Skip to content

Repository files navigation

🦉 OWLBEARAG

  ____           _ _                     _     ____    _    ____ 
 / __ \         | | |                   | |   |  _ \  / \  / ___|
| |  | |_      _| | |__   ___  __ _ _ __| |__ | |_) |/ _ \| |  _ 
| |  | \ \ /\ / / | '_ \ / _ \/ _` | '__| '_ \|  _ // ___ \ |_| |
| |__| |\ V  V /| | |_) |  __/ (_| | |  | | | | | \/ /   \ \____|
 \____/  \_/\_/ |_|_.__/ \___|\__,_|_|  |_| |_|_| \_\/   \_\____|

Multi-Node AI Orchestration, PyTorch Vector Reranking & Dual-GPU Compute Management Console.


Build Status Latest Release Python 3.10+ PyTorch CUDA License: MIT


⚡ What is Owlbearag?

Owlbearag bridges your local workstation to remote GPU accelerator nodes and Cloudflare production VPS clusters. Whether you need live dual-GPU telemetry, real-time PyTorch document reranking, or automated VPS staging synchronization, Owlbearag handles it smoothly across both a PyQt6 Desktop GUI and a Rich Terminal CLI.


🚀 Quick Start

1. Installation

Install directly from GitHub or download pre-built wheel binaries from Latest Releases:

pip install git+https://github.com/areqpl/Owlbearag.git

2. Launch Interface

# Launch PyQt6 Desktop GUI
owlbearag

# Run Rich Terminal CLI
owlbearag-cli gpu status

🔥 Key Capabilities

  • ⚡ Dual-GPU Live Telemetry: Stream nvidia-smi memory allocations, core temperatures, and model states over SSH (GTX 1080 + RTX 3060).
  • 🧠 PyTorch Neural Vector Reranker: Custom CUDA float16 AMP similarity matrix calculations for chunk reranking.
  • 🌐 Cloudflare VPS Synchronization: Automated background rsync workers pulling staging configurations from remote production nodes.
  • 💬 Web Application & GitHub Pages: Lightweight React + Vite chat UI with true AMOLED dark mode, token streaming, and native multilingual support (English, Polish, Ukrainian, Chinese, Dutch, German).
  • 🔍 389+ Dynamic Command Auto-Discovery: Auto-scans local agent skills, CLI functions, and remote SSH tools in real time.
  • 🔧 Self-Healing Connection Resolver: Probes Ollama HTTP endpoints, tests fallbacks, and executes systemd service restarts automatically.

📚 Deep Technical Documentation


📜 License

Released under the MIT License.

⚠️ Windows users: The generated owlbearag.exe may trigger Windows Defender SmartScreen false‑positive warnings. This is harmless; you can allow the app to run.

About

Enterprise Multi-Node Hybrid RAG, PyTorch Neural Vector Reranker & GPU Compute Console

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages