Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
Python ai-agentsai-toolsbrowser-agentbrowser-automationbrowser-usecdpcloud-browsercomputer-useheadless-browserllmmcpplaywrightpythonremote-browserstealth-browserweb-automationweb-scraping
Add ChatBrowserUse as primary example across docs
Reagan Hsuface228acca5
diff --git a/docs/customize/agent/all-parameters.mdx b/docs/customize/agent/all-parameters.mdxindex bb0213f9e..e190c26be 100644--- a/docs/customize/agent/all-parameters.mdx+++ b/docs/customize/agent/all-parameters.mdx@@ -8,7 +8,7 @@ mode: "wide"## Available Parameters### Core Settings-- `tools`: Registry of [our tools](https://github.com/browser-use/browser-use/blob/main/browser_use/tools/service.py) the agent can call. [Example for custom tools](https://github.com/browser-use/browser-use/tree/main/examples/custom-functions)+- `tools`: Registry of <a href = "../tools/available">tools</a> the agent can call. <a href = "../tools/basics">Example</a>- `browser`: Browser object where you can specify the browser settings.- `output_model_schema`: Pydantic model class for structured output validation. [Example](https://github.com/browser-use/browser-use/blob/main/examples/features/custom_output.py)diff --git a/docs/customize/agent/basics.mdx b/docs/customize/agent/basics.mdxindex b0cafd5ec..40b3a6888 100644--- a/docs/customize/agent/basics.mdx+++ b/docs/customize/agent/basics.mdx@@ -7,11 +7,11 @@ mode: "wide"```python-from browser_use import Agent, ChatOpenAI+from browser_use import Agent, ChatBrowserUseagent = Agent(task="Search for latest news about AI",- llm=ChatOpenAI(model="gpt-4.1-mini"),+ llm=ChatBrowserUse(),)async def main():@@ -25,3 +25,5 @@ async def main():The agent is executed using the async `run()` method:- `max_steps` (default: `100`): Maximum number of steps an agent can take.++Check out all customizable parameters <a href = "/customize/agent/all-parameters"> here</a>.\ No newline at end of filediff --git a/docs/customize/agent/supported-models.mdx b/docs/customize/agent/supported-models.mdxindex c20a8aeaa..61b84fbcb 100644--- a/docs/customize/agent/supported-models.mdx+++ b/docs/customize/agent/supported-models.mdx@@ -1,7 +1,7 @@---title: "Supported Models"description: "Choose your favorite LLM"-icon: "robot"+icon: "microchip-ai"---@@ -9,12 +9,38 @@ icon: "robot"- Best accuracy: `O3`- Fastest: `llama4` on groq-- Balanced: fast + cheap + clever: `gemini-flash-latest` or `gpt-4.1-mini`+- Balanced: fast + cheap + clever: `BU 1.0`+`BU 1.0` is our in-house model trained on millions of browser automation tasks, matching the accuracy of top models while completing tasks **3-5x** faster. [See our blog post→](https://browser-use.com/posts/speed-matters)++### Browser Use [example](https://github.com/browser-use/browser-use/blob/main/examples/models/browser_use_llm.py)++Fastest and smartest option, optimized specifically for browser automation.++```python+from browser_use import Agent, ChatBrowserUse++# Initialize the model+llm = ChatBrowserUse()++# Create agent with the model+agent = Agent(+ task="...", # Your task here+ llm=llm+)+```++Required environment variables:++```bash .env+BROWSER_USE_API_KEY=+```++Get your API key from the [Browser Use Cloud](https://cloud.browser-use.com/dashboard/api). New signups get \$10 free credit via OAuth or \$1 via email.### OpenAI [example](https://github.com/browser-use/browser-use/blob/main/examples/models/gpt-4.1.py)-`O3` model is recommended for best performance.+`O3` model is recommended for best accuracy.```pythonfrom browser_use import Agent, ChatOpenAI@@ -94,7 +120,9 @@ AZURE_OPENAI_API_KEY=### Gemini [example](https://github.com/browser-use/browser-use/blob/main/examples/models/gemini.py)-> [!IMPORTANT] `GEMINI_API_KEY` was the old environment var name, it should be called `GOOGLE_API_KEY` as of 2025-05.+<Warning>+`GEMINI_API_KEY` is deprecated and should be named `GOOGLE_API_KEY` as of 2025-05.+</Warning>```pythonfrom browser_use import Agent, ChatGooglediff --git a/docs/docs.json b/docs/docs.jsonindex 1609431d5..91349591a 100644--- a/docs/docs.json+++ b/docs/docs.json@@ -141,13 +141,13 @@{"group": "Customize","pages": [+ "customize/agent/supported-models",{"group": "Agent","icon": "robot","isDefaultOpen": true,"pages": ["customize/agent/basics",- "customize/agent/supported-models","customize/agent/prompting-guide","customize/agent/output-format","customize/agent/all-parameters"diff --git a/docs/quickstart.mdx b/docs/quickstart.mdxindex 3e836b03d..2a1108307 100644--- a/docs/quickstart.mdx+++ b/docs/quickstart.mdx@@ -65,9 +65,15 @@ echo. > .env</Tabs><Tabs>+<Tab title="Browser Use Cloud">+```bash add your key to .env file+BROWSER_USE_API_KEY=+```+Get your API key from [Browser Use Cloud](https://cloud.browser-use.com/dashboard/api).+</Tab><Tab title="Google">```bash add your key to .env file-GEMINI_API_KEY=+GOOGLE_API_KEY=```</Tab><Tab title="OpenAI">@@ -82,11 +88,29 @@ ANTHROPIC_API_KEY=</Tab></Tabs>-See [Supported Models](/customize/supported-models) for more.+See [Supported Models](/customize/agent/supported-models) for more.## 3. Run your first agent<Tabs>+<Tab title="Browser Use">+```python agent.py+from browser_use import Agent, ChatBrowserUse+from dotenv import load_dotenv+import asyncio++load_dotenv()++async def main():+ llm = ChatBrowserUse()+ task = "Find the number 1 post on Show HN"+ agent = Agent(task=task, llm=llm)+ await agent.run()++if __name__ == "__main__":+ asyncio.run(main())+```+</Tab><Tab title="Google">```python agent.pyfrom browser_use import Agent, ChatGoogle