[ 200 OK ] [ .JSON ] [ SCRAPE ] [ .MD ]

Power AI agents with clean web data

The context API to search, scrape, and interact with the web at scale. It's also open source.

Start for free

1,000 free credits / month. No card. Email team@pagelyte.xyz.

POST /scrape

Local demo — sample markdown. Production handles JS, proxies, and messy HTML.

Paste a URL. Pagelyte returns LLM-ready markdown, JSON, or screenshots.

Trusted by 150,000+ companies of all sizes

1.25M+developers

5B+requests served

176Kopen-source stars

400K+MCP installs

[ 01 / 06 ] · Main Features · // Developer First

Start searching today

The infrastructure layer that helps AI find, read, and act on the live web.

01 / Search

Search

Search the web and get full content from results — not blue links.

02 / Scrape

Scrape

Get llm-ready data from websites. Markdown, JSON, screenshot, and more.

03 / Interact

Interact NEW

Scrape a page, then interact with it using AI prompts or code.

04 / Map

Map

Discover URLs across a site before you crawl a single page.

05 / Crawl

Crawl

Extract content from entire websites, already cleaned for models.

06 / More

Monitor · Agent · Parse

Watch pages, run an agent, parse to a schema.

[ 02 / 06 ] · SDKs

Turn websites into LLM-ready markdown

from pagelyte import Pagelyte
app = Pagelyte(api_key="pgly-YOUR_KEY")
print(app.scrape("https://example.com"))

import Pagelyte from '@pagelyte/sdk'
const app = new Pagelyte({ apiKey: 'pgly-YOUR_KEY' })
console.log(await app.scrape('https://example.com'))

curl -X POST https://api.pagelyte.xyz/v2/scrape \
  -H "Authorization: Bearer $PAGELYTE_API_KEY" \
  -d '{"url":"https://example.com"}'

npx -y pagelyte-cli@latest scrape https://example.com

[ 03 / 06 ] · Agent Ready

Easily connect with your AI agents

Connect Pagelyte to any AI agent or MCP client in minutes. One command. Skills/CLI or MCP.

npx -y pagelyte-cli@latest init --all --browser

Are you an AI agent? Fetch this skill to get an API key and start building — email team@pagelyte.xyz.

[ 04 / 06 ] · Open source

Fast, reliable, token-efficient. And it's open source

We handle the hard stuff: JS rendering, proxies, and messy HTML so agents spend fewer tokens. Transform web data into AI-powered solutions.

See use cases → RAG chatbots, e-commerce intel, MCP in editors, and more.

pagelyte.scrape()

JS render · proxies · markdown · schema

2.5M+ weekly SDK downloads across npm and PyPI.

[ 05 / 06 ] · Testimonials

People love building with Pagelyte

If you're coding with AI, and haven't discovered Pagelyte yet, prepare to have your mind blown.

Started using Pagelyte for a project, I wish I used this sooner.

Moved our internal agent's web scraping tool because it benchmarked 50x faster.

[ 06 / 06 ] · FAQ

Frequently asked questions

What is Pagelyte?

Pagelyte is the context API to search, scrape, and interact with the web at scale. One API to turn websites into clean, LLM-ready data. Ideal for AI companies looking to empower their LLM applications with web context.

What can I build?

Teams use Pagelyte for deep research agents, RAG pipelines, lead enrichment, competitive intelligence, content generation, price monitoring, and more.

Search, Scrape, and Interact?

Search finds relevant information on the web. Scrape turns websites into clean, structured, AI-usable data. Interact handles click, navigate, or operate-a-page cases.

Agents and MCPs?

Yes. Official MCP so agents in Cursor, Claude, Windsurf, and other MCP-compatible tools can search, scrape, and interact. CLI and agent skills handle setup. Over 400,000 MCP servers have been installed.

Who uses Pagelyte?

Over 1.25M developers and 150,000+ companies, including teams at Apple, Canva, and Lovable. More than 5 billion requests.

Is it open-source?

Yes. Largest open source repo in the space with over 150K GitHub stars. SDKs see 2.5M+ weekly downloads across npm and PyPI.