AI-TDD  by di-sukharev

GPT-powered CLI tool for test-driven development

created 2 years ago
277 stars

Top 94.5% on sourcepulse

GitHubView on GitHub
Project Summary

This CLI tool automates Test-Driven Development (TDD) by leveraging GPT models to write code that passes user-provided tests. It targets developers seeking to accelerate their coding workflow by offloading repetitive code generation tasks to AI, enabling faster iteration and validation.

How It Works

AI-TDD operates by taking a test suite as input and prompting a GPT model (defaulting to the latest available) to generate the necessary code to satisfy those tests. The process iterates, feeding the generated code back into the test runner until all tests pass. This approach aims to significantly reduce the manual effort in writing boilerplate code and implementing logic based on test specifications.

Quick Start & Requirements

  • Install via curl -sSL https://raw.githubusercontent.com/di-sukharev/AI-TDD/master/install.sh | bash
  • Requires Bun (latest version recommended).
  • Requires an OpenAI API key with payment details configured.
  • Test runner command must be configured (e.g., npm run test).
  • OpenAI API usage costs apply.

Highlighted Details

  • Supports various testing frameworks, including Jest and Testing Library for frontend tests.
  • Allows configuration of maximum response tokens for GPT.
  • Demonstrates successful generation of React components based on test cases.

Maintenance & Community

  • Project appears to be maintained by a single author, di-sukharev.
  • No explicit community channels (Discord, Slack) or roadmap are mentioned in the README.

Licensing & Compatibility

  • The README does not specify a license.

Limitations & Caveats

The tool relies heavily on the OpenAI API, incurring costs per request. The README notes that the author encountered difficulties in getting the ChatGPT model to reliably solve problems through few-shot prompting, suggesting potential limitations in AI's current ability to handle complex or nuanced coding tasks without significant prompt engineering.

Health Check
Last commit

1 year ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
6 stars in the last 90 days

Explore Similar Projects

Starred by Andrej Karpathy Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n), Patrick von Platen Patrick von Platen(Core Contributor to Hugging Face Transformers and Diffusers), and
4 more.

yet-another-applied-llm-benchmark by carlini

0.2%
1k
LLM benchmark for evaluating models on previously asked programming questions
created 1 year ago
updated 3 months ago
Feedback? Help us improve.