Primitives

Your agent is only as good as its context

The Search and Fetch APIs let agents see and gather context on the web before acting on it.

Get started Read the docs

Web APIs built for agents, not humans.

Most agent tasks start with a question: where should I go, and what's there?

Search API

Most search APIs are designed around how people browse. Agents don't browse. They navigate, extract, and act, and every unnecessary hop costs tokens, time, and reliability.

Read the docs
Fetch API

Most tools return what a page looks like in theory. The Fetch API returns what's actually there. Pass a URL, choose your format, and get back clean, structured content your agent can use immediately.

Read the docs

Search, Fetch, and Browse.

An agent-optimized web experience

1. Search returns ranked URLs with titles and descriptions so your agent lands in the right place on the first try.

2. Fetch’s sync response design makes it trivial for LLMs to use. Request a page, get content back. No polling, no callbacks.

3. Browse: Once your agent knows where to go, it still has to get there and do something. Log in. Fill out a form. Download a file.

Integrated with our browser agent SDK: Stagehand

One API Key gives your agents access to the whole web.

Get started with Stagehand

                
                                    Typescript
                            
                        import { Stagehand } from "@browserbasehq/stagehand";

const stagehand = new Stagehand({
  env: "BROWSERBASE"
})

await stagehand.init();

const agent = stagehand.agent({
  model: "anthropic/claude-sonnet-4-6",
});

const page = stagehand.context.pages()[0];
await page.goto("https://browserbase.com");

const result = await agent.execute({
  instruction: "Find the latest pricing for Browserbase",
  useSearch: true,
  maxSteps: 20,
});