Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun.
Cheetah Cheetah is an AI-powered macOS app designed to assist users with software engineering interview practice. It provides real-time coaching and live coding platform integration. Quick demo video (1:28) How it works Cheetah leverages Whisper for real-time audio transcription, and GPT-4 for generating hints and solutions. You need to have your own OpenAI API key to use the app. Whisper runs locally on your system, utilizing Georgi Gerganov's whisper. A recent Mac with Apple silicon
is required for optimal performance. Getting started Prerequisites Requires macOS 13. cpp must be checked out in , and the SDL2 library must be installed: Audio driver setup For the best results, ensure the audio input captures both sides of the conversation. When using a video chat app like Zoom or Google Meet, you can achieve this with BlackHole, a free audio loopback driver. Follow the instructions for setting up a Multi-Output Device, and remember not to use the loopback
device as input for the video chat app. App overview Open the app and select an audio input to start live transcription. A snippet of the transcription will be displayed under the audio input selector. *Note:* running the app in debug mode will result in very slow audio transcription performance. The UI features three buttons: **Answer:** Generates an answer for the interviewer's question. **Refine:** Updates the existing answer, useful for when the interviewer provides additional constraints or clarification. **Analyze:** Analyzes
code and logs from the live coding environment in your web browser. You can also select (highlight) a portion of a generated answer and click Refine to get more detail. Installing the browser extension Currently, only Firefox is supported. Follow these steps to install the extension: 1. Add the domain of the live coding platform to in . json Disclaimer Cheetah is intended for use in mock interviews only. It may generate incorrect or inappropriate solutions. Users take full responsibility for
the information provided by the app.
Frequently asked questions
How many stars and forks are recorded?
leetcode-mafia/cheetah has 4,261 stars and 298 forks.
What is the repository rank?
leetcode-mafia/cheetah is ranked 7,653.
What language and category are recorded?
leetcode-mafia/cheetah has 4,261 stars, uses Swift and belongs to Applications.
Which repository is closest in rank?
leetcode-mafia/cheetah is compared with composio-community/open-claude-cowork, ranked 7,642 with 4,292 stars.
README
Cheetah
Cheetah is an AI-powered macOS app designed to assist users with software engineering interview practice. It provides real-time coaching and live coding platform integration.
Cheetah leverages Whisper for real-time audio transcription, and GPT-4 for generating hints and solutions. You need to have your own OpenAI API key to use the app.
Whisper runs locally on your system, utilizing Georgi Gerganov's whisper.cpp. A recent Mac with Apple silicon is required for optimal performance.
Getting started
Prerequisites
Requires macOS 13.1 or later.
To build Cheetah, whisper.cpp must be checked out in ../whisper.cpp, and the SDL2 library must be installed:
brew install sdl2
Audio driver setup
For the best results, ensure the audio input captures both sides of the conversation.
When using a video chat app like Zoom or Google Meet, you can achieve this with BlackHole, a free audio loopback driver. Follow the instructions for setting up a Multi-Output Device, and remember not to use the loopback device as input for the video chat app.
App overview
Open the app and select an audio input to start live transcription. A snippet of the transcription will be displayed under the audio input selector.
Note: running the app in debug mode will result in very slow audio transcription performance.
The UI features three buttons:
Answer: Generates an answer for the interviewer's question.
Refine: Updates the existing answer, useful for when the interviewer provides additional constraints or clarification.
Analyze: Analyzes code and logs from the live coding environment in your web browser. Requires the browser extension.
You can also select (highlight) a portion of a generated answer and click Refine to get more detail.
Installing the browser extension
Currently, only Firefox is supported. Follow these steps to install the extension:
Add the domain of the live coding platform to matches in ./extension/manifest.json
Cheetah is intended for use in mock interviews only. It may generate incorrect or inappropriate solutions. Users take full responsibility for the information provided by the app.
