A Python-First Simulated Operating System with a Neural Kernel and Unified Grid UI.
jaxOS is an experimental operating system simulation that explores the intersection of traditional OS architecture and modern AI. It features a Neural Kernel that uses a Large Language Model (LLM) to interpret user intent, a Unified Grid UI for consistent application design, and a robust Filesystem Shell.
- Intent-Driven Execution: The kernel parses natural language command using a local LLM (
gemma3:12b). - Hybrid Shell: Supports both traditional commands (
ls,cd) and AI queries.
- Procedural Rendering: A custom
TkRendererdraws a retro-futurist, monochrome interface. - Grid Layout Engine: Applications use a responsive
PanelandGridLayoutsystem. - Apps:
- Calculator: A fully functional grid-based calculator.
- SysMon: Real-time system monitoring (CPU, RAM, Network).
- Notes: A text editor with toolbar and file I/O.
- Code Studio: A Python REPL environment.
- Clock: A digital timer.
- Filesystem Shell: Full support for
ls,cd,mkdir,rmdir,cat,pwd. - Package Manager (
map): Install and remove apps dynamically (map list,map install). - Authentication: Secure login with password hashing and recovery keys.
-
Clone the Repository:
git clone https://github.com/Jalpan04/jaxOS.git cd jaxOS -
Install Dependencies:
pip install -r requirements.txt
-
Boot the OS:
python kernel/main.py
Note: For AI features, ensure Ollama is running with
gemma3:12b.
- Kernel:
kernel/main.py- The central event loop and syscall handler. - UI:
ui/tk_renderer.py- Tkinter-based rendering engine. - Filesystem:
fs/db.py- SQLite-backed flat filesystem with virtual directories. - AI Bridge:
kernel/intent_parser.py- Interfaces with Ollama for NLU.
See ARCHITECTURE.md for a deep dive.
Contributions are welcome! Please read CONTRIBUTING.md for guidelines.
MIT License. See LICENSE for details.