Gitingest和Robix：两个渲染适用于LLM摄入的代码库的工具

在这里，我们看一下Gitingest和Robix，这是两个渲染适合LLM摄入的代码库的工具。为什么有用？

Here we take a look at Gitingest and Repomix, two tools that render a codebase suitable for LLM ingestion. Why is that useful?

在这里，我们看一下Gitingest和Robix，这是两个渲染适合LLM摄入的代码库的工具。为什么有用？

When wanting to share code with a LLM for asking it to do some work on it, developers face two issues:

当想与LLM共享代码以要求其对其进行一些工作时，开发人员面临两个问题：

* Firstly, LLMs prefer a single input file, while a codebase is split into multiple files and directories.

*首先，llms更喜欢单个输入文件，而代码库分为多个文件和目录。

* Secondly, the URL of the code on services like Github isn't recognized by LLMs.

*其次，诸如GITHUB之类的服务上的代码URL并未被LLM识别。

So here's two tools that help with these issues. First of all Gitingest, which promises to:

因此，这是有助于解决这些问题的两个工具。首先，有望：

Turn any Git repository into a simple text digest of its codebase. Perfect for ingesting code into large language models (LLMs).

将任何git存储库变成其代码库的简单文本摘要。非常适合将代码摄入大型语言模型（LLMS）。

It has a dedicated site with an input box where you can enter the repo's URL, although you can also replace hub with ingest in any Github URL for the same, as in "github.com" to "gitingest.com". Even easier, there's a browser extension for the most popular browsers.

它具有一个专用网站，上面有一个输入框，您可以在其中输入仓库的URL，尽管您也可以在任何GitHub URL中使用摄入的Hub替换Hub，例如“ github.com”中的“ gitingest.com”。更容易的是，最受欢迎的浏览器有一个浏览器扩展程序。

And then Repomix is:

然后ropomix是：

A powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.

一个功能强大的工具，将整个存储库包装到一个单一的AI友好文件中。非常适合当您需要将代码库提供给大型语言模型（LLMS）或其他AI工具（例如Claude，Chatgpt，Deepseek，Cllexity，Gemini，Gemini，Gemma，Gemma，Lllama，Grok等）等其他AI工具。

Repomix looks more professional by sporting a cleaner web interface, giving more options to tweak, while it can also output the result file in XML, Markdown and plain text.

Ropomix通过采用更清洁的Web界面，提供更多调整的选项，同时可以输出XML，Markdown和纯文本的结果。

In either case what do you do with the resulting file? You can give the following instructions to your LLM:

无论哪种情况，您如何处理结果文件？您可以将以下说明给您的LLM：

This file contains all the files in the repository combined into one.

该文件包含存储库中的所有文件合并为一个。

I want to refactor the code, so please review it first. After that I want you to debug the code and write tests for it. Finally generate some code to add a feature.

我想重构代码，因此请先对其进行检查。之后，我希望您调试代码并为其编写测试。最终生成一些代码以添加功能。

Both projects can also be selfhosted by cloning their Github repo. There you have it, modern tooling for developers in the age of AI.

克隆其github存储库也可以自我主持。在那里，您可以为AI时代的开发人员提供现代工具。

More Information

更多信息

GitIngest

吉孔

Repomix

ropomix

Related Articles

相关文章

Potpie - Agentic AI On Your Codebase

POTPIE-代码库上的代理AI

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

要了解有关I程序员的新文章，请注册我们的每周新闻通讯，订阅RSS Feed，然后在Twitter，Facebook或LinkedIn上关注我们。

Pi isn't infinite but it exemplifies the problem with allowing infinity into your life. Every year March 14 (3.14) is celebrated as Pi Day by π aficionados across the globe who can use it as a e[ ... ]

PI不是无限的，但它示出了使无限进入生活的问题。每年3月14日（3.14）庆祝全球π爱好者，他们可以将其用作AE [...]

OpenSilver 3.2 has been released, and can now be used to create WPF applications for mobile platforms. The open-source alternative to Silverlight is capable of running large, complex legacy applicatio[ ... ]

OpenSilver 3.2已发布，现在可以用于为移动平台创建WPF应用程序。 Silverlight的开源替代品能够运行大型，复杂的旧应用程序[...]