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
Agent settings ready to ship
Magnus Müller3df6c8413f20
diff --git a/docs/customize/agent-output-format.mdx b/docs/customize/agent-output-format.mdxindex 8cbf663cf..391487d5d 100644--- a/docs/customize/agent-output-format.mdx+++ b/docs/customize/agent-output-format.mdx@@ -1,11 +1,11 @@---title: "Output Format"-description: "Understanding agent execution results and structured output"+description: ""icon: "arrow-right-to-bracket"mode: "wide"----## Output Format+## Agent HistoryThe `run()` method returns an `AgentHistoryList` object with the complete execution history:@@ -42,38 +42,4 @@ See all helper methods in the [AgentHistoryList source code](https://github.com/## Structured Output-For structured data extraction, use the `output_model_schema` parameter with a Pydantic model:--```python-from pydantic import BaseModel-from browser_use import Agent, ChatOpenAI--class Post(BaseModel):- post_title: str- post_url: str- num_comments: int- hours_since_post: int--class Posts(BaseModel):- posts: list[Post]--# Create agent with structured output-agent = Agent(- task="Go to hackernews show hn and give me the first 5 posts",- llm=ChatOpenAI(model="gpt-4.1-mini"),- output_model_schema=Posts-)--# Run and parse structured result-history = await agent.run()-result = history.final_result()--if result:- parsed: Posts = Posts.model_validate_json(result)- for post in parsed.posts:- print(f"Title: {post.post_title}")- print(f"URL: {post.post_url}")- print(f"Comments: {post.num_comments}")-```--For a complete structured output example, see the [custom_output.py example](https://github.com/browser-use/browser-use/blob/main/examples/features/custom_output.py).+For structured output, use the `output_model_schema` parameter with a Pydantic model. [Example](https://github.com/browser-use/browser-use/blob/main/examples/features/custom_output.py).diff --git a/docs/customize/agent-parameters.mdx b/docs/customize/agent-parameters.mdxindex 1eaed7c77..ec8015023 100644--- a/docs/customize/agent-parameters.mdx+++ b/docs/customize/agent-parameters.mdx@@ -8,9 +8,10 @@ mode: "wide"## Available Parameters### Core Settings-- `controller`: Registry of tools the agent can call. Defaults to base Controller. [Example for custom tools](https://github.com/browser-use/browser-use/tree/main/examples/custom-functions)+- `controller`: Registry of [our tools](https://github.com/browser-use/browser-use/blob/main/browser_use/controller/service.py+) the agent can call. [Example for custom tools](https://github.com/browser-use/browser-use/tree/main/examples/custom-functions)- `browser_session`: BrowserSession object where you can specify the browser settings.-- `output_model_schema`: Pydantic model class for structured output validation. [Full example](https://github.com/browser-use/browser-use/blob/main/examples/features/custom_output.py)+- `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)### Vision & Processing- `use_vision` (default: `True`): Enable/disable vision capabilities for processing screenshots@@ -18,21 +19,21 @@ mode: "wide"- `page_extraction_llm`: Separate LLM model for page content extraction. You can choose a small & fast model because it only needs to extract text from the page (default: same as `llm`)### Actions & Behavior-- `initial_actions`: List of actions to run before the main task without LLM. [Full example](https://github.com/browser-use/browser-use/blob/main/examples/features/initial_actions.py)+- `initial_actions`: List of actions to run before the main task without LLM. [Example](https://github.com/browser-use/browser-use/blob/main/examples/features/initial_actions.py)- `max_actions_per_step` (default: `10`): Maximum actions per step, e.g. for form filling the agent can output 10 fields at once. We execute the actions until the page changes.- `max_failures` (default: `3`): Maximum retries for steps with errors- `use_thinking` (default: `True`): Controls whether the agent uses its internal "thinking" field for explicit reasoning steps.-- `flash_mode` (default: `False`): Fast mode that skips evaluation, next goal and thinking and only uses memory. If `flash_mode` is enabled, it overrides `use_thinking` and disables the thinking process entirely. [Full example](https://github.com/browser-use/browser-use/blob/main/examples/getting_started/05_fast_agent.py)+- `flash_mode` (default: `False`): Fast mode that skips evaluation, next goal and thinking and only uses memory. If `flash_mode` is enabled, it overrides `use_thinking` and disables the thinking process entirely. [Example](https://github.com/browser-use/browser-use/blob/main/examples/getting_started/05_fast_agent.py)### System Messages- `override_system_message`: Completely replace the default system prompt.-- `extend_system_message`: Add additional instructions to the default system prompt. [Full example](https://github.com/browser-use/browser-use/blob/main/examples/features/custom_system_prompt.py)+- `extend_system_message`: Add additional instructions to the default system prompt. [Example](https://github.com/browser-use/browser-use/blob/main/examples/features/custom_system_prompt.py)### File & Data Management- `save_conversation_path`: Path to save complete conversation history- `save_conversation_path_encoding` (default: `'utf-8'`): Encoding for saved conversations- `available_file_paths`: List of file paths the agent can access-- `sensitive_data`: Dictionary of sensitive data to handle carefully. [Full example](https://github.com/browser-use/browser-use/blob/main/examples/features/sensitive_data.py)+- `sensitive_data`: Dictionary of sensitive data to handle carefully. [Example](https://github.com/browser-use/browser-use/blob/main/examples/features/sensitive_data.py)### Visual Output- `generate_gif` (default: `False`): Generate GIF of agent actions. Set to `True` or string pathdiff --git a/docs/customize/supported-models.mdx b/docs/customize/supported-models.mdxindex 0c13dd48d..88a7b0d40 100644--- a/docs/customize/supported-models.mdx+++ b/docs/customize/supported-models.mdx@@ -2,7 +2,7 @@title: "Supported Models"description: "Choose your favorite LLM"icon: "robot"-mode: "wide"+---### Recommendations@@ -12,7 +12,7 @@ mode: "wide"- Balanced: fast + cheap + clever: `gemini-2.5-flash` or `gpt-4.1-mini`-### OpenAI+### OpenAI [example](https://github.com/browser-use/browser-use/blob/main/examples/models/gpt-4.1.py)`O3` model is recommended for best performance.@@ -43,7 +43,7 @@ OPENAI_API_KEY=into the normal OpenAI API call).</Info>-### Anthropic+### Anthropic [example](https://github.com/browser-use/browser-use/blob/main/examples/models/claude-4-sonnet.py)```pythonfrom browser_use import Agent, ChatAnthropic@@ -66,7 +66,7 @@ And add the variable:ANTHROPIC_API_KEY=```-### Azure OpenAI+### Azure OpenAI [example](https://github.com/browser-use/browser-use/blob/main/examples/models/azure_openai.py)```pythonfrom browser_use import Agent, ChatAzureOpenAI@@ -92,7 +92,7 @@ AZURE_OPENAI_ENDPOINT=https://your-endpoint.openai.azure.com/AZURE_OPENAI_API_KEY=```-### Gemini+### 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.@@ -119,7 +119,7 @@ Required environment variables:GOOGLE_API_KEY=```-### AWS Bedrock+### AWS Bedrock [example](https://github.com/browser-use/browser-use/blob/main/examples/models/aws.py)AWS Bedrock provides access to multiple model providers through a single API. We support both a general AWS Bedrock client and provider-specific convenience classes.@@ -177,7 +177,7 @@ You can also use AWS profiles or IAM roles instead of environment variables. The- Session tokens for temporary credentials- AWS SSO authentication (`aws_sso_auth=True`)-## Groq+## Groq [example](https://github.com/browser-use/browser-use/blob/main/examples/models/llama4-groq.py)```pythonfrom browser_use import Agent, ChatGroq@@ -212,3 +212,8 @@ llm = ChatOllama(model="llama3.1:8b")We support all other models that can be called via OpenAI compatible API. We are open to PRs for more providers.+**Examples available:**+- [DeepSeek](https://github.com/browser-use/browser-use/blob/main/examples/models/deepseek-chat.py)+- [Novita](https://github.com/browser-use/browser-use/blob/main/examples/models/novita.py)+- [OpenRouter](https://github.com/browser-use/browser-use/blob/main/examples/models/openrouter.py)+