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

Browserpilot

BrowserPilot is an open-source Python web-browsing agent that translates natural-language instructions into Selenium-based browser actions using ChromeDriver and GPT-3.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Browserpilot — 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 BrowserPilot when a browser task can be expressed as a clear sequence of page actions and you want to drive those actions through a Python Selenium agent.

Who it is for

  • Developers automating repeatable browser navigation or form interactions
  • People building browser-based information-gathering or scraping workflows
  • Python users comfortable writing precise, Selenium-aware instructions

Documented uses

  • Describe browser navigation and page interactions in plain English rather than writing each action as bespoke automation code.
  • Find and interact with page elements, enter text, wait, scroll and retrieve page information.
  • Organize repeated instruction sequences using the documented function syntax or YAML/JSON instruction files.
Before you choose

Requirements & limits

The repository specifies an MIT license. The documented setup requires an OpenAI API key.

  • Requires Python, ChromeDriver and an OpenAI API key for the documented workflow.
  • The README recommends precise instructions and familiarity with Selenium and programming.
  • Compiled instructions can be saved to a file to avoid repeated API costs for those instructions.

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 BrowserPilot for browser automation

Install the package and prepare the documented ChromeDriver and API-key prerequisites for using the Python agent.

Before you start

  • Python environment with pip
  • ChromeDriver downloaded and unpacked
  • OpenAI API key

Steps

  1. Install BrowserPilot with the command below.

    Documented command
    pip install browserpilot

  2. Download ChromeDriver and place the unpacked executable in the working folder.

  3. Set the OPENAI_API_KEY environment variable.

Expected outcome

The documented package, browser driver and API-key prerequisites are prepared for the agent usage stage.

Guide limitations

  • These steps cover setup only; the README's usage example requires Python code, natural-language instructions and a ChromeDriver path.
  • The README recommends precise, Selenium-aware prompts.
Documentation 1 ↗
Source-based practical guide

Describe a browser task for the Python agent

Pass a sequence of browser actions as natural-language instructions to the documented GPTSeleniumAgent interface.

Before you start

  • BrowserPilot installed
  • ChromeDriver executable and its path
  • OPENAI_API_KEY environment variable
  • Python programming familiarity

Steps

  1. Import GPTSeleniumAgent from browserpilot.agents.gpt_selenium_agent.

  2. Write instructions as separate, specific actions, using page-element terms such as textarea when appropriate.

  3. Create the agent with the instructions and ChromeDriver path, then call agent.run().

Expected outcome

The agent receives the task instructions and runs the documented browser-automation workflow.

Guide limitations

  • Prompt precision matters; the README advises familiarity with Selenium and programming.
  • The documented example uses GPT-3 to translate natural-language instructions into code.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
handrew/browserpilot · Official homepage title · retained in its source language
How we review sourcesSuggest a correction