File I/O - Kernel

Downloads

Kernel browsers run in fully sandboxed environments with writable filesystems. When your automation downloads a file, it’s saved inside the browser’s filesystem and can be retrieved using Kernel’s File I/O APIs.

Files can only be retrieved while the browser session is still active. Once the browser session is destroyed or times out, all files from that session are permanently deleted and no longer accessible.

Playwright

Playwright performs downloads via the browser itself, so there are a few steps:

Create a browser session
Configure browser download behavior using CDP
Perform the download
Retrieve the file from the browser’s filesystem

With behavior: 'default', downloads are saved to the browser’s default download directory. The CDP downloadProgress event includes a filePath field when the download completes, which tells you exactly where the file was saved. Use this path with Kernel’s File I/O APIs to retrieve the file.

The CDP downloadProgress event signals when the browser finishes writing a file, but there may be a brief delay before the file becomes available through Kernel’s File I/O APIs. This is especially true for larger downloads. We recommend polling listFiles to confirm the file exists before attempting to read it.

import Kernel from '@onkernel/sdk';
import { chromium } from 'playwright';
import fs from 'fs';
import path from 'path';
import pTimeout from 'p-timeout';

const kernel = new Kernel();

// Poll listFiles until the expected file appears in the directory
async function waitForFile(
  sessionId: string,
  filePath: string,
  timeoutMs = 30_000
) {
  const dir = path.dirname(filePath);
  const filename = path.basename(filePath);
  const start = Date.now();
  while (Date.now() - start < timeoutMs) {
    const files = await kernel.browsers.fs.listFiles(sessionId, { path: dir });
    if (files.some((f) => f.name === filename)) {
      return;
    }
    await new Promise((r) => setTimeout(r, 500));
  }
  throw new Error(`File ${filePath} not found after ${timeoutMs}ms`);
}

async function main() {
  const kernelBrowser = await kernel.browsers.create();
  console.log('live view:', kernelBrowser.browser_live_view_url);

  const browser = await chromium.connectOverCDP(kernelBrowser.cdp_ws_url);
  const context = browser.contexts()[0] || (await browser.newContext());
  const page = context.pages()[0] || (await context.newPage());

  const client = await context.newCDPSession(page);
  await client.send('Browser.setDownloadBehavior', {
    behavior: 'default',
    eventsEnabled: true,
  });

  // Set up CDP listeners to capture download path and completion
  let downloadFilePath: string | undefined;
  let downloadState: string | undefined;
  let downloadCompletedResolve!: () => void;
  const downloadCompleted = new Promise<void>((resolve) => {
    downloadCompletedResolve = resolve;
  });

  client.on('Browser.downloadWillBegin', (event) => {
    console.log('Download started:', event.suggestedFilename);
  });

  client.on('Browser.downloadProgress', (event) => {
    if (event.state === 'completed' || event.state === 'canceled') {
      downloadState = event.state;
      downloadFilePath = event.filePath;
      downloadCompletedResolve();
    }
  });

  console.log('Navigating to download test page');
  await page.goto('https://browser-tests-alpha.vercel.app/api/download-test');
  await page.getByRole('link', { name: 'Download File' }).click();

  try {
    await pTimeout(downloadCompleted, {
      milliseconds: 10_000,
      message: new Error('Download timed out after 10 seconds'),
    });
    console.log('Download completed');
  } catch (err) {
    console.error(err);
    throw err;
  }

  if (downloadState === 'canceled') {
    throw new Error('Download was canceled');
  }

  if (!downloadFilePath) {
    throw new Error('Unable to determine download file path');
  }

  // Wait for the file to be available via Kernel's File I/O APIs
  console.log(`Waiting for file: ${downloadFilePath}`);
  await waitForFile(kernelBrowser.session_id, downloadFilePath);

  console.log(`Reading file: ${downloadFilePath}`);

  const resp = await kernel.browsers.fs.readFile(kernelBrowser.session_id, {
    path: downloadFilePath,
  });

  const bytes = await resp.bytes();
  fs.mkdirSync('downloads', { recursive: true });
  const localPath = `downloads/${path.basename(downloadFilePath)}`;
  fs.writeFileSync(localPath, bytes);
  console.log(`Saved to ${localPath}`);

  await kernel.browsers.deleteByID(kernelBrowser.session_id);
  console.log('Kernel browser deleted successfully.');
}

main();

import asyncio
import os
from pathlib import Path
import time
from kernel import Kernel
from playwright.async_api import async_playwright

kernel = Kernel()


