makecindy
精选
cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.
AI 仓库情报摘要
FR-AI / ANALYSIS为什么值得关注
它将PDF教科书处理的每种故障模式（列错乱、静默数据丢失、图表消失、幻觉引用）视为独立的工程问题，并用确定性门控来解决，只将昂贵模型用于合成环节——这使得在单台机器上从数百本书生成高质量、可追溯的笔记成为可能。
适合谁使用
- 需要管理数十本参考教科书的医学生和临床医生
- 从PDF构建个人可搜索知识库的研究人员
- 希望自动化知识整理的高级AI代理用户（如Claude Code）
- 使用多本教科书学习并希望获得带引用结构化笔记的自学者
典型使用场景
- 将40+本指定参考书转换为统一的AI可搜索Markdown语料库
- 结合多本教科书来源，生成关于某个主题的逐条引用的结构化笔记
- 从PDF教科书中提取并质量检查图表，包括表格和插图
- 通过本地语义搜索（借助vault‑search）跨书查找概念，无需记忆具体出自哪本书
项目优势
- 针对双栏教科书的列感知阅读顺序重建，并提供精确回退路径
- 表格（页面框架拒绝、内容丢失检测、全书可靠性横幅）和图表的确定性质量控制门控（空白填充、文本溢出、OCR长行检查），AI判断前执行
- 按硬件分级的OCR梯级（Surya → PaddleOCR-VL → 本地视觉模型 → 前沿视觉模型），并具备按页静默失败检测
- 生成笔记中的每个声明都追踪到书籍+章节；AI推断的内容会被明确标记
使用前须知
- 需要Python 3.10+并手动安装依赖（pip、ollama、可选GPU驱动），非一键式应用
- 图表提取仍标记为实验性，尚未处理所有书籍布局；欢迎改进PR
- 表格提取在续页或剂量类表格上可能产生错行（值被分配到错误的行）；可选择开启审查队列进行标记，但不自动修复
README 快速开始
textbook-to-note
Turn your own PDF textbooks into an AI-searchable knowledge base and structured, fully-cited notes — figures included. A local-first pipeline that spends (almost) zero LLM tokens on the heavy lifting and reserves the frontier model for the one thing it's uniquely good at: synthesizing a note you can actually learn from.
Why I built this
I've loved taking notes since med school, and over the years I've built up thousands of them — but I can no longer keep every one at the same quality by hand. In an age of information overload, trustworthy high-quality sources become the precious thing, and textbooks are among the best; yet my specialty alone has 40+ designated reference books, with a single concept scattered across chapters in many of them. Reading them all cover to cover just isn't realistic. LLMs are great at long context, but you can't dump hundreds of books on one at once — so the real unlock is pairing good search and a database with teaching the AI my own note-making process, so it produces grounded, structured notes I only have to absorb.
Left: one of the templates in templates/. Right: a real note in my vault, written against it — every claim traceable, every section where I expect it.
Which path are you on?
Not everyone wants the whole pipeline, and the parts stack in one direction — each profile below is the one above it plus one more thing. Pick the smallest one that solves your problem; you can move up later without redoing anything.
| Profile | What you get | What you set up |
|---|---|---|
| A · Converter only | Your PDFs/EPUBs as clean, greppable markdown with page markers, tables, and figure-reference markers. Search with grep. | pip install -r requirements.txt, then converter/convert.py. Nothing else — no GPU, no ollama, no index. |
| B · A + the note workflow | An AI writes structured, per-claim-cited notes from that corpus, with figures extracted through a QC gate. | A, plus the two skills in skills/ and workflows/note-writing.md. |
| C · B + semantic search | Cross-book retrieval by meaning rather than keyword — worth it once "which book was that in?" stops being obvious. | B, plus an indexer: the companion repo vault-search, a local embed |
项目描述
Turn your own PDF textbooks into an AI-searchable knowledge base and structured, fully-cited notes — figures included. Local-first, token-frugal.
相关仓库与替代方案
根据分类、Topic 和编程语言匹配的相似项目。
0xwilliamortiz
精选
openclaude-improved
OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.
7-e1even
精选
learn-agent
A collection of notes on building coding agents, derived from the production development of the desktop agent Reina, with each mechanism simplified into a zero-dependency, single-file Node.js demo.