| title | wrangle the wild web |
|---|---|
| sidebarTitle | Introduction |
| description | |
| mode | wide |
We build crazy fast, open source infra for AI agents to access the internet. Trusted by Cash App, Framer, and 3,000+ teams.
We spin up cloud browsers in <30ms with GPU acceleration when needed. We manage auth for your agents so you don't have to. We solve CAPTCHAs and manage residential proxies to help you see fewer of them. You can view sessions live and record them as MP4s for debugging. Spin up a browser and pick the shape — headless, stealth, GPU, profiles. Drive it with computer use, playwright execution, CDP, or WebDriver BiDi. Watch it live, record replays, and capture screenshots.import { CopyPromptButton } from '/snippets/copy-prompt-button.jsx';
copy and paste this into your AI coding agent (Cursor, Claude, Windsurf, etc.). it installs the Kernel CLI and skills, authenticates you, and opens a live browser session that you or your agent can interact with.
Our app platform is a serverless compute service for running agent loops triggered on demand or by scheduled events without having to provision or manage sandboxes. Your agent runs co-located with its browser to minimize network latency.
Scaffold a project from a template:
kernel create --template computer-useDeploy and invoke it on demand:
kernel deploy agent.ts
kernel invoke my-agent my-task --payload '{"url": "https://example.com"}'browser pools are how you take a working automation to production: they keep browsers warm and pre-configured so you skip start-up latency on every task, and idle browsers in a pool aren't billed. once you know how to create and drive a browser, browser pools are worth evaluating for almost any production workload.