IELTS Band 8 Coach: writing and speaking mock tests with official scoring
An IELTS preparation GPT that evaluates essays using official scoring criteria, conducts speaking mock tests, and creates study plans based on a student's target band. It uses LLMs to simulate a coach providing detailed feedback and practice for IELTS candidates.
Visit project ↗Entities
Related
AI voice interview coach for technical communication in English
TechFluent is an AI voice interview coach that trains technical communication in English for non-native speakers. It uses LLMs to simulate interview scenarios and provide feedback on clarity and confidence, not grammar or accent. The tool targets software engineers who need to improve their ability to walk through technical reasoning during interviews.
Open-source AI interview simulator with CLI and local web dashboard
Interview Coach is a free, open-source AI interview simulator that runs in a CLI with a local web dashboard. It uses LLMs to conduct structured mock interviews for any role, supports voice interviews, smart memory, analytics, and PDF reports, and works with any LLM provider or local models.
GroupMark: offline AI grading tool for teachers
GroupMark is a free, offline Windows app for teachers to grade tests and exams. It uses AI to automatically detect answer regions and assign scores, keeping all student data on the user's device. It solves the problem of expensive and feature-limited online grading platforms like Gradescope.
GPAgent - Automated classroom note-taking from lecture recordings
GPAgent is an automated note-taking tool that downloads course recordings from the HKUST-GZ TRMS platform, converts them to audio, transcribes with Whisper, and uses an LLM to generate summaries, knowledge points, self-test questions, and exam information. It outputs structured notes in Markdown, helping students efficiently review lecture content.
Accent coach that scores each sound in speech and drills weak spots
An offline accent coach for non-native English speakers that breaks speech into individual sounds, scores each one (green/yellow/red) in under a second, and identifies mispronunciations (e.g., 't' instead of 'th'). It builds a weak-spot list and drills users until they master each sound twice. The app uses an LLM for sound analysis and feedback generation.
