide to retrieval-augmented generation that actually works in production. Code samples in TS and Python.

Marcus Webb, DevRel

Apr 2, 2026·6 min read

Designing the Contents API: tradeoffs we made (and would make again)

Behind the scenes on the architectural choices that make Contents API fast, cheap, and predictable.

Priya Anand, Eng Manager

Status

All systems normal

Real-time uptime and incident reports.

  • Search APIOperational
  • Contents APIOperational
  • Research APIOperational
  • DashboardOperational

Changelog

Recent updates

Everything new across the platform.

v2.4.0
Apr 21

Streaming responses for Research API

You can now stream intermediate steps from the Research API for lower perceived latency.

v2.3.1
Apr 17

Increased Contents API rate limits

Default tier rate limits raised from 60 to 120 RPM. No action required.

v2.3.0
Apr 9

New 'freshness' parameter on Search API

Filter results by recency: hour, day, week, month, year.

v2.2.0
Mar 31

Python SDK 1.0 released

First stable release of the official Python SDK with async support and full type hints.

v2.1.0
Mar 19

TypeScript SDK now supports edge runtimes

Cloudflare Workers, Vercel Edge, and Deno are now first-class targets.