Get QUAILS

Free, open-source, and runs entirely on your own machine.
No account. No subscription. No data leaving your desk.

MIT License Version 1.0 · February 2026 Python 3.10+ · Node.js 20+
🪟

Windows

Windows 10 / 11
64-bit · x86

Coming Soon

Installer not yet available — use GitHub source below

🍎

macOS

macOS 12 Monterey+
Intel & Apple Silicon

Coming Soon

Installer not yet available — use GitHub source below

🐧

Linux

Ubuntu 20.04+ · Debian
AppImage · .deb

Coming Soon

Installer not yet available — use GitHub source below

Source Code

Build from source · Latest commits
MIT License · Contributions welcome

Always Latest
View on GitHub
💡
No packaged installer yet? The source installation takes about 5 minutes. Clone the repository, install Python and Node dependencies, and launch with the included one-click starter script for your OS. Full instructions below.
Requirements

What You Need

ComponentRequired
Python3.10 or later (3.14+ recommended)
Node.js20.19+ or 22.12+
RAM8 GB minimum (16 GB+ for larger models)
Disk2 GB (app) + model storage (4–40 GB per model)
OSWindows 10/11, macOS 12+, Ubuntu 20.04+
OllamaOptional — required for local AI only
InternetOnly needed to download models; not for analysis
💡
A GPU accelerates Ollama inference significantly but is not required. QUAILS runs on CPU-only hardware — it will be slower per unit, but fully functional.
What else you'll need

Ollama (Recommended)

Ollama is a free background application that runs AI models locally on your machine. It's what makes QUAILS work with no internet, no API key, and no data leaving your desk.

  • Download from ollama.com (Windows, macOS, Linux)
  • Install and run — it starts automatically in the background
  • Pull a model: ollama pull gemma3
  • QUAILS detects Ollama automatically — no configuration needed
✓
Use QUAILS's built-in "Test my system" feature in AI Settings to get hardware-matched model recommendations — no guessing about which model fits your machine.
Installation

Install from Source

QUAILS runs as a local web app — a small Python backend and a React frontend, both on your machine. Follow the steps for your operating system.

🪟 Windows
🍎 macOS
🐧 Linux

Prerequisites

  • Python 3.10+ — download from python.org (check "Add Python to PATH" during install)
  • Node.js 20.19+ — download from nodejs.org
  • Git — download from git-scm.com

Steps

  1. Clone the repository:
    git clone https://github.com/jeremyriel/QUAILS.git
cd QUAILS
  2. Double-click start.bat in the QUAILS folder — it validates your Python version, installs all dependencies, and opens the app in your browser automatically.
  3. On first run, go to AI Settings and configure your LLM (Ollama recommended).
⚠️
If you have multiple Python installations, make sure start.bat is using Python 3.10+. Run python --version in Command Prompt to verify.

Prerequisites

  • Python 3.10+ — install via Homebrew (brew install python@3.12) or from python.org
  • Node.js 20.19+ — install via Homebrew (brew install node) or from nodejs.org
  • Git — included with Xcode Command Line Tools (xcode-select --install)

Steps

  1. Clone the repository:
    git clone https://github.com/jeremyriel/QUAILS.git
cd QUAILS
  2. Make the launcher executable and run it:
    chmod +x start.command
open start.command
    Or double-click start.command in Finder. It installs dependencies and opens the app.
  3. On first run, go to AI Settings and configure your LLM (Ollama recommended).
💡
On Apple Silicon (M1/M2/M3/M4), Ollama runs models natively using the Neural Engine and GPU — performance is excellent even without a discrete GPU.

Prerequisites

  • Python 3.10+: sudo apt install python3 python3-pip (Debian/Ubuntu)
  • Node.js 20.19+: use fnm (curl -fsSL https://fnm.vercel.app/install | bash) or nvm
  • Git: sudo apt install git

Steps

  1. Clone the repository:
    git clone https://github.com/jeremyriel/QUAILS.git
cd QUAILS
  2. Run the Linux launcher:
    chmod +x start_linux.sh
./start_linux.sh
    The launcher checks Node/Python versions, handles fnm version switching if needed, installs dependencies, and opens the browser.
  3. For a desktop shortcut, copy QUAILS.desktop to ~/.local/share/applications/ and update the Path= line to your QUAILS directory.
  4. On first run, go to AI Settings and configure your LLM (Ollama recommended).
✓
The Linux launcher uses sensible-browser to open the app when launched from a desktop entry — more reliable than xdg-open in non-interactive shells.
Next Steps

Installed? Here's Where to Start.

QUAILS is running at http://localhost:5173. Open it in your browser and follow the Quick Start Guide.

⚙️
1. Configure AI
Click "AI Settings" on the project list and set up Ollama or a cloud provider.
📁
2. Create a Project
Click "New Project," choose a template, upload your corpus, and configure your first block.
🎯
3. Calibrate First
Go to the Alignment tab, label a sample, and run your first Kappa comparison before full analysis.
Read the Quick Start Guide →

Open Source & Free Forever

QUAILS is MIT-licensed. Use it freely in your research, fork it, extend it, or contribute back. The source is on GitHub and always will be.

jeremyriel/QUAILS on GitHub