TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: Flatty – Dead Simple Codebase-to-Text for LLMs

1 点作者 MediaSquirrel4 个月前
Transform any GitHub repo or folder on your Mac into a simple text file so that you can upload it to an LLM (Claude, ChatGPT, etc.) to reason over the whole thing in the context window.<p>LLMs like ChatGPT and Claude let you upload files, but they limit how many you can upload at once. When you&#x27;re dealing with large codebases that have tons of files, you can&#x27;t just upload them directly to an LLM. You end up having to use RAG (retrieval augmented generation) techniques, which in my experience aren&#x27;t as effective as uploading everything into the full context window - especially when you need to reason about architecture or understand the entire system.<p>Flatty is simple to use.<p>Navigate to your project directory in the Terminal and then type &quot;flatty&quot; - that&#x27;s it.<p>The script will output your GitHub repo as a text file (or series of text files in case of large repos) into a folder called &quot;flattened&quot; in your home directory.<p>I hope you find this tool useful in your own work!

1 comment

arnorhs4 个月前
I&#x27;m not an expert in this field, but won&#x27;t you quickly exhaust most context windows with any reasonably sized repo?