mcpField
K
KognitiveKompanion

KognitiveKompanion

Local
github.com/MagicUnicornIncAI & Agents0Updated 84w ago
Repository

About KognitiveKompanion

KognitiveKompanion is an AI interface for KDE and other desktop environments, for users who want to work with different model backends and manage conversations. It combines chat history tools with screen and audio input and a RAG toggle.

Key features

  1. 01Supports OpenAI, Ollama, and AMD Ryzen AI
  2. 02Save, load, and export conversations
  3. 03Screen capture and audio input
  4. 04RAG toggle
  5. 05KDE theming, system tray, and floating window

Use cases

  1. 01Switch between AI backends in a desktop interface
  2. 02Save and organize AI conversation history
  3. 03Add screen or audio context to conversations
  4. 04Use the RAG feature during interactions

MCP support

The project includes an MCP client component; the README does not specify how it connects to or manages MCP servers.

#kde#ai#interface#openai#ollama#amd#ryzen#hardware#acceleration

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

KognitiveKompanion

A modern, versatile AI interface for KDE and other desktop environments, designed to provide a seamless interaction with various AI backends including OpenAI, Ollama, and AMD Ryzen AI hardware acceleration.

Features

  • Multi-Backend Support:
    • OpenAI API integration (GPT-4o, GPT-3.5-Turbo, etc.)
    • Ollama backend for local models
    • AMD Ryzen AI hardware acceleration
  • Advanced UI:
    • Collapsible sections for a clean interface
    • Conversation sidebar for managing chat history
    • Modern styling with KDE theming integration
    • System tray icon and floating window option
  • Context Features:
    • Screen capture capability for visual context
    • Audio input support
    • RAG (Retrieval-Augmented Generation) toggle
  • Conversation Management:
    • Save and load conversations
    • Export chat history

Requirements

  • Python 3.8+ (Python 3.12 recommended)
  • PyQt5
  • KDE Plasma 5 Desktop (optional, works on other desktops too)
  • One of the following backends:
    • OpenAI API key
    • Ollama running locally
    • AMD Ryzen AI compatible hardware (optional)

Installation

  1. Clone the repository:
git clone https://github.com/MagicUnicornInc/KognitiveKompanion.git
cd KognitiveKompanion
  1. Install dependencies:
pip install -r requirements.txt
  1. Run the application with your preferred backend:
# OpenAI backend
./run_openai_gui.sh

# Ollama backend
./run_kde_ai_interface.py

# AMD Ryzen AI (if supported hardware is available)
./run_ryzen_ai_model.py

Configuration

See MULTI_BACKEND_GUIDE.md for detailed setup of different backends.

For AMD Ryzen AI specific setup, see README_RYZEN_AI_SETUP.md.

Project Structure

├── app_root/             # Core application code
│   ├── ui/               # UI components and widgets
│   ├── mcp/              # Model Control Protocol client
│   ├── config/           # Configuration management
│   ├── rag/              # Retrieval-Augmented Generation
│   ├── system/           # System integration and optimization
│   └── utils/            # Utility functions
├── amd-ryzen-ai/         # AMD Ryzen AI integration
├── quark-integration/    # Quantization toolkit integration
└── MCP-INTEGRATION-GUIDE.md  # MCP server documentation

License

This project is licensed under the MIT License - see the LICENSE file for details.

Project Status

See PROJECT_STATUS.md for the current development status and roadmap.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Acknowledgments

  • KDE Community
  • OpenAI and Ollama projects
  • AMD for Ryzen AI support
  • PyQt/Qt developers

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.