⬇️ ⬆️

Inspiration

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.

What is Sorana?

⬇️ ⬆️

Sorana is an AI-powered visual workspace that transforms how you organize and interact with digital files. Using semantic AI analysis, it automatically groups related files and folders onto a spatial 2D canvas, replacing traditional hierarchies with intuitive visual layouts. Build drag-and-drop workspaces and no-code agent pipelines, connect to on-prem or cloud AI backends (OpenAI, Mistral, LLamacpp, Lemonade, Ollama), and keep your data under your control.

Demonstration of Sorana workspace

⬇️ ⬆️

Download Sorana

Get started with your intelligent workspace.


        $ md5sum Sorana.exe 55e9f2f8179fc59ce552947d30433d4f
        
Get it from Microsoft

Core Capabilities

⬇️ ⬆️
  • Spatial AI Organization: Uses AI to semantically group files and arrange them on a 2D canvas, providing a visual overview of projects.
  • WYSIWYG Canvas Editor: Direct manipulation of workspace elements. Drag and drop files between groups, create new categories, rename items, and adjust group boundaries.
  • Advanced Model Management: Connect to multiple cloud and on-prem LLM backends including OpenAI, Mistral, Ollama, Lemonade, Llamacpp, and other compatible services. The model manager lists all available models and allows users to activate or deactivate models as needed for specific tasks.
  • Multi-Service AI Integration: Sorana supports seamless connection to both on-prem and cloud-based AI services:
    • On-Prem Services: Ollama, Llamacpp, and other self-hosted LLM solutions
    • Cloud Services: OpenAI, Mistral, Lemonade, and other cloud-based AI platforms
  • No-Code Agent Orchestration: Create custom agents and connect them into processing pipelines using a drag-and-drop interface.
  • Contextual Document Chat: Build custom agents and connect them into intelligent pipelines using a simple drag-and-drop interface. Agents collaborate by passing insights from one to another to solve complex problems, all without writing code.
  • Structure Visualization: Generate visual representations of folder hierarchies to understand relationships and organization.
  • Dynamic Structure Mapping: Visualize the big picture. Generate mind maps of your folder hierarchies to reveal relationships and structure.
  • Portable: The application is portable and keeps data under user control.
Sorana Visual Workspace Screenshot

Intended Users

⬇️ ⬆️

Sorana is designed for users who need to organize and analyze complex digital information:

  • Developers: Organize codebases, document projects, and create automation workflows.
  • Researchers: Manage research papers, datasets, and notes with visual organization.
  • Professionals: Organize project files, documents, and resources with visual tools.
  • Creatives: Organize digital assets and project files in a visual workspace.
Sorana Model Manager Screenshot

Operation

⬇️ ⬆️

The application functions through these steps:

  1. Connect folders and files to the workspace.
  2. AI Processing organizes content spatially and semantically.
  3. Visualize projects as interactive layouts.
  4. Interact with documents to extract information.
  5. Create automation workflows by connecting components.
  6. Configure workflow settings.
Sorana Mind Map Screenshot

Technical Implementation

⬇️ ⬆️

AI Model Performance

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.

Hardware Requirements

  • Built-in Models: Range from 1B parameter (806MB) to 20B parameter (12-16GB)
  • Recommended 8B Models (e.g., Llama 3.1 8b Instruct): Minimum 12 GB RAM or 8 GB VRAM for smooth operation
  • Hardware Requirements Increase with Model Size: Larger models with more parameters require higher specifications
  • Cloud Models: No local hardware requirements (requires internet connection)

Alternatives for Limited Hardware

If your system has limited hardware resources, you have two main options:

  • Built-in Portable Model: Works fully offline but may classify complex files as "Miscellaneous"
  • Cloud-based LLMs: Connect to services like OpenAI, Mistral, etc. for high accuracy without local hardware costs
  • Built-in Models: Range from 1B parameter (806MB) to 20B parameter (17-18GB). The smallest model (~806MB) is downloaded on first run and works fully offline. It is fast, but may sometimes classify complex files as "Miscellaneous". For significantly better results, we recommend Llama 3.1 8b Instruct or higher models.
  • AI Integration: Supports connection to both on-prem and cloud-based AI services:
    • Built-in Models: Pre-configured models accessible through the model manager.
    • On-Prem Services:Lemonade, Llamacpp, Ollama, and other self-hosted LLM solutions
    • Cloud Services: OpenAI, Mistral, and other cloud-based AI platforms (paid services provide the best performance)
    • Configuration: Switch between different AI backends based on requirements

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 Capabilities

⬇️ ⬆️

Sorana includes powerful Optical Character Recognition (OCR) capabilities for processing various document types with support for common character encodings:

  • Text PDFs: Extract text from PDF documents (supports embedded text and OCR for scanned content)
  • Plain Text Files: Process .txt files with support for:
    • UTF-8 (recommended for full Unicode support)
    • Latin-1 (ISO-8859-1) as fallback encoding
  • Code Files: OCR support for source code files including:
    • Python (.py), C++ (.cpp), JavaScript (.js), Java (.java)
    • C# (.cs), PHP (.php), Ruby (.rb), Go (.go)
    • TypeScript (.ts), Swift (.swift), Kotlin (.kt)
    • And other common programming language files in UTF-8 or Latin-1 encoding
  • PDFs with Images: Built-in method for OCR processing of PDFs containing images

Requirements for PDF Image OCR

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:

Encoding Support Notes

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.

Feature Comparison

⬇️ ⬆️

Technical differences between Sorana and traditional file management approaches:

Feature Sorana Traditional Tools
File Organization AI-driven spatial layout Manual folder structure
Document Analysis Interactive document interface Basic search functionality
Workflow Creation Visual drag-and-drop interface Manual scripting
Visualization Dynamic visual representations Static list views
Privacy Local AI processing Cloud-based processing
Deployment Portable application Installed application

Installation & Setup

⬇️ ⬆️

Basic installation steps:

  1. Download: Obtain Sorana.exe.
  2. Execute: Run the executable file.
  3. Configure: Add folders to begin organizing digital content.

System Requirements

⬇️ ⬆️
ComponentMinimum
OSWindows 11 (64-bit)
🧠 AI SupportBuilt-in models or on-prem/cloud AI services
💾 RAM≥ 4 GB
💽 StorageMinimum 2 GB (app + model)
⚡ RightsStandard user
⬇️ ⬆️

Get Sorana

Download and install the application.

            
        $ md5sum.exe Sorana.exe 55e9f2f8179fc59ce552947d30433d4f
        
Get it from Microsoft

Support & Donations

⬇️ ⬆️

Support Sorana development.

⬇️ ⬆️

Join our Discord community

⬇️ ⬆️

Leave a review or star the project

The Visual AI Workspace
⬇️ ⬆️

Support via PayPal or Bitcoin Cash

Bitcoin Cash (BCH)

bitcoincash: qrvhk77ujevd9n7jse4jewm99eg95at7tvc6m9v2vv

Bitcoin Cash QR Code

Discover our other tools and games:

⬇️ ⬆️

Check out our other products and tools:

⬇️ ⬆️

New Spaceship - Retro Mini Game

Retro Arcade 2d side-scroller bullet-hell shmup game

⬇️ ⬆️

Website

Spaceship
⬇️ ⬆️

Featured on itch.io

New Spaceship - Retro Mini Game
⬇️ ⬆️

Featured on IndieDB

New Spaceship
⬇️ ⬆️

RyzenZPilot - AMD Ryzen Power Management Tool

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.

⬇️ ⬆️

Website

RyzenZPilot
⬇️ ⬆️

Aicono - AI Intelligent Desktop Icon Autopilot

Aicono automatically organizes your cluttered Windows desktop using AI. Group icons intelligently, arrange them neatly!

⬇️ ⬆️

Website

Aicono
⬇️ ⬆️

Featured on Microsoft Store

Get it from Microsoft
⬇️ ⬆️

Featured on Softpedia

Get it from Softpedia
⬇️ ⬆️

Featured on AlternativeTo

Aicono - AI Intelligent Desktop Icon Autopilot
⬇️ ⬆️

Featured on Product Hunt

Aicono - The AI intelligent desktop icon autopilot for Windows | Product Hunt