# Poll list_files until the expected file appears in the directory
async def wait_for_file(
    session_id: str, file_path: str, timeout_sec: float = 30
):
    dir_path = str(Path(file_path).parent)
    filename = Path(file_path).name
    start = time.time()
    while time.time() - start < timeout_sec:
        files = kernel.browsers.fs.list_files(session_id, path=dir_path)
        if any(f.name == filename for f in files):
            return
        await asyncio.sleep(0.5)
    raise TimeoutError(f"File {file_path} not found after {timeout_sec}s")


async def main():
    kernel_browser = kernel.browsers.create()
    print("Kernel browser live view url:", kernel_browser.browser_live_view_url)

    async with async_playwright() as playwright:
        browser = await playwright.chromium.connect_over_cdp(kernel_browser.cdp_ws_url)
        context = browser.contexts[0]
        page = context.pages[0] if len(context.pages) > 0 else await context.new_page()

        cdp_session = await context.new_cdp_session(page)
        await cdp_session.send(
            "Browser.setDownloadBehavior",
            {
                "behavior": "default",
                "eventsEnabled": True,
            },
        )

        download_completed = asyncio.Event()
        download_file_path: str | None = None
        download_state: str | None = None

        def _on_download_begin(event):
            print(f"Download started: {event.get('suggestedFilename', 'unknown')}")

        def _on_download_progress(event):
            nonlocal download_state, download_file_path
            if event.get("state") in ["completed", "canceled"]:
                download_state = event.get("state")
                download_file_path = event.get("filePath")
                download_completed.set()

        cdp_session.on("Browser.downloadWillBegin", _on_download_begin)
        cdp_session.on("Browser.downloadProgress", _on_download_progress)

        print("Navigating to download test page")
        await page.goto("https://browser-tests-alpha.vercel.app/api/download-test")
        await page.get_by_role("link", name="Download File").click()

        try:
            await asyncio.wait_for(download_completed.wait(), timeout=10)
            print("Download completed")
        except asyncio.TimeoutError:
            print("Download timed out after 10 seconds")
            raise

        if download_state == "canceled":
            raise RuntimeError("Download was canceled")

        if not download_file_path:
            raise RuntimeError("Unable to determine download file path")

        # Wait for the file to be available via Kernel's File I/O APIs
        print(f"Waiting for file: {download_file_path}")
        await wait_for_file(kernel_browser.session_id, download_file_path)

        resp = kernel.browsers.fs.read_file(
            kernel_browser.session_id, path=download_file_path
        )
        local_path = f"./downloads/{Path(download_file_path).name}"
        os.makedirs("./downloads", exist_ok=True)
        resp.write_to_file(local_path)
        print(f"Saved to {local_path}")

        kernel.browsers.delete_by_id(kernel_browser.session_id)
        print("Kernel browser deleted successfully.")


if __name__ == "__main__":
    asyncio.run(main())

We recommend using the list files API to poll for file availability before calling read file, as shown in the examples above. This approach ensures reliable downloads, especially for larger files. You can also use listFiles to enumerate and save all downloads at the end of a session.

Stagehand v3

When using Stagehand with Kernel browsers, you need to configure the download behavior in the localBrowserLaunchOptions:

const stagehand = new Stagehand({
  env: "LOCAL",
  verbose: 1,
  localBrowserLaunchOptions: {
    cdpUrl: kernelBrowser.cdp_ws_url,
    downloadsPath: DOWNLOAD_DIR, // Specify where downloads should be saved
    acceptDownloads: true, // Enable downloads
  },
});

Here’s a complete example:

import { Stagehand } from "@browserbasehq/stagehand";
import Kernel from "@onkernel/sdk";
import fs from "fs";

const DOWNLOAD_DIR = "/tmp/downloads";

// Poll listFiles until any file appears in the directory
async function waitForFile(
    kernel: Kernel,
    sessionId: string,
    dir: string,
    timeoutMs = 30_000
) {
    const start = Date.now();
    while (Date.now() - start < timeoutMs) {
        const files = await kernel.browsers.fs.listFiles(sessionId, { path: dir });
        if (files.length > 0) {
            return files[0];
        }
        await new Promise((r) => setTimeout(r, 500));
    }
    throw new Error(`No files found in ${dir} after ${timeoutMs}ms`);
}

async function main() {
    const kernel = new Kernel();

    console.log("Creating browser via Kernel...");
    const kernelBrowser = await kernel.browsers.create({
        stealth: true,
    });

    console.log(`Kernel Browser Session Started`);
    console.log(`Session ID: ${kernelBrowser.session_id}`);
    console.log(`Watch live: ${kernelBrowser.browser_live_view_url}`);

    // Initialize Stagehand with Kernel's CDP URL and download configuration
    const stagehand = new Stagehand({
        env: "LOCAL",
        verbose: 1,
        localBrowserLaunchOptions: {
            cdpUrl: kernelBrowser.cdp_ws_url,
            downloadsPath: DOWNLOAD_DIR,
            acceptDownloads: true,
        },
    });

    await stagehand.init();

    const page = stagehand.context.pages()[0];

    await page.goto("https://browser-tests-alpha.vercel.app/api/download-test");

    // Use Stagehand to click the download button
    await stagehand.act("Click the download file link");
    console.log("Download triggered");

    // Wait for the file to be fully available via Kernel's File I/O APIs
    console.log("Waiting for file to appear...");
    const downloadedFile = await waitForFile(
        kernel,
        kernelBrowser.session_id,
        DOWNLOAD_DIR
    );
    console.log(`File found: ${downloadedFile.name}`);

    const remotePath = `${DOWNLOAD_DIR}/${downloadedFile.name}`;
    console.log(`Reading file from: ${remotePath}`);

    // Read the file from Kernel browser's filesystem
    const resp = await kernel.browsers.fs.readFile(kernelBrowser.session_id, {
        path: remotePath,
    });

    // Save to local filesystem
    const bytes = await resp.bytes();
    fs.mkdirSync("downloads", { recursive: true });
    const localPath = `downloads/${downloadedFile.name}`;
    fs.writeFileSync(localPath, bytes);
    console.log(`Saved to ${localPath}`);

    // Clean up
    await stagehand.close();
    await kernel.browsers.deleteByID(kernelBrowser.session_id);
    console.log("Browser session closed");
}

main().catch((err) => {
    console.error(err);
    process.exit(1);
});

Browser Use

Browser Use handles downloads automatically when configured properly. Documentation for Browser Use downloads coming soon.

Uploads

Playwright’s setInputFiles() method allows you to upload files directly to file input elements. You can fetch a file from a URL and pass the buffer directly to setInputFiles().

import Kernel from '@onkernel/sdk';
import { chromium } from 'playwright';

const IMAGE_URL = 'https://www.kernel.sh/brand_assets/Kernel-Logo_Accent.png';
const kernel = new Kernel();

async function main() {
    // Create Kernel browser session
    const kernelBrowser = await kernel.browsers.create();
    console.log('Live view:', kernelBrowser.browser_live_view_url);

    // Connect Playwright
    const browser = await chromium.connectOverCDP(kernelBrowser.cdp_ws_url);
    const context = browser.contexts()[0] || (await browser.newContext());
    const page = context.pages()[0] || (await context.newPage());

    // Navigate to a page with a file input
    await page.goto('https://browser-tests-alpha.vercel.app/api/upload-test');

    // Fetch file and pass buffer directly to setInputFiles
    const response = await fetch(IMAGE_URL);
    const buffer = Buffer.from(await response.arrayBuffer());

    await page.locator('input[type="file"]').setInputFiles([{
        name: 'Kernel-Logo_Accent.png',
        mimeType: 'image/png',
        buffer: buffer,
    }]);
    console.log('File uploaded');

    await kernel.browsers.deleteByID(kernelBrowser.session_id);
    console.log('Browser deleted');
}

main();

import asyncio
import httpx
from kernel import Kernel
from playwright.async_api import async_playwright

IMAGE_URL = 'https://www.kernel.sh/brand_assets/Kernel-Logo_Accent.png'
kernel = Kernel()


async def main():
    # Create Kernel browser session
    kernel_browser = kernel.browsers.create()
    print(f'Live view: {kernel_browser.browser_live_view_url}')

    async with async_playwright() as playwright:
        # Connect Playwright
        browser = await playwright.chromium.connect_over_cdp(kernel_browser.cdp_ws_url)
        context = browser.contexts[0] if browser.contexts else await browser.new_context()
        page = context.pages[0] if context.pages else await context.new_page()

        # Navigate to a page with a file input
        await page.goto('https://browser-tests-alpha.vercel.app/api/upload-test')

        # Fetch file and pass buffer directly to set_input_files
        async with httpx.AsyncClient() as client:
            response = await client.get(IMAGE_URL)
            buffer = response.content

        await page.locator('input[type="file"]').set_input_files([{
            'name': 'Kernel-Logo_Accent.png',
            'mimeType': 'image/png',
            'buffer': buffer,
        }])
        print('File uploaded')

        await browser.close()

    kernel.browsers.delete_by_id(kernel_browser.session_id)
    print('Browser deleted')


if __name__ == '__main__':
    asyncio.run(main())

​Downloads

​Playwright

​Stagehand v3

​Browser Use

​Uploads

Downloads

Playwright

Stagehand v3

Browser Use

Uploads