Initial commit: NOVA - Neuro-Optimizing Versatile Agent

Complete transformer LLM built from scratch with:

Core Features:
- Full transformer architecture (RoPE, RMSNorm, SwiGLU, KV-cache)
- SentencePiece tokenizer (BPE/Unigram)
- Training pipeline (AMP, gradient checkpointing, DDP)
- Persona system with personality matrix (NO AI disclosure by default)
- Genetic evolution (NOVA-EVO) for hyperparameter optimization
- Legal-only data pipeline with license tracking
- Chat interface (CLI + REST API)
- Conversation memory (SQLite)

Model Sizes:
- 125M, 350M, 1.3B, 3B parameters
- Local-first, runs on CPU or GPU
- Python 3.10.6+, PyTorch 2.0+

Personas:
- girlfriend_gentle (high warmth, high empathy)
- girlfriend_playful (high humor, high playfulness)
- girlfriend_supportive (balanced, default)

Documentation:
- Complete README with quickstart
- Model card with ethical considerations
- Privacy documentation (local-first, zero telemetry)
- Data licenses and attribution
- Contributing guide

Infrastructure:
- GitHub Actions CI/CD
- Comprehensive test suite
- Quickstart script
- CLI tool

License: Apache 2.0

🤖 Generated with Claude Code
https://claude.com/claude-code

Co-Authored-By: Claude <noreply@anthropic.com>

scripts/quickstart.sh

@@ -0,0 +1,87 @@
+#!/bin/bash
+
+# NOVA Quickstart Script
+# Sets up NOVA for first-time use
+
+set -e
+
+echo "======================================"
+echo "NOVA Quickstart"
+echo "======================================"
+echo ""
+
+# Check Python version
+echo "Checking Python version..."
+python_version=$(python --version 2>&1 | grep -oP '(?<=Python )\d+\.\d+')
+required_version="3.10"
+
+if [ "$(printf '%s\n' "$required_version" "$python_version" | sort -V | head -n1)" != "$required_version" ]; then
+    echo "❌ Python 3.10+ required. Found: $python_version"
+    exit 1
+fi
+
+echo "✓ Python $python_version"
+echo ""
+
+# Create virtual environment
+if [ ! -d "venv" ]; then
+    echo "Creating virtual environment..."
+    python -m venv venv
+    echo "✓ Virtual environment created"
+else
+    echo "✓ Virtual environment exists"
+fi
+
+echo ""
+
+# Activate virtual environment
+echo "Activating virtual environment..."
+if [[ "$OSTYPE" == "msys" || "$OSTYPE" == "win32" ]]; then
+    source venv/Scripts/activate
+else
+    source venv/bin/activate
+fi
+
+echo "✓ Virtual environment activated"
+echo ""
+
+# Install dependencies
+echo "Installing dependencies..."
+pip install --upgrade pip > /dev/null
+pip install -r requirements.txt
+
+echo "✓ Dependencies installed"
+echo ""
+
+# Install NOVA in development mode
+echo "Installing NOVA..."
+pip install -e .
+
+echo "✓ NOVA installed"
+echo ""
+
+# Initialize project
+echo "Initializing NOVA project..."
+python scripts/cli.py init
+
+echo ""
+echo "======================================"
+echo "✓ NOVA Setup Complete!"
+echo "======================================"
+echo ""
+echo "Next steps:"
+echo ""
+echo "1. Train tokenizer:"
+echo "   python scripts/cli.py tokenizer train --input data/toy_dataset/toy.txt"
+echo ""
+echo "2. (Optional) Download legal datasets:"
+echo "   python scripts/cli.py data build --source wikipedia-en"
+echo ""
+echo "3. Train model:"
+echo "   python scripts/cli.py train --size 125m"
+echo ""
+echo "4. Chat:"
+echo "   python scripts/cli.py chat cli"
+echo ""
+echo "For more info: cat README.md"
+echo ""