We were frustrated by the limitations of traditional file managers. For decades, we've been forced to organize digital lives into rigid, list-based hierarchies and nested folders that hide information rather than reveal it. Our brains don't work in lists; they work through associations and spatial relationships. We wanted to build a system that reflects this—moving away from "where did I save that file?" to "what is this project about?" by using semantic and visual grouping to reveal the hidden structure of our data.
Sorana is an AI-powered visual workspace featuring a built-in MCP server for advanced file operations, OCR document processing, and spatial AI organization. Transform how you organize digital files with semantic analysis that groups related content onto an intuitive 2D canvas. Create no-code agent workflows, enhance document context with OCR, perform advanced file operations through the MCP server, and connect to on-prem or cloud AI backends (OpenAI, Mistral, Lemonade, and more) while keeping your data under your control.
Demonstration of Sorana workspace
Get started with your intelligent workspace.
$ md5sum Sorana.exe 25829338a9bdfcf1cd77006daf3ba268
Sorana is designed for users who need to organize and analyze complex digital information:
The application functions through these steps:
Sorana uses AI models to intelligently group files and folders based on semantic meaning and logical relationships. The built-in default model is lightweight and works offline, but may not always classify files perfectly, especially for less common file types. For optimal performance, we strongly recommend using Llama 3.1 8b Instruct or higher models. Processing time depends entirely on the folder size - fewer files mean faster processing times. Naturally, the best performance is achieved with paid cloud services.
If your system has limited hardware resources, you have two main options:
Note: Larger models can provide better grouping, but require more memory and processing power. Processing time is directly proportional to the number of files - fewer files result in faster processing. For the best performance, especially with large folders, we recommend using paid cloud services.
Document OCR and Context Enhancement allows users to enrich agents with specific knowledge by dragging and dropping documents directly onto agents. After organizing files spatially, users can make documents accessible to agents by processing them through OCR, converting them into contextual information. This is accomplished via the context menu options 'Document Overview' and 'Process Documents,' which is particularly valuable for PDFs and image-based documents.
It's important to distinguish this from MCP server functionality. While the MCP server allows file interaction during chats, it currently lacks OCR capabilities and can only access text-based file content.
Sorana includes powerful Optical Character Recognition (OCR) capabilities for processing various document types with support for common character encodings:
To enable OCR for PDFs with images, you need to install the official Tesseract OCR engine with default settings and ensure it's available in your system PATH. Tesseract is an open-source OCR engine that provides high-quality text extraction from images.
Download Tesseract from:
The application primarily uses UTF-8 encoding for document processing and falls back to Latin-1 (ISO-8859-1) when UTF-8 decoding fails. For optimal results, we recommend using UTF-8 encoding for your documents. This ensures the best compatibility with international characters and special symbols.
Sorana includes a built-in MCP (Model Context Protocol) server that enables advanced file operations through AI agents. To use these capabilities:
Common file operations you can perform in the agent chat:
Technical differences between Sorana and traditional file management approaches:
| Feature | Sorana | Traditional Tools |
|---|---|---|
| File Organization | AI-driven spatial layout with semantic grouping | Manual folder structure |
| Document Analysis | Interactive document interface with AI chat capabilities | Basic search functionality |
| OCR & Context Enhancement | Drag-and-drop document enrichment with OCR processing for agents | No context enhancement capabilities |
| Workflow Creation | Visual drag-and-drop interface | Manual scripting |
| No-Code Multi-Agent Orchestration | Complex workflows within 2D canvas workspace | Separate tools or manual processes |
| Advanced File Operations | Built-in MCP server for AI-driven file management (read, write, move, search, edit files) | Limited to basic file operations |
| Visualization | Dynamic visual representations and mind maps | Static list views |
| Privacy | Local AI processing with user-controlled data | Cloud-based processing |
| Deployment | Portable application | Installed application |
Basic installation steps:
Sorana.exe.| Component | Minimum |
|---|---|
| OS | Windows 11 (64-bit) |
| 🧠 AI Support | Built-in models or on-prem/cloud AI services |
| 💾 RAM | ≥ 4 GB |
| 💽 Storage | Minimum 2 GB (app + model) |
| ⚡ Rights | Standard user |
Download and install the application.
$ md5sum.exe Sorana.exe 25829338a9bdfcf1cd77006daf3ba268
Support Sorana development.
bitcoincash: qrvhk77ujevd9n7jse4jewm99eg95at7tvc6m9v2vv
Check out our other products and tools:
Retro Arcade 2d side-scroller bullet-hell shmup game
RyzenZPilot is a powerful tool for managing AMD Ryzen processor power settings on Windows. It allows users to adjust CPU performance, power limits, and thermal configurations for optimal performance and efficiency.
Aicono automatically organizes your cluttered Windows desktop using AI. Group icons intelligently, arrange them neatly!
