Get structured band feedback on a practice IELTS Writing Task 2 essay.
Review a Speaking transcript for feedback with a pronunciation confidence caveat.
Analyze Reading mistakes to get evidence based practice recommendations.
Embed the evaluator core into an existing IELTS prep product.
| shpaldik/openielts-ai | apex-dao/limitless-trading-bot | sethispr/image-compressor | |
|---|---|---|---|
| Stars | 84 | 84 | 84 |
| Language | TypeScript | TypeScript | TypeScript |
| Setup difficulty | moderate | easy | easy |
| Complexity | 3/5 | 2/5 | 2/5 |
| Audience | developer | developer | general |
Figures from each repo's GitHub metadata at analysis time.
Requires your own OpenAI API key and Node.js 20 or newer.
OpenIELTS AI is a self hosted evaluation tool for people practicing the IELTS English test. It focuses on three parts of the exam: Writing Task 2, Speaking, and Reading. Instead of giving you a single mystery score, it produces a structured report you can actually inspect, with an estimated practice band, feedback broken down by the official IELTS style criteria, exact quotes from your own answer as evidence, a list of strengths, and a prioritised plan for what to fix first. The project was pulled out of a larger platform called Hack Admission, where it was originally built, and released as a separate open source core so other developers can reuse it. It is not affiliated with or endorsed by IELTS, IDP, the British Council, or Cambridge, so it should be treated as a practice helper rather than an official scoring tool. Each evaluator is defined by a YAML configuration file, so you can change the model, the instructions, or the grading criteria without touching the underlying code. It connects to OpenAI through the Responses API, using structured JSON Schema output so a product interface or analytics tool can read the results directly instead of parsing free text. Writing evaluations add a word count, Speaking evaluations add a note about the transcript, and Reading evaluations add patterns of mistakes. To use it you need Node.js 20 or newer. You clone the repository, install dependencies, copy the example environment file, add your own OpenAI API key, and run the evaluate command with a chosen config and input file. There is also a dry run mode that shows you the exact prompt being sent, without making a network call, which is useful for checking your setup before spending API credits. The README states clearly that no official IELTS materials, Cambridge books, audio, or real learner records are bundled with the project, only original or example content. It includes a CLI, example inputs, and a test suite, and is released under the MIT license.
A self hosted tool that grades IELTS Writing, Speaking, and Reading practice answers using AI, returning a structured score report instead of a single number.
Mainly TypeScript. The stack also includes TypeScript, Node.js, OpenAI API.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.