[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-6894":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":19,"rankGlobal":10,"rankLanguage":10,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":21,"hasPages":21,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":33,"readmeContent":34,"aiSummary":35,"trendingCount":16,"starSnapshotCount":16,"syncStatus":36,"lastSyncTime":37,"discoverSource":38},6894,"cheetah","leetcode-mafia\u002Fcheetah","leetcode-mafia","Mac app for crushing tech interviews with AI","",null,"Swift",4261,300,39,19,0,1,3,60.24,"Creative Commons Zero v1.0 Universal",false,"main",[24,25,26,27,28,29,30,31,32],"ai","chatgpt","gpt","gpt-4","openai","swift","swiftui","whisper","whisper-cpp","2026-06-12 04:00:30","# Cheetah\n\nCheetah 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.\n\n[Quick demo video (1:28)](https:\u002F\u002Fuser-images.githubusercontent.com\u002F106342593\u002F229961889-489e2b36-f3e6-453a-9784-f160bc1c4f8d.mp4)\n\n\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fleetcode-mafia\u002Fcheetah\u002Fraw\u002F91cc5b89864fe28476a7e2062ede2c8322c17896\u002Fcheetah.jpg\" alt=\"Screenshot\">\n\n## How it works\n\nCheetah 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.\n\nWhisper runs locally on your system, utilizing Georgi Gerganov's [whisper.cpp](https:\u002F\u002Fgithub.com\u002Fggerganov\u002Fwhisper.cpp). A recent Mac with Apple silicon is required for optimal performance.\n\n## Getting started\n\n### Prerequisites\n\nRequires macOS 13.1 or later.\n\nTo build Cheetah, [whisper.cpp](https:\u002F\u002Fgithub.com\u002Fggerganov\u002Fwhisper.cpp) must be checked out in `..\u002Fwhisper.cpp`, and the SDL2 library must be installed:\n\n```shell\nbrew install sdl2\n```\n\n### Audio driver setup\n\nFor the best results, ensure the audio input captures both sides of the conversation.\n\nWhen using a video chat app like Zoom or Google Meet, you can achieve this with [BlackHole](https:\u002F\u002Fexistential.audio\u002Fblackhole\u002F), a free audio loopback driver. Follow the instructions for setting up a [Multi-Output Device](https:\u002F\u002Fgithub.com\u002FExistentialAudio\u002FBlackHole\u002Fwiki\u002FMulti-Output-Device), and remember not to use the loopback device as input for the video chat app.\n\n### App overview\n\nOpen the app and select an audio input to start live transcription. A snippet of the transcription will be displayed under the audio input selector.\n\n*Note:* running the app in debug mode will result in very slow audio transcription performance.\n\nThe UI features three buttons:\n\n**Answer:** Generates an answer for the interviewer's question.\n\n**Refine:** Updates the existing answer, useful for when the interviewer provides additional constraints or clarification.\n\n**Analyze:** Analyzes code and logs from the live coding environment in your web browser. Requires the browser extension.\n\nYou can also select (highlight) a portion of a generated answer and click Refine to get more detail.\n\n### Installing the browser extension\n\nCurrently, only Firefox is supported. Follow these steps to install the extension:\n\n1. Add the domain of the live coding platform to `matches` in .\u002Fextension\u002Fmanifest.json\n2. Go to [about:debugging](https:\u002F\u002Ffirefox-source-docs.mozilla.org\u002Fdevtools-user\u002Fabout_colon_debugging\u002Findex.html)\n3. Click \"This Firefox\"\n4. Click \"Load Temporary Add-on\"\n5. Select .\u002Fextension\u002Fmanifest.json\n\n## Disclaimer\n\nCheetah 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.\n","Cheetah 是一款基于AI的macOS应用程序，旨在帮助用户进行软件工程面试练习。它通过集成实时指导和在线编程平台来提供支持，利用Whisper实现实时音频转录，并使用GPT-4生成提示和解决方案。该应用需要用户自备OpenAI API密钥才能运行。Whisper在本地运行，适用于配备苹果芯片的现代Mac设备以获得最佳性能。Cheetah特别适合于模拟面试场景下使用，能够为用户提供即时反馈与代码分析，但需注意其仅推荐用于模拟面试环境中，且可能生成不准确或不合适的内容。",2,"2026-06-11 03:09:25","top_language"]