PaperClerk AI：用本地 LLaMA 模型管理 PDF 文献库
PaperClerk AI: Taming the PDF Graveyard | Mohamed Moustafa Dawoud
PaperClerk AI 是一款轻量本地 AI 助手，可扫描电脑中散落的 PDF，并通过 Ollama 调用本地 LLaMA 模型生成摘要，无需靠文件名猜测论文内容。它支持按兴趣自动保留、跳过或归档论文，并按天或按周发送邮件摘要，所有处理均在本地完成以保护文献隐私。
正文
当前显示原文，中文全文译文尚未就绪。
← Back to blog
Monday: "This paper looks essential!" download
Tuesday: "Ooh, looks interesting!" download
Wednesday: "Just in case..." download
Thursday: "Wait, didn't I already...?"
Friday: 500 PDFs stare back, unread.
If this feels familiar, same. That's why I built PaperClerk AI, a lightweight, local, AI-powered assistant that keeps a research library under control.
What it does
It finds the PDFs scattered across your machine and summarizes them with a local LLaMA model (via Ollama), so you can see what each paper is about without guessing from the filename. You can set it to auto-keep, auto-skip, or auto-archive papers based on your interests, and it emails you a digest every day or week. Everything runs locally, so your library stays private.
If your "Read Later" folder has become a PDF graveyard, this might help.
Check it out on GitHub.
Applying to PhD programs, or thinking about it? I mentor a cohort each cycle.