BrowserKitten
A Chrome side-panel agent for your signed-in browser. Read pages, take action, create files, and run local follow-ups. Bring your own models.
What is BrowserKitten?
A Chrome side-panel agent for your signed-in browser. Read pages, take action, create files, and run local follow-ups. Bring your own models.
Overview of BrowserKitten
What it is
BrowserKitten is an MIT-licensed Chrome MV3 extension that adds an agent to the browser's side panel. It works with your existing signed-in browser session, keeping conversations, workspace files, and follow-up tasks on your local computer. You bring your own models and configure providers for inference, page actions, and other services.
Key features
- Read & research: Understand pages you are signed in to, select relevant content, and collect findings.
- Act on pages: Delegate clicks, form entry, and navigation to a separately configured execution model.
- Create deliverables: Save documents, HTML pages, data, and files in a session workspace.
- Follow up: Arrange local checks, preserve progress, and manage ongoing tasks from a collapsible drawer.
- No build step required: The source folder itself is the extension load root; no Node.js, Python, or npm needed.
Use cases
- Research and summarization of web pages, especially those behind login.
- Automating repetitive browser interactions like form filling and navigation.
- Generating documents, reports, or data files from web content.
- Setting up local monitoring tasks that run on a minute-scale schedule while Chrome is open.
Getting started
See the repository README for installation and quick-start instructions.
License and pricing
MIT license. Open source. No pricing information provided.
Based on the project's public README and repository metadata.