NixOrb v2.0 🌐

Floating AI assistant orb for Arch Linux — KDE Plasma 6 Wayland — Local-Only

A complete ground-up remake of NixOrb with a focus on local AI, rock-solid Qt6 stability, and clean modular architecture.

What's New in v2.0

• Local-only AI — Ollama backend, no API keys needed
• Fixed Qt errors — Proper qasync integration, QSocketNotifier fixes, accessibility bridge disabled
• Simplified architecture — Removed broken backends, focused on what works
• Better VRAM management — Priority eviction keeps GTX 1080 from OOM
• Offline TTS — Piper + espeak-ng fallback
• Improved settings — GUI settings editor with live updates

Architecture Overview

Quick Start

Install (Arch Linux)

git clone https://github.com/minerofthesoal/nixorb.git
cd nixorb
chmod +x install.sh
./install.sh

Start NixOrb

nixorb start          # Launch the floating orb
nixorb trigger        # Activate the running orb (bind to a KDE shortcut)
nixorb status         # Check system status
nixorb quit           # Shut the running orb down
nixorb ask "What is 2+2?"   # One-shot query
nixorb check          # Check dependencies

nixorb trigger talks to the running instance over a Unix socket in $XDG_RUNTIME_DIR, so it works the same under Wayland, X11, or a bare TTY — which is what makes it usable as a KDE global shortcut.

Pipeline Flow

Trigger (Hotkey/WakeWord/Click)
  → Record Audio (sounddevice + VAD)
  → Transcribe (faster-whisper INT8, ~2.1GB VRAM)
  → Think (Ollama LLM stream, localhost:11434)
  → Speak (Piper TTS, offline)
  → Execute (<ACTION> sandboxed bash)

VRAM Budget (GTX 1080 8GB)

Configuration

Edit ~/.config/nixorb/config.toml or use the GUI (right-click orb → Settings):

hotkey = "Ctrl+Alt+Space"
orb_size = 88
llm_model = "llama3.2"
ollama_host = "http://localhost:11434"
tts_backend = "piper"

# Requires the optional extra: pip install 'nixorb[wakeword]'
wake_word_enabled = false

# Ask before running every command the model emits.
require_action_confirmation = true

See config/default.toml for every option with comments.

Orb States

The orb has no caption — its colour is the state, and the tray tooltip spells it out in words.

Keyboard Shortcuts

Project Structure

nixorb/
├── core/           # Event bus, VRAM manager
├── asr/            # Whisper speech-to-text + wake word
├── llm/            # Ollama local LLM backend
├── tts/            # Piper text-to-speech
├── ui/             # Qt6 UI (orb, tray, settings, hotkey)
├── action/         # Sandboxed command execution + clipboard
├── memory/         # ChromaDB vector memory
├── plugins/        # Plugin loader
├── utils/          # Paths, logging, web search
├── vision/         # Screen capture
├── main.py         # Entry point
├── cli.py          # CLI interface
└── settings.py     # Configuration

Dependencies

• System: python 3.12+, qt6-base, qt6-declarative, qt6-wayland, portaudio, wl-clipboard, grim, ollama
• AUR: piper-tts (speech). Note its binary is piper-tts — Arch's piper package is the unrelated gaming-mouse tool. espeak-ng is the fallback if Piper is missing.
• Python: See requirements.txt / pyproject.toml

Troubleshooting

NixOrb writes everything it does to ~/.local/share/nixorb/logs/nixorb.log. Start with nixorb status — it reports whether Ollama is actually reachable and whether the configured model is installed.

Testing

pip install -e ".[dev]"
pytest tests/ -v

License

MIT © NixOrb Contributors