Browser use

pip install "langchain-stagehand @ git+https://github.com/langchain-ai/langchain-browserbase.git@40d1ae1d5e0543fe1e49b13d0887df40acf1c4c8" deepagents langchain-openai

export OPENAI_API_KEY="your-openai-api-key"
export BROWSERBASE_API_KEY="your-browserbase-api-key"

import asyncio
import os

from deepagents import create_deep_agent
from langchain_stagehand import StagehandMiddleware
from stagehand import Stagehand, browserbase


async def main():
    browser = await browserbase.launch(api_key=os.environ["BROWSERBASE_API_KEY"])
    try:
        stagehand = await Stagehand.create(browser=browser)
        agent = create_deep_agent(
            model="openai:gpt-5.5-2026-04-23",
            middleware=[StagehandMiddleware(stagehand=stagehand)],
        )
        result = await agent.ainvoke({
            "messages": [{
                "role": "user",
                "content": (
                    "On opentable.com, find a table for two in San Francisco this Friday "
                    "at 7 PM. Stop before confirming, and report the restaurant, time, and booking link."
                ),
            }]
        })
        print(result["messages"][-1].content_blocks)
    finally:
        await browser.close()


asyncio.run(main())

npm install -g agent-browser@latest
agent-browser install --with-deps

export LANGSMITH_API_KEY="your-langsmith-api-key"
export OPENAI_API_KEY="your-openai-api-key"
export QA_SNAPSHOT_ID="your-prepared-snapshot-id"
export QA_START_COMMAND="cd /app && npm run dev -- --host 0.0.0.0 --port 3000"

pip install deepagents langsmith langchain-openai

import os
from pathlib import Path

from deepagents import create_deep_agent
from deepagents.backends.langsmith import LangSmithSandbox
from langsmith.sandbox import SandboxClient

client = SandboxClient()
sandbox = client.create_sandbox(snapshot_id=os.environ["QA_SNAPSHOT_ID"])
backend = LangSmithSandbox(sandbox=sandbox)

try:
    app = sandbox.run(os.environ["QA_START_COMMAND"], wait=False, timeout=0, idle_timeout=-1)
    for command in [
        "curl --fail --retry 20 --retry-connrefused --retry-delay 1 "
        "--retry-max-time 30 http://127.0.0.1:3000",
        'agent-browser --session qa --args "--no-sandbox" '
        "open http://127.0.0.1:3000",
    ]:
        response = backend.execute(command)
        if response.exit_code != 0:
            raise RuntimeError(response.output)

    agent = create_deep_agent(
        model="openai:gpt-5.5-2026-04-23",
        backend=backend,
        system_prompt=(
            "Test the app through its UI using execute and agent-browser. "
            "Use agent-browser --session qa for every browser command. "
            "Use snapshot -i to inspect controls, then click or fill them. "
            "Take a new snapshot after page changes. Do not edit the app "
            "or alter its state by executing JavaScript. Save a screenshot "
            "to /tmp/qa.png before reporting observed results and failures."
        ),
    )
    result = agent.invoke({
        "messages": [{
            "role": "user",
            "content": "Sign up as qa@example.com and confirm that the dashboard loads.",
        }]
    })
    print(result["messages"][-1].content_blocks)
    image = backend.download_files(["/tmp/qa.png"])[0]
    if image.error:
        raise RuntimeError(image.error)
    Path("qa.png").write_bytes(image.content)
finally:
    client.delete_sandbox(sandbox.name)
    client.close()