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
Lint
Magnus Müllerfb24117363ab
diff --git a/browser_use/agent/system_prompt_flash.md b/browser_use/agent/system_prompt_flash.mdindex 54f37a0a7..699e79af9 100644--- a/browser_use/agent/system_prompt_flash.md+++ b/browser_use/agent/system_prompt_flash.md@@ -169,7 +169,7 @@ Be clear and concise in your decision-making. Exhibit the following reasoning pa<output>You must respond with a valid JSON in this exact format:{{- "memory": "Up to 5 sentences of specific reasoning about: Was the previous step successful / failed? What do we need to remeber from the current state for the task? Plan ahead what are the best next agtions. Whats the next immediate goal? Depending on the complexity think longer. For example if its opvious to click the start button just say: click start. But if you need to remeber more about the step it could be: Step succcessful, need to remember A, B, C to visit later. Next click on A.",+ "memory": "Up to 5 sentences of specific reasoning about: Was the previous step successful / failed? What do we need to remember from the current state for the task? Plan ahead what are the best next actions. What's the next immediate goal? Depending on the complexity think longer. For example if its opvious to click the start button just say: click start. But if you need to remember more about the step it could be: Step successful, need to remember A, B, C to visit later. Next click on A.","action":[{{"go_to_url": {{ "url": "url_value"}}}}]}}diff --git a/browser_use/tools/service.py b/browser_use/tools/service.pyindex 8734cc573..d3fb66ba8 100644--- a/browser_use/tools/service.py+++ b/browser_use/tools/service.py@@ -1058,6 +1058,7 @@ SHADOW DOM ACCESS EXAMPLE:return ActionResult(error=error_msg)# Custom done action for structured output+ @observe_debug(ignore_input=True, ignore_output=True, name='extract_clean_markdown')async def extract_clean_markdown(self, browser_session: BrowserSession, extract_links: bool = False) -> tuple[str, dict[str, Any]]: