BU Agent API

BU Agent API (v3) — a next-generation AI browser agent for web scraping, data extraction, file manipulation, and multi-step workflows in a single API call.

What is it?

A completely new agent built from scratch. Think Claude Code for the browser: web scraping, data extraction, file manipulation, and complex multi-step workflows.

Example: “Here’s a CSV with 50 people. For each person, find their LinkedIn profile, extract their current title and company, and return an enriched CSV.”

The BU Agent handles the entire pipeline in a single task.

Quick start

Same package, different import path:

Python

import asyncio
from browser_use_sdk.v3 import AsyncBrowserUse

async def main():
    client = AsyncBrowserUse()
    result = await client.run("Find the top 3 trending repos on GitHub today")
    print(result.output)

asyncio.run(main())

import { BrowserUse } from "browser-use-sdk/v3";

const client = new BrowserUse();
const result = await client.run("Find the top 3 trending repos on GitHub today");
console.log(result.output);

Structured output

Python

from browser_use_sdk.v3 import AsyncBrowserUse
from pydantic import BaseModel

class Contact(BaseModel):
    name: str
    title: str
    company: str

client = AsyncBrowserUse()
result = await client.run(
    "Find the founding team of Browser Use on LinkedIn",
    output_schema=Contact,
)
print(result.output)

import { BrowserUse } from "browser-use-sdk/v3";
import { z } from "zod";

const Contact = z.object({
  name: z.string(),
  title: z.string(),
  company: z.string(),
});

const client = new BrowserUse();
const result = await client.run(
  "Find the founding team of Browser Use on LinkedIn",
  { schema: Contact },
);
console.log(result.output);

Workspaces

Workspaces are persistent file storage that lives across sessions. Attach a workspace to a task and the agent can read and write files in it.

Python

workspace = await client.workspaces.create(name="my-workspace")
result = await client.run("Save results to output.csv", workspace_id=str(workspace.id))

files = await client.workspaces.files(str(workspace.id))
for f in files.files:
    print(f.path, f.size)

const workspace = await client.workspaces.create({ name: "my-workspace" });
const result = await client.run("Save results to output.csv", { workspaceId: workspace.id });

const files = await client.workspaces.files(workspace.id);
for (const f of files.files) {
  console.log(f.path, f.size);
}

See the full Workspaces guide for CRUD, file management, and more.

Session messages

Retrieve the full message history for a session — useful for debugging or building custom UIs.

Python

msgs = await client.sessions.messages(session_id, limit=50)
for m in msgs.messages:
    print(f"[{m.role}] {m.data[:200]}")

const msgs = await client.sessions.messages(sessionId, { limit: 50 });
for (const m of msgs.messages) {
  console.log(`[${m.role}] ${m.data.slice(0, 200)}`);
}

Use after and before cursors for pagination through large message histories.

BU Agent API Reference

Full endpoint reference.

Workspaces Guide

Persistent file storage across sessions.

Agent Tasks

Task guide.

The BU Agent API interface may change.