browser-use-rules

🧠 General Guidelines for Contributing to browser-use

Browser-Use is an AI agent that autonomously interacts with the web. It takes a user-defined task, navigates web pages using Chromium via CDP, processes HTML, and repeatedly queries a language model (like gpt-4.1-mini) to decide the next action—until the task is completed.

---

🧰 Development Rules

• ✅ Always use uv instead of pip For deterministic and fast dependency installs.

uv venv --python 3.11
source .venv/bin/activate
uv sync

• ✅ Use real model names Do not replace gpt-4o with gpt-4. The model gpt-4o is a distinct release and supported.

• ✅ Type-safe coding Use Pydantic v2 models for all internal action schemas, task inputs/outputs, and tools I/O. This ensures robust validation and LLM-call integrity.

• ✅ Pre-commit formatting ALWAYS make sure to run pre-commit before making PRs.

---

Notes:

• Use descriptive names and docstrings for each action.
• Prefer returning ActionResult with structured content to help the agent reason better.

---

🧠 Creating and Running an Agent

To define a task and run a browser-use agent:

from browser_use import Agent, ChatOpenAI

task = "Find the CEO of OpenAI and return their name"
model = ChatOpenAI(model="gpt-4.1-mini")

agent = Agent(task=task, llm=model, tools=tools)

history = await agent.run()

Never create random examples

When I ask you to implement a feature never create new files that show off that feature -> the code just gets messy. If you do anything to test it out, just do the inline code inside the terminal (if you want).