Practical overview
When it fits
Use it when you have a test suite and a command that runs those tests, and want GPT-generated code shaped by the test results.
Who it is for
- Developers who write tests and want GPT to generate implementation code against them.
- Frontend developers using test suites such as Jest and Testing Library.
Documented uses
- Provide a test suite as the specification for generated code.
- Run a configured test command as part of an iterative code-generation workflow.
Requirements & limits
Requires Bun and an OpenAI API key. The README says users pay for their own OpenAI API requests and that the key is stored locally in `~/.aitdd/config`.
- You supply the tests and configure the command used to run them.
- The README demonstrates a frontend example using Jest and Testing Library.
- The default maximum response-token setting is 2,000; the README documents a configuration setting for changing it.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Configure AI Tdd for a test suite
Install the CLI and configure its OpenAI key and test-running command.
Before you start
- Bun
- An OpenAI API key with payment details added so API requests can work
- A project test command
Steps
Install AI Tdd globally using the install command in the project README.
Set the API key with
aitdd config set OPENAI_API_KEY.Set the test command, for example
aitdd config set RUN_TESTS "npm run test".
Expected outcome
The CLI has an OpenAI API key and a configured command for running the project's tests.
Guide limitations
- OpenAI API requests are paid by the user.
- This setup guide does not verify that the project’s tests run successfully.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 17 October 2026
- Original website title
- di-sukharev/AI-TDD · Official homepage title · retained in its source language