Probly is a next-generation spreadsheet application designed for users who want to integrate AI-driven analysis, Python computation, and document processing directly into their data workflows. It aims to simplify complex data analysis tasks by offering a familiar spreadsheet interface enhanced with intelligent features and local Python execution.

How It Works

Probly utilizes a modern, privacy-focused architecture. The frontend is built with Next.js, running React and TypeScript in the browser. Core data analysis and Python computation are handled by Pyodide, which compiles Python to WebAssembly, enabling execution directly within the browser. AI-powered insights and document processing leverage external APIs, specifically OpenAI for language models and Vision API for data extraction from images. This client-side execution model enhances performance and user privacy by minimizing server-side data processing.

Quick Start & Requirements

• Docker: git clone https://github.com/PragmaticMachineLearning/probly.git && cd probly && echo "OPENAI_API_KEY=your_api_key_here" > .env && docker compose build && docker compose up -d
• Manual: Node.js 18+, npm/yarn, modern browser, OpenAI API key.
• Documentation: Probly Documentation

Highlighted Details

• Full-featured spreadsheet with formula support and intelligent cell suggestions.
• Direct Python execution in the browser via Pyodide (WebAssembly).
• AI-powered analysis and automated trend identification using OpenAI.
• Document processing for data extraction from images via Vision API.
• Interactive data visualization with ECharts.

Maintenance & Community

• Active Discord community for support and contributions: Discord.

Licensing & Compatibility

• MIT License. Permissive for commercial use and integration with closed-source projects.

Limitations & Caveats

Requires an OpenAI API key for AI features, incurring external costs. The Vision API for document processing may have associated usage limits or costs.