Kognitivekompanion — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Kognitivekompanion (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
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.
git clone https://github.com/MagicUnicornInc/KognitiveKompanion.git
cd KognitiveKompanionpip install -r requirements.txt# 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.pySee MULTI_BACKEND_GUIDE.md for detailed setup of different backends.
For AMD Ryzen AI specific setup, see README_RYZEN_AI_SETUP.md.
├── 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 documentationThis project is licensed under the MIT License - see the LICENSE file for details.
See PROJECT_STATUS.md for the current development status and roadmap.
Contributions are welcome! Please feel free to submit a Pull Request.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.