ClioDeck - Writing Assistant for Historians

Desktop application (Electron + React + TypeScript) to assist historians in writing, with RAG (Retrieval-Augmented Generation) and Zotero/Tropy integrations.

Note: ClioDeck is a vibe-coding experiment. It is provided as is, at your own risk. Designed by Frédéric Clavert, coded with Claude Code. See my talk on vibe-coding for historians (French) and ethics considerations.

License: GPLv3

Download

Download v1.0.0-rc.1 (macOS and Linux)

• macOS: DMG for Intel and Apple Silicon
• Linux: AppImage and .deb packages

Key Features

• RAG-powered Research Assistant - Query your PDFs and primary sources using natural language with source citations
• Zotero Integration - Sync bibliography, download PDFs, manage tags and metadata
• Tropy Integration - Import and search primary sources with OCR support
• WYSIWYG Markdown Editor - Write with citation autocomplete (@) and footnotes
• Corpus Analysis - Knowledge graph, textometrics, topic modeling, similarity finder
• Hybrid Search - HNSW vectors + BM25 keywords with multilingual query expansion
• Local-first - All data stays on your machine; works offline with embedded LLM
• Export - PDF (via Pandoc/LaTeX) and Word with template support

Quick Start

1. Install Ollama and models

# macOS
brew install ollama && brew services start ollama

# Linux
curl -fsSL https://ollama.ai/install.sh | sh

# Download required models
ollama pull nomic-embed-text
ollama pull gemma2:2b

2. Install ClioDeck

Download from Releases and run.

For detailed installation instructions, see:

• macOS Installation Guide
• Linux Installation Guide

Build from source (developers)

git clone https://github.com/inactinique/cliodeck.git
cd cliodeck
npm install
npx electron-rebuild -f
npm run build
npm start

See Build and Deployment Guide for distribution builds.

Documentation

Full documentation is available in the ClioDeck Wiki:

User Guides

• Installation - Quick start
• Keyboard Shortcuts - Complete reference
• Zotero Integration - Bibliography sync
• Tropy Integration - Primary sources
• Embedded LLM - Offline mode
• Corpus Analysis - Knowledge graph & textometrics
• Export Options - PDF & Word

Technical Documentation

• Features Overview - Complete feature list
• Technical Architecture - RAG system design
• Build Guide - Development setup

Tech Stack

Layer	Technologies
Frontend	Electron 28, React 18, TypeScript, Milkdown, Zustand, Vite
Backend	Node.js, better-sqlite3, hnswlib-node, pdfjs-dist
AI/LLM	Ollama (nomic-embed-text, gemma2:2b), embedded Qwen2.5
Analysis	Python 3.11+, BERTopic (optional)

Contributing

Issues and contributions are welcome on GitHub.