This project is an AI meeting assistant and interview copilot that monitors system audio and screen content to generate real-time responses during video calls. It functions as a system audio transcription tool and a context-aware prompt manager, injecting user documents and behavioral profiles into large language model prompts to tailor AI outputs. The system features a stealth screen overlay, utilizing a transparent window that displays information on top of other applications while remaining invisible to screen-sharing software and proctoring tools. It employs a process-hiding mechanism to
Cheetah is an LLM technical interview assistant composed of a native macOS application and a browser extension. It provides real-time coding and answering suggestions during technical interviews by combining live audio transcription with web-based context extraction. The system functions as a real-time interview coach that converts spoken questions into text using on-device speech-to-text processing. It uses a browser-integrated DOM scraper to extract live code and console logs, allowing the AI to analyze the current coding state and generate technical solutions based on the specific environm
Authboss is a modular authentication framework designed to manage user identity and account orchestration. It provides a comprehensive system for handling user registration, email verification, and the full lifecycle of user profiles. The framework distinguishes itself through a focused suite of security and identity tools, including multi-factor authentication via time-based passwords and SMS, and identity integration with external providers using OAuth1 and OAuth2 protocols. It also includes a dedicated account security manager that implements brute-force protection through credential-based
PocketSphinx is an offline speech recognition engine that converts raw audio from files or live microphone streams into written text without requiring a network connection. It functions as a speech-to-text library, a real-time transcription engine, and a voice command processor, capable of detecting and transcribing spoken commands from continuous audio streams with configurable acoustic and language models. The engine uses weighted finite-state transducers to represent acoustic, phonetic, and language models as a single search graph for efficient decoding. It employs fixed-point acoustic mod
Ce projet est une suite d'outils centrée autour d'un assistant d'entretien piloté par IA, un constructeur de CV professionnel et une base de données de salaires d'ingénierie. L'application principale fournit une transcription audio en temps réel et génère du code et des solutions de conception système lors d'entretiens techniques.
Les fonctionnalités principales de ibttf/interview-coder sont : Real-Time Interview Copilots, AI-Powered Code Generation, Real-Time Transcription, Real-Time Audio Transcribers, Keyboard-Driven Interfaces, Stealth Interface Shortcuts, Salary Benchmarking Databases, Audio Processing.
Les alternatives open-source à ibttf/interview-coder incluent : sohzm/cheating-daddy — This project is an AI meeting assistant and interview copilot that monitors system audio and screen content to… leetcode-mafia/cheetah — Cheetah is an LLM technical interview assistant composed of a native macOS application and a browser extension. It… volatiletech/authboss — Authboss is a modular authentication framework designed to manage user identity and account orchestration. It provides… cmusphinx/pocketsphinx — PocketSphinx is an offline speech recognition engine that converts raw audio from files or live microphone streams… thewh1teagle/vibe — Vibe is a cross-platform transcription tool that converts spoken audio into text by running Whisper neural models… const-me/whisper — Whisper is a high-performance speech-to-text inference engine that uses graphics hardware shaders to accelerate the…