Quickstart

Two paths. Start with the first if a coding agent is writing the code; use the second if you are.

Path 1: hand it to your coding agent

Copy this prompt into Cursor, Claude Code, Codex, or whatever you use. It installs the Kernel CLI and skills, authenticates you, and opens a live browser session that you or your agent can drive.

Agent-readable surfaces

Surface	What it’s for
`kernel.sh/llms.txt`	Hand-written. What Kernel is, when to use it, every machine endpoint. Start here.
`kernel.sh/docs/llms.txt`	Index of every docs page, for fetching the ones a task needs.
`kernel.sh/docs/llms-full.txt`	The whole docs corpus in one file, for agents with room for it.
Agent Skills	Kernel know-how installed into the agent, so it doesn’t re-read docs every session.
MCP server	Kernel’s API as tools, for agents that call tools instead of writing code.
OpenAPI 3.1	For generating a client or calling the REST API directly.

Path 2: write it yourself

You’ll need an API key from the dashboard. Set it as KERNEL_API_KEY — every SDK, the CLI, and the MCP server read it from the environment.

Install an SDK

npm install @onkernel/sdk

pip install kernel

go get github.com/kernel/kernel-go-sdk

Create a browser and drive it

This creates a browser, runs Playwright code inside the browser’s VM, returns the result, and cleans up. No local Chromium, no CDP connection to manage.

import Kernel from '@onkernel/sdk';

const kernel = new Kernel();

const browser = await kernel.browsers.create({ timeout_seconds: 300 });
console.log('live view:', browser.browser_live_view_url);

try {
  const { result } = await kernel.browsers.playwright.execute(browser.session_id, {
    code: `
      await page.goto('https://news.ycombinator.com');
      return await page.$$eval('.titleline > a', (as) => as.slice(0, 5).map((a) => a.textContent));
    `,
  });
  console.log(result);
} finally {
  await kernel.browsers.deleteByID(browser.session_id);
}

from kernel import Kernel

kernel = Kernel()

browser = kernel.browsers.create(timeout_seconds=300)
print("live view:", browser.browser_live_view_url)

try:
    response = kernel.browsers.playwright.execute(
        browser.session_id,
        code="""
          await page.goto('https://news.ycombinator.com');
          return await page.$$eval('.titleline > a', (as) => as.slice(0, 5).map((a) => a.textContent));
        """,
    )
    print(response.result)
finally:
    kernel.browsers.delete_by_id(browser.session_id)

Open browser_live_view_url while it runs and you’ll watch the page load.

Pick your next decision

Two things determine the shape of everything after this: which control surface you use, and where your loop runs. How you drive the browser covers both.From there:

Getting blocked? Stealth and proxies.
Behind a login? Authentication.
Need to pay? Payments.
Worked examples: cookbooks.

Overview

Start building

How it works

Partnering with KERNEL

Path 1: hand it to your coding agent

Agent-readable surfaces

Path 2: write it yourself

​Path 1: hand it to your coding agent

​Agent-readable surfaces

​Path 2: write it yourself

Path 1: hand it to your coding agent

Agent-readable surfaces

Path 2: write it yourself