OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Browser Agents

Browser Use

An open-source Python project for building AI agents that navigate and interact with websites through a browser, using the Playwright ecosystem.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Browser Use — OpenViST project profile in Browser Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a workflow requires an agent to interpret webpages and perform several browser actions in sequence, such as finding an appointment slot and completing a booking flow.

Who it is for

  • Developers building browser-using AI agents
  • Teams automating multi-step website workflows
  • Users creating browser research, crawling or form-completion systems

Documented uses

  • Navigate websites and execute multi-step tasks
  • Find and select available appointment dates and times
  • Complete browser-based forms
  • Collect information through web research or crawling
  • Test website interactions with an agent
Before you choose

Requirements & limits

The project is available as a public, MIT-licensed repository. An Agents API is documented. Supported environments listed in the evidence include cloud, Linux, macOS, Windows and Docker.

  • Whether the workflow requires multi-step browser navigation rather than a single scripted action
  • Python and Playwright compatibility
  • Need for an open-source MIT-licensed codebase
  • Whether the project needs an Agents API
  • Whether deployment across cloud, Linux, macOS, Windows or Docker matters

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up and run a local Browser Use Python agent

Install Browser Use, configure an OpenAI key, and run the documented repository-star lookup agent.

Before you start

  • Python 3.11 or later.
  • uv installed; for a new project, the documented setup uses Python 3.12.
  • An OpenAI API key stored in a .env file.
  • The browser-use Python package.

Steps

  1. If starting a new project, initialize it with Python 3.12 using the command below, then install Browser Use with the command below.

    Documented command
    uv init --python 3.12
    Documented command
    uv add browser-use

  2. Create a .env file containing OPENAI_API_KEY=your-key. A BROWSER_USE_API_KEY is optional for the documented BU2 model or cloud-browser option.

  3. Save the documented agent.py example, which creates an Agent with ChatOpenAI, assigns the task Find the number of stars of the browser-use repo, awaits agent.run(), and prints history.final_result().

  4. Run the saved Python script.

Expected outcome

The local Python agent runs the documented browser task and prints its final result.

Guide limitations

  • The example uses OpenAI's gpt-5.6-luna; the evidence does not document model availability or performance.
  • Using BU2 or a cloud browser requires the optional BROWSER_USE_API_KEY; cloud execution is not otherwise documented here.
  • The evidence documents one example task, not general task success or CAPTCHA completion.
  • The source does not provide a command for running the saved script.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
browser-use/browser-use · Official homepage title · retained in its source language
How we review sourcesSuggest a correction