Update README.md

README.md

@@ -13,86 +13,83 @@ tags:
   - offline
   - local-ai
   - multilingual
+  - cli-runtime
 pipeline_tag: text-generation
 library_name: llama.cpp
 ---
 
 # Offline AI 2.1 – EuroLLM-9B-Q8_0 (GGUF)
 
-Offline AI 2.1 is the next evolution of the OfflineAI.online project.
+Offline AI 2.1 is a fully local AI runtime built around digital sovereignty, privacy, and system autonomy.
 
-Version 1 proved a simple idea:  
-AI can run completely offline.  
 No cloud.  
+No telemetry.  
 No tracking.  
-No data collection.  
+No external dependencies.  
 
-Version 2.1 expands this concept into a lightweight private AI workspace designed for independent work, experimentation, and digital sovereignty.
-
-Everything runs locally.  
-No internet connection required.  
-No data leaves your device.
-
-This repository distributes a **quantized GGUF Q8_0 variant of the EuroLLM-9B model** for efficient offline inference via llama.cpp.  
-The original model weights are unmodified and not fine-tuned as part of this project.
+Everything runs locally via llama.cpp.
 
 ---
 
-## 🖥️ PLATFORM
+## 🖥️ CLI Preview
 
-macOS / Windows  
+Below is the Offline AI runtime interface:
 
-- No installation required  
-- No external dependencies  
-- No account needed  
-- Launch and use  
+![Offline AI CLI Help Menu](cli_help_menu.png)
 
-(Platform-specific instructions remain the same as in Version 1.)
+Offline AI is not just a model launcher — it is a structured local AI workspace with:
+
+- Profile handling  
+- Runtime status inspection  
+- Controlled execution flow  
+- Modular architecture foundation  
+- Admin mode (locked access for advanced system control)
 
 ---
 
 ## 🔧 TECHNICAL INFORMATION
 
-Base model: EuroLLM-9B (quantized Q8_0 for offline execution)  
-Format: GGUF (llama.cpp compatible)  
+Base model: EuroLLM-9B  
+Quantization: Q8_0 (GGUF)  
+Format: llama.cpp compatible  
 Runtime: llama.cpp  
 Offline AI Version: 2.1  
 Recommended RAM: 16 GB  
 Platforms: macOS, Windows  
 
-The EuroLLM model provides strong multilingual performance (Czech, Slovak, English, German), optimized for European language contexts. :contentReference[oaicite:2]{index=2}
+This repository distributes a quantized GGUF Q8_0 variant of the EuroLLM-9B model for efficient offline inference.  
+The original model weights are unmodified and not fine-tuned as part of this project.
 
 ---
 
-## 🧠 WHAT CHANGED IN 2.1
+## 🧠 WHAT'S NEW IN 2.1
 
 - Refined CLI architecture  
+- Structured command system  
 - Improved response handling  
 - More stable execution  
-- Cleaner interaction flow  
-- Stronger project identity and structure  
-- Designed as a private AI workspace rather than a simple launcher  
+- Admin access layer (locked system control mode)  
+- Cleaner internal logic separation  
 
-Offline AI 2.1 is not just “run model → chat → exit”.  
-It is built as a foundation for future expansion while remaining minimal and fully local.
+Offline AI 2.1 transitions from a simple launcher to a structured local runtime environment.
 
 ---
 
 ## 🔐 PROJECT PHILOSOPHY
 
-Offline AI exists to demonstrate that:
+Offline AI demonstrates that:
 
-- Modern AI does not require cloud infrastructure  
-- Open-source models can operate independently  
-- Digital tools can respect user privacy  
-- AI can be used without surveillance economics  
+- Modern AI can operate without cloud infrastructure  
+- Open models can run independently  
+- AI tools can respect user privacy  
+- Local-first computing is viable  
 
-This project promotes:
+The project promotes:
 
 - Digital independence  
-- Transparency  
-- Local-first computing  
-- Educational experimentation
+- Transparent system design  
+- Offline experimentation  
+- User-controlled AI environments  
 
 ---
 
@@ -101,11 +98,11 @@ This project promotes:
 Model: EuroLLM-9B  
 Original authors: EuroLLM Project consortium  
 Funded by: European Union research initiatives  
-Base model license: Apache License 2.0
+Base model license: Apache License 2.0  
 
-Quantized distribution: GGUF Q8_0 (for offline inference)  
+Quantized distribution: GGUF Q8_0  
 Runtime: llama.cpp (MIT License)  
-Offline AI interface and wrapper: © David Káninský
+Offline AI interface and wrapper: © David Káninský  
 
 All components are used in compliance with their respective licenses.
 
@@ -125,5 +122,5 @@ Use beyond personal, research, or educational purposes is at your own responsibi
 ## 🌍 PROJECT
 
 Website: https://OfflineAI.online  
-Localizations: .cz / .sk / .de  
-Author: David Káninský
+Domains: .cz / .sk / .de  
+Author: David Káninský