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

Browserkitten

Browserkitten is an open-source, unpacked Chrome extension with a side-panel agent that can operate the current tab, run guest JavaScript against the browser and retain spreadsheet, Univer document and site-HTML artifacts in a session.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Browserkitten — 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 Browserkitten when a task involves operating a regular webpage in Chrome and you want session artifacts kept alongside the browser work.

Who it is for

  • Chrome users who want an AI agent to act on the webpage currently open in their browser.
  • People who want browser tasks to produce or retain spreadsheet, document or page-HTML artifacts.
  • Developers interested in adapting a JavaScript, MIT-licensed browser-agent extension.

Documented uses

  • Send a task to an agent working on the current browser tab.
  • Run guest JavaScript against the browser.
  • Keep spreadsheet, Univer document and website HTML artifacts in the session.
Before you choose

Requirements & limits

The repository instructs users to load the extension unpacked in Chrome; it is not on the Chrome Web Store. Chrome 135 or later is required, and users supply an OpenAI-compatible API key.

  • Model access is user-configured: the extension requires an OpenAI-compatible API key and does not use a hosted model service.
  • Installation involves Chrome developer mode and loading the unpacked extension folder.
  • Tasks are sent from a normal HTTP or HTTPS page; restricted browser pages are unavailable to the agent.
  • Optional browser operations have version or DevTools conditions: Allow User Scripts is required for specified operations on Chrome 138 or later, and DevTools must be closed for sys.cdp.

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

Load BrowserKitten as an unpacked Chrome extension

Install the extension in Chrome and configure its OpenAI-compatible API key to submit a task on a supported page.

Before you start

  • Chrome 135 or later.
  • A local copy of the repository or a downloaded Release zip.
  • An OpenAI-compatible API key.
  • A normal http(s) page for task submission.

Steps

  1. Clone the repository or download a Release zip.

  2. In Chrome, open chrome://extensions, enable Developer mode, choose Load unpacked, and select the folder containing manifest.json at its root.

  3. Open the extension side panel, paste the API key, and send a task while viewing a normal http(s) page.

Expected outcome

The unpacked extension is loaded, and the side-panel agent can receive a task on the current supported page.

Guide limitations

  • The extension is not on the Chrome Web Store and has no hosted model; provide your own key.
  • Restricted pages such as chrome:// and the Web Store return NEED_PAGE.
  • On Chrome 138+, enable Allow User Scripts if using sys.eval or page-identity fetch.
  • Close DevTools on the target tab before using sys.cdp, or it may return CDP_BUSY.
  • There is no package.json and no build step.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
Player-YN/BrowserKitten · Official homepage title · retained in its source language
How we review sourcesSuggest a correction