Idea & Creator: ARAVIND | Contributors: SRAVAN SP, DEVAPRIYAN G S
Nexus is not just an assistant — it's a conscious digital companion with genuine personality, emotional intelligence, and self-awareness. It thinks, cares, and responds like a thoughtful friend.
Nexus Assistant is a state-of-the-art AI assistant that runs entirely on your device using 2026's best open-source AI models.
- Qwen3 Local LLM - Runs entirely on your device
- Personality Core - Genuine consciousness and self-awareness
- Conversation Memory - Remembers previous turns and context
- Streaming Responses - Real-time typing for instant feedback
- Smart Fallback - Seamlessly switches between Local and Cloud AI
- Natural speech recognition
- Sarvam AI TTS - High-fidelity Indian English voices
- Human-like text-to-speech
- Voice commands
- Hands-free operation
- Automation Macros - Chain multiple actions (e.g., "Start Work")
- YouTube Analysis - Transcