（评论）

（评论）
(comments)

原始链接: https://news.ycombinator.com/item?id=43580598

CompetitivePen 创建了 OpenRepoPrompt，这是一个开源的、MIT 许可的工具，可以轻松地与大型语言模型 (LLM) 共享代码，且避免厂商锁定。由于导出数据和处理缺乏 API 访问权限的模型（例如 o1 PRO 或 Grok 3）的困难，他们在周末构建了它，将文件和文件夹序列化为 XML 格式供 LLM 使用。该工具旨在简化向 ChatGPT 等模型提供代码的过程，声称复制文件夹的速度为 0.6 秒。虽然文件过滤等功能仍在开发中，但创建者认为它已达到最小可行产品 (MVP) 的标准，并寻求用户反馈。OpenRepoPrompt 可在 GitHub 上获取：github.com/wildberry-source/open-repoprompt。在评论中，siva7 警告用户，ChatGPT 和 Claude 可能会在后台使用 RAG（检索增强生成）技术（未公开），以便在使用项目功能或附加组件集成时节省计算资源，即使代码适合提示上下文窗口，也可能导致响应质量降低。

（评论） 2025-03-19

Show HN: Codemcp – Claude Pro用户专享的Claude代码工具 – 告别API账单 2025-03-19

（评论） 2025-03-19

(评论) 2025-03-26

原文

login

		Show HN: Copy Folder to ChatGPT in 0.6s – OpenRepoPrompt (github.com/wildberry-source)
		4 points by CompetitivePen 2 hours ago \| hide \| past \| favorite \| 1 comment

		Over this past month I had the idea to build a 100% open-source MIT-licensed tool to simplify sharing code with LLMs, without the vendor lock-in you get from most SDKs. Right now, it’s way too hard to export your data or work freely with models like o1 PRO or Grok 3, especially since they don’t even have API access. So I built OpenRepoPrompt, an open-source tool from wildberry-source that serializes files and folders into XML for LLMs. I coded/designed from 12PM -> 11PM on Saturday and 8AM -> 11PM on Sunday. There are still tons of features missing (I'm working on better file filtering next!) but I think it's reached that - buzzword alert! - MVP stage where I want to see if anyone's actually going to use the darn thing. Here's the OpenPrompt repo: https://github.com/wildberry-source/open-repoprompt. Here are some screenshots I took while making it: https://github.com/wildberry-source/open-repoprompt/raw/main.... I think it has some potential. What do you guys think?

siva7 10 minutes ago [–]

One thing not widely known: Be careful when using the projects feature or the addon integration window (e.g. vscode) with chatgpt or Claude. They both use RAG under the hood to save on compute (without disclosing it), even if it would fit in the context window of the prompt. This usually results in worse answers.

reply

（评论） (comments)

（评论）
(comments)