Skip to main content

A CLI tool for generating Markdown notes from academic PDF papers using customizable templates, Zotero metadata, and LLM-powered summaries.

Project description

Zotomatic

Zotomatic is a CLI tool that generates Markdown research notes from PDFs using user-defined templates, Zotero metadata, and extracted text.

Zotomatic は、研究論文の PDF から Zotero の書誌情報や本文抽出結果をもとに、 ユーザー定義テンプレートに従った Markdown 形式の研究ノートを自動生成する CLI ツールです。
日本語版READMEはこちら


Quick Start

Start Guide

Install

pip install zotomatic
zotomatic init --pdf-dir ./papers  # Directory for PDFs

Generate notes from a PDF file

Generate a Markdown note from a specific PDF in any directory.
pdf_dir is not required.

zotomatic scan --path ./papers/sample.pdf

Batch process PDFs under the configured directory

Process all PDFs under the configured directory.
pdf_dir is required.

zotomatic scan --once

Watch the configured directory for new PDFs

Watch the configured directory and generate notes whenever a PDF is added.
pdf_dir is required.

zotomatic scan --watch

Overview

Zotomatic is a CLI tool that starts from research PDFs, uses bibliographic information and extracted text, and generates Markdown notes based on user-defined templates.

For PDFs managed in Zotero, Zotomatic can fetch metadata such as authors, title, and abstract to produce notes enriched with bibliographic details. It can also generate minimal notes for PDFs outside Zotero.

Zotomatic can optionally integrate with an LLM to generate summaries and tags in a specified language and insert the results into notes.
Note: Output quality and accuracy depend on the LLM.

Notes are plain Markdown files, and templates are fully user-defined. You can use them with any editor or knowledge tool, including Obsidian.


Key Features

  • Automatic Markdown note generation from research PDFs
    Avoid manual note taking and output reusable research notes in Markdown.

  • Automatic metadata retrieval from Zotero-managed PDFs
    Pull authors, title, abstract, and other bibliographic data from Zotero and insert them into notes.

  • Support for PDFs outside Zotero
    Generate minimal, structured notes even when PDFs are not registered in Zotero.

  • Best-effort completion for missing metadata
    If Zotero metadata is incomplete, Zotomatic attempts to fill missing fields from PDF text.
    Note: Completion runs only for Zotero-managed PDFs.

  • Flexible, user-defined templates
    Customize headings and sections to match your workflow.

  • Optional LLM summaries and tags (language-selectable)
    Generate summaries and tags via LLM when enabled (default output is Japanese with other languages available).

  • Multiple scan modes
    Use watch, once, or path mode to fit your workflow.


Installation

pip install zotomatic

Use Cases

  • Auto-generate notes from PDFs saved in the browser
    Save a PDF via Zotero Connector and run scan --watch for real-time note creation.
  • Batch-generate notes for an existing library
    Run scan --once to process everything under pdf_dir.
  • Spot-process PDFs outside Zotero
    Use scan --path for quick, file-specific note generation.
  • Auto-insert summaries and tags (optional)
    With an API key, generate summaries and tags in a chosen language (ChatGPT and Gemini supported).

If you want Zotero metadata, keep the Zotero desktop app running.

See docs/en/getting-started.md for step-by-step instructions.


Documentation


Roadmap

  • Support additional LLM providers

Note: Roadmap items and timelines may change.


Notes

  • Zotomatic is a research support tool and does not guarantee the accuracy of generated summaries or tags.
  • Always verify results against the original paper before citing.

License

MIT License


Support and Feedback

Please use GitHub Issues for bug reports.

This is a personal project, so not all issues or pull requests can be addressed. Pull requests are not accepted at this time.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

zotomatic-0.2.0.tar.gz (139.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

zotomatic-0.2.0-py3-none-any.whl (77.1 kB view details)

Uploaded Python 3

File details

Details for the file zotomatic-0.2.0.tar.gz.

File metadata

  • Download URL: zotomatic-0.2.0.tar.gz
  • Upload date:
  • Size: 139.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.1

File hashes

Hashes for zotomatic-0.2.0.tar.gz
Algorithm Hash digest
SHA256 1a868acdf91db320354f25aa96b340bd9202363dd57444af629486cd1c71fbd4
MD5 7e5836560ad9d06ab060958e149d1f6d
BLAKE2b-256 a2d9070d844055434d46cda2f28e08f31f60203f2d5c5947c6fd3e56d6792d37

See more details on using hashes here.

File details

Details for the file zotomatic-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: zotomatic-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 77.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.1

File hashes

Hashes for zotomatic-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 cf0bc33d9d32a1278ac1c989b31a901f1211c8ca6261632cdd154910bd71a7a6
MD5 c72b822b4c94a0d64820397c9f98a213
BLAKE2b-256 e2e73766fcb3917ca4b95c2549c31eed86906b648ef0984180f28b6377383b1a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page