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

Browsegenie

Browsegenie is a GPL-3.0 Python AI agent that uses natural-language prompts to automate browser interactions and scrape structured data from websites. Its documented stack includes Playwright for browser control, BeautifulSoup4 for generated extractors, LiteLLM for model access, tool calling and MCP-related tooling. The scraping workflow caches extractors using an HTML structural hash and regenerates them when a page

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Browsegenie — 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 Browsegenie when a task requires browser navigation or website data extraction and a prompt-driven workflow is more suitable than hand-written selectors or fixed browser scripts. The cached extractor approach is relevant when repeated requests target pages with the same HTML structure.

Who it is for

  • Developers building browser automation workflows
  • Technical teams collecting structured information from websites
  • Users who prefer a local web interface for prompt-driven browser tasks
  • Builders exploring Playwright, web scraping and MCP-connected agent workflows

Documented uses

  • Navigate websites and perform actions such as clicking and scrolling from natural-language instructions
  • Extract requested fields into JSON or CSV output
  • Create reusable page-specific BeautifulSoup4 extractors
  • Run browser-agent tasks through a local web UI
  • Expose or extend browser automation through documented CLI, Python and MCP-related paths
Before you choose

Requirements & limits

The repository documents installation through PyPI and a local web UI launched with `browsegenie-ui`. It identifies the project as public, open source and GPL-3.0 licensed. Provider API keys are documented for Gemini, OpenAI and Anthropic; Ollama is also listed as a selectable provider.

  • Choose it when natural-language browser control and extraction are central to the task.
  • Consider the Playwright and BeautifulSoup4 split when deciding whether the project fits browser interaction, page parsing or both.
  • The extractor cache is relevant to recurring scrapes against stable HTML layouts.
  • Model-provider configuration affects the web UI workflow; the README documents Gemini, OpenAI, Anthropic and Ollama options.
  • Review GPL-3.0 obligations before embedding the project in another software product.

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

Launch the Browsegenie local web UI

Set up and open Browsegenie’s documented no-code local interface.

Before you start

  • Python package installation capability
  • An environment for running the Browsegenie command
  • An AI provider key when required by the selected provider

Steps

  1. Install the package with the command below.

    Documented command
    pip install browsegenie

  2. Launch the interface with browsegenie-ui.

  3. Use the browser interface at the documented local address, http://127.0.0.1:7860.

  4. Select a provider and model, then use the documented browser-agent or extraction workflow.

Expected outcome

A locally running Browsegenie web UI for prompt-based browser tasks and scraping workflows.

Guide limitations

  • The supplied documentation does not specify a complete runtime configuration for every provider or deployment environment.
  • This is a documented setup path, not a verification of successful execution.
Documentation 1 ↗
Evidence and transparency

Sources & review

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