npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@tgpt/dev

v1.1.5

Published

CLI based smol AI developer, you can use today (for JS projects)

Readme

@tgpt/dev

AI 编程工具正在从 copilot 的对话、补全往项目级代码生成发展。

你可以和 TA 进行反复对话交互开发,将其想象为通过命令行进行结对编程的助手。

显然,这会消耗大量的 token,不过我已经预设了默认免费的 openai_key,开箱即用,快来试试吧~

EN


Feature

初始化

在新目录或者已有项目中执行 setup,按照提示配置基础信息。

cd my-js-project
npx @tgpt/dev setup

如果你没特殊需求,可以一直回车,因为我已经预设了默认值,包括openai_key, 可以在 config 中再次修改,比如 gpt4 效果更佳。

tgpt-setup.gif

你也可以不用 npx,clone @tgpt/dev 到本地,开发调试。

git clone [email protected]:T-Macgrady/tgpt-dev.git
cd tgpt-dev
pnpm i
tgpt-dev setup / npm link

根据提示生成代码

适合根据简短提示需求(中英文都可以)生成基础样板代码/草稿,再逐步优化。

cd my-js-project
npx @tgpt/dev prompt

告诉它你想做什么,如果你没啥头绪,可以直接回车,它会读取当前代码并提供建议。这个过程需要反复请求,稍等片刻~

tgpt-prompt-express_1.gif

AI 完成任务后,可能会发现错误?执行 prompt 让 AI 为你提供修复方案,或者告诉它如何修复,如此反复,直到满意。

响应效果受模型和提示词影响,gpt4 效果更佳,感兴趣可以 clone @tgpt/dev 到本地调优 prompt。

根据代码生成文档

对于简单繁复的文档编写感到乏味?可以让 AI 为你批量生成,协助你理解代码。

可以配置 config.src_include 过滤需要的文件

tgpt-code2spec.gif

在 spec 文件夹可以查看生成的所有文档

根据文档生成代码

新增 spec/README.md 详细描述你的需求,最好是列出每个需要的文件并描述功能,这样在构建更大型项目时才能准确满足你的需求,参考示例:Example

spec 格式:

  • README.md 必要
  • NOTES.md 可选,全局传递给 AI 的更多反馈/指令,可能在 spec 中没有意义
  • <folder>/<filename>.<type>.md 特定文件的 spec

tgpt-spec2code.jpg

End

根据实践,目前它更适合帮助做一些批量转换 / 样板代码生成的工作,结合 copilot 完善细节,还在迭代优化,可以 @tgpt/dev star 一下~