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
Quickstart for llms
Magnus Müller0c096a65e235
diff --git a/docs/docs.json b/docs/docs.jsonindex 176c13f50..695cf3e80 100644--- a/docs/docs.json+++ b/docs/docs.json@@ -43,12 +43,8 @@"customize/browser-settings","customize/real-browser","customize/output-format",- "customize/system-prompt","customize/sensitive-data",- "customize/custom-functions",- "customize/mcp-client",- "customize/mcp-server",- "customize/hooks"+ "customize/custom-functions"]},{@@ -56,6 +52,9 @@"pages": ["development/contribution-guide","development/local-setup",+ "customize/mcp-client",+ "customize/mcp-server",+ "customize/hooks","development/telemetry","development/observability","development/evaluations",diff --git a/docs/quickstart.mdx b/docs/quickstart.mdxindex 5e88e5d17..961a63833 100644--- a/docs/quickstart.mdx+++ b/docs/quickstart.mdx@@ -1,5 +1,5 @@----title: "Quickstart for human"+title: "Quickstart for humans"description: ""icon: "rocket"---diff --git a/docs/quickstart_llm.mdx b/docs/quickstart_llm.mdxindex 1621f3a43..d96d54cc8 100644--- a/docs/quickstart_llm.mdx+++ b/docs/quickstart_llm.mdx@@ -1,62 +1,14 @@----title: "Quickstart for LLM"+title: "Quickstart for LLMs"description: ""-icon: "rocket"+icon: "robot"---+<Info>+**Copy our entire documentation into your coding agent**+1. Click the [link](https://docs.browser-use.com/llms-full.txt)+2. Copy all content (~40k tokens)+3. Paste it to Cursor, Claude or ChatGPT+</Info>+**🔗 [Our docs for LLMs](https://docs.browser-use.com/llms-full.txt)**-## 1. Easy setup--Use [uv](https://docs.astral.sh/uv/) to create and activate the environment:--```bash-uv venv --python 3.12-```--```bash-# For Mac/Linux:-source .venv/bin/activate--# For Windows:-.venv\Scripts\activate-```--Install browser-use:--```bash-uv pip install browser-use-```--Install Chromium:--```bash-uvx playwright install chromium --with-deps-```--## 2. Choose your favorite LLM-Create a `.env` file and add your API key:--```bash .env-OPENAI_API_KEY=-```--See [Supported Models](/customize/supported-models) for other models.--## 3. Run your first agent--```python agent.py-from browser_use import Agent, ChatOpenAI-from dotenv import load_dotenv-import asyncio--load_dotenv()--async def main():- llm = ChatOpenAI(model="gpt-4.1-mini")- task = "Find the number 1 post on Show HN"- agent = Agent(task=task, llm=llm)- await agent.run()--if __name__ == "__main__":- asyncio.run(main())-```