Skip to content

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

LLM docs

Magnus Müller68ed8f16500f
diff --git a/docs/docs.json b/docs/docs.json
index b6821ef73..176c13f50 100644
--- a/docs/docs.json
+++ b/docs/docs.json
@@ -31,7 +31,8 @@
"group": "Get Started",
"pages": [
"introduction",
- "quickstart"
+ "quickstart",
+ "quickstart_llm"
]
},
{
diff --git a/docs/quickstart.mdx b/docs/quickstart.mdx
index 6ce8139ce..5e88e5d17 100644
--- a/docs/quickstart.mdx
+++ b/docs/quickstart.mdx
@@ -1,5 +1,5 @@
---
-title: "Quickstart"
+title: "Quickstart for human"
description: ""
icon: "rocket"
---
diff --git a/docs/quickstart_llm.mdx b/docs/quickstart_llm.mdx
new file mode 100644
index 000000000..1621f3a43
--- /dev/null
+++ b/docs/quickstart_llm.mdx
@@ -0,0 +1,62 @@
+---
+title: "Quickstart for LLM"
+description: ""
+icon: "rocket"
+---
+
+
+## 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())
+```