Claude, OpenAI and Gemini

Three ways to combine browser-use with Anthropic, OpenAI and Google:

You want	Use
browser-use’s agent, running on Claude, GPT or Gemini	Their models
Claude Code, Claude Desktop, Codex or Cursor to drive a browser	The CLI skill or the MCP server
Your own Claude or OpenAI agent to delegate browser work	A browse tool

Use Claude, GPT or Gemini as the model

Pass the provider’s model class. Each reads its own API key from the environment. Anthropic and Google are built in; no extra install.

from browser_use import Agent, ChatAnthropic

agent = Agent('What is the title of https://example.com?', llm=ChatAnthropic('claude-sonnet-5-5'))  # ANTHROPIC_API_KEY
print(agent.run_sync().final_result())

from browser_use import Agent, ChatOpenAI

agent = Agent('What is the title of https://example.com?', llm=ChatOpenAI('gpt-6-luna'))  # OPENAI_API_KEY
print(agent.run_sync().final_result())

from browser_use import Agent, ChatGoogle

agent = Agent('What is the title of https://example.com?', llm=ChatGoogle('gemini-3.5-flash'))  # GOOGLE_API_KEY
print(agent.run_sync().final_result())

Claude on Bedrock, GPT on Azure and Gemini on Vertex work through Pydantic AI model strings, such as llm='bedrock:<model id>' or llm='azure:<deployment>'. Options, reasoning effort and cost: Models.

Give your coding agent a browser

The coding agent writes the browser code itself, against your Chrome or a cloud browser. There are two ways in; both use the same helpers.

Claude Code

The CLI with its skill is the most direct:

uv tool install 'browser-use==1.0.0'
browser-use skill install

skill install writes the skill for every agent it finds: Claude Code, Codex, Copilot, Cursor, Gemini, OpenClaw and OpenCode. See Browser Use CLI. Or add the MCP server:

claude mcp add browser-use -- uvx --from 'browser-use==1.0.0' browser-use --cli-mcp

Claude Desktop and Cursor

Add the MCP server to claude_desktop_config.json (Claude Desktop: Settings > Developer > Edit Config) or to .cursor/mcp.json:

{
  "mcpServers": {
    "browser-use": {
      "command": "uvx",
      "args": ["--from", "browser-use==1.0.0", "browser-use", "--cli-mcp"]
    }
  }
}

Codex

browser-use skill install covers Codex too. For the MCP server, add this to ~/.codex/config.toml:

[mcp_servers.browser-use]
command = "uvx"
args = ["--from", "browser-use==1.0.0", "browser-use", "--cli-mcp"]

The server gives the client three tools: browser_exec, browser_screenshot and browser_login. Local or cloud browser, and what the tools do: MCP server.

Call a browser agent from your own agent

Wrap a browser-use Agent in a tool. Your agent decides when it needs the web; browser-use does the browsing and returns the answer.

from pydantic_ai import Agent as PydanticAgent

from browser_use import Agent


async def browse(task: str) -> str:
    """Do a task in a real web browser and return what it found."""
    result = await Agent(task).run(max_steps=30)
    return result.final_result() or f'{result.status}: {result.error}'


assistant = PydanticAgent('anthropic:claude-sonnet-5-5', tools=[browse])
print(assistant.run_sync('What is the title of the top story on Hacker News right now?').output)

from agents import Agent as OpenAIAgent
from agents import Runner, function_tool

from browser_use import Agent


@function_tool
async def browse(task: str) -> str:
    """Do a task in a real web browser and return what it found."""
    result = await Agent(task).run(max_steps=30)
    return result.final_result() or f'{result.status}: {result.error}'


assistant = OpenAIAgent(name='assistant', model='gpt-6-luna', tools=[browse])
print(Runner.run_sync(assistant, 'What is the title of the top story on Hacker News right now?').final_output)

The OpenAI version needs uv add openai-agents. The same browse function works as a tool in the Anthropic SDK, LangGraph or any framework that calls Python functions. Each call starts a cloud browser and stops it when the inner run ends; to reuse one browser across calls that run one at a time, pass browser=Browser(keep_alive=True) and stop it yourself. To have Browser Use host the whole agent instead, use the Cloud API. Cloud guides: Claude Code, OpenAI.

0.x integrations

The 0.x Anthropic and OpenAI hosted-browser integrations (browser_use.integrations, including Browser Use toolsets for Claude) are not in 1.0. They come back on the new Browser in a later release. To use them now, stay on 0.x (uv add 'browser-use>=0.13.11,<1') and follow toolsets for Claude (0.x) or OpenAI (0.x).

Get Started

Core

Safety

Features

Integrations

Reference

Claude, OpenAI and Gemini

Use Claude, GPT or Gemini as the model

Give your coding agent a browser

Claude Code

Claude Desktop and Cursor

Codex

Call a browser agent from your own agent

0.x integrations

​Use Claude, GPT or Gemini as the model

​Give your coding agent a browser

​Claude Code

​Claude Desktop and Cursor

​Codex

​Call a browser agent from your own agent

​0.x integrations

Use Claude, GPT or Gemini as the model

Give your coding agent a browser

Claude Code

Claude Desktop and Cursor

Codex

Call a browser agent from your own agent

0.x integrations