Introduction

The SDK wraps the API v4 Reference. Create a run, wait for it to finish, then read result.

from browser_use_sdk.v4 import AsyncBrowserUse

client = AsyncBrowserUse()
created = await client.runs.create("List the top 20 Hacker News posts and their points")
run = await client.runs.wait_for_completion(created.id)
print(run.result)

import { BrowserUse } from "browser-use-sdk/v4";

const client = new BrowserUse();
const created = await client.runs.create({
  task: "List the top 20 Hacker News posts and their points",
});
const run = await client.runs.waitForCompletion(created.id);
console.log(run.result);

curl -X POST https://api.browser-use.com/api/v4/runs \
  -H "X-Browser-Use-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"task": "List the top 20 Hacker News posts and their points"}'

runs.create() automatically creates a session and workspace. wait_for_completion() / waitForCompletion() polls the lightweight run status endpoint, then fetches the full run result once it reaches completed, failed, or cancelled. Use the agent for:

Data extraction and research across many pages
Form filling, downloads, and multi-step workflows
Authenticated work with browser profiles
Long-running tasks that create or consume files
Follow-up turns that preserve the same conversation, workspace, and live browser

See Follow-up tasks, Live messages, and Workspaces & files for the main V4 patterns.

Get Started

Pillars

More