Skip to content

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

Quickstart page

Magnus Müllerd6beef0c7e4a
diff --git a/docs/quickstart.mdx b/docs/quickstart.mdx
index a9a692f62..2df42e4ca 100644
--- a/docs/quickstart.mdx
+++ b/docs/quickstart.mdx
@@ -1,23 +1,18 @@
---
title: "Quickstart"
-description: "Start using Browser Use with this quickstart guide"
+description: ""
icon: "rocket"
---
-<Info>
- You can skip this steps by using [Browser Use Cloud](/cloud/v2/quickstart)
-</Info>
-## Prepare the environment
+## 1. Fast setup
-Use [uv](https://docs.astral.sh/uv/) to setup the Python environment.
+Use [uv](https://docs.astral.sh/uv/) to create and activate the environment:
```bash
uv venv --python 3.12
```
-and activate it with:
-
```bash
# For Mac/Linux:
source .venv/bin/activate
@@ -26,50 +21,43 @@ source .venv/bin/activate
.venv\Scripts\activate
```
-Install the dependencies:
+Install browser-use:
```bash
uv pip install browser-use
```
-Then install Chromium from [source](https://www.chromium.org/getting-involved/download-chromium/) or run the command below (this does not install Playwright only Chromium and dependencies).
+Install Chromium:
```bash
uvx playwright install chromium --with-deps
```
-## Create an agent
+## 2. Choose your LLM
+Create a `.env` file:
+
-Then you can use the agent as follows:
+```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.llm import ChatOpenAI
-from browser_use import Agent
+from browser_use import Agent, ChatOpenAI
from dotenv import load_dotenv
-load_dotenv()
-
import asyncio
-llm = ChatOpenAI(model="gpt-5")
+load_dotenv()
+
+llm = ChatOpenAI(model="gpt-4.1-mini")
+task="Find the number 1 post on Show HN"
async def main():
- agent = Agent(
- task="Go to Hacker News and find the number 1 trending on Show HN",
- llm=llm,
- )
- result = await agent.run()
- print(result)
+ agent = Agent(task, llm)
+ await agent.run()
asyncio.run(main())
```
-
-## Set up your LLM API keys
-
-You need to set up API keys for the LLM you want to use and store them in `.env` file. For example, for OpenAI and Anthropic:
-
-```bash .env
-OPENAI_API_KEY=
-ANTHROPIC_API_KEY=
-```
-
-For other LLM models you can refer to the [Supported Models](/customize/supported-models) page to find how to set them up with their specific API keys.