Skip to main content

A macOS overlay for AI web applications, providing a floating window with a web view and hotkey support.

Project description

Quiper

A versatile macOS application that provides a system-wide overlay for multiple AI services, including Grok, Gemini ChatGPT and everything other engine that provides a web application. This tool allows you to quickly access your favorite AI assistants with a global hotkey, quickly switch between engines and manage multiple chat instances for each service.

Quiper

Features

  • Multi-Service Support: Seamlessly switch between Grok and Gemini.
  • Multi-Instance Chats: Manage up to 10 simultaneous chat sessions for each service.
  • Global Hotkeys:
    • Option+Space (customizable) to show/hide the application window.
    • Command+Control+<digit-n> to switch to nth engine.
    • Cmd+0 through Cmd+9 to switch between chat instances.
  • Customizable:
    • Easily change the global hotkey to your preferred combination.
    • Adjust the window size and position to fit your workflow. It will remember the last position and size.
    • Add, remove, or reorder the AI services in the settings (Cmd+,).
    • Set css selectors for auto-focusing the input box of the chatbot.

Installation

Easiest way to install and run the application is downloading it from the Latest Release and put it in your Applications folder. macOS will nag you about it being from an unidentified developer, but you can bypass that by right-clicking the app and selecting "Open".

Direct Download Link

You can also install the application using pip:

python3 -m pip install quiper

Or you can clone the repository and run it directly:

git clone https://github.com/sassanh/quiper.git
cd quiper
uv run quiper

To build the application into a standalone macOS app, run:

uv run poe build-app

The dmg file will be created in the dist directory. You can then drag the app to your Applications folder.

To have the application launch automatically at login, run:

/Applications/quiper.app/Contents/MacOS/quiper --install

How It Works

This application is built with PyObjC, which allows Python to interact with Apple's native Objective-C frameworks. It creates a borderless, always-on-top window that contains a WKWebView for each chat instance. The global hotkeys are registered using the quickmachotkey library, and the application state is managed in the AppController class.

Contributing

This is an open-source project, and contributions are welcome. If you have ideas for new features or improvements, please open an issue or submit a pull request on the GitHub repository.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Credits

It is greatly inspired by the macos-grok-overlay project by tchlux, which was originally designed for the Grok AI service. The base of this codebase is mostly copied from that project, mostly the boilerplate code for setting up the macOS application.

Most of the code has been written with gemini-cli and grok. That's why it is so unorganized and messy :D If people find it useful, I will refactor it and make it cleaner, maybe even rewrite it in Swift.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

quiper-0.1.2.tar.gz (160.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

quiper-0.1.2-py3-none-any.whl (161.1 kB view details)

Uploaded Python 3

File details

Details for the file quiper-0.1.2.tar.gz.

File metadata

  • Download URL: quiper-0.1.2.tar.gz
  • Upload date:
  • Size: 160.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for quiper-0.1.2.tar.gz
Algorithm Hash digest
SHA256 8c263ef039c5101cd1036a8dfffb9dc0315562fb8c020555505efa8d370808bc
MD5 e460f920dcc74b19ba84e0cea459b3f0
BLAKE2b-256 2be116b488fdaf38bcf5cd0a96bc86fc71929ef7cea6c4ffb6ec4859e3ea6488

See more details on using hashes here.

Provenance

The following attestation bundles were made for quiper-0.1.2.tar.gz:

Publisher: integration_delivery.yml on sassanh/quiper

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file quiper-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: quiper-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 161.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for quiper-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 84ec12d1e65a21cef5c2e27785a28e748eec5e05c15b826bb8c3d21477176ada
MD5 d2163e4235715d338c1be906f212139b
BLAKE2b-256 7a6f088784150bfeff3bbc34daa451316e633702d262ac9ce7f00976ec685c16

See more details on using hashes here.

Provenance

The following attestation bundles were made for quiper-0.1.2-py3-none-any.whl:

Publisher: integration_delivery.yml on sassanh/quiper

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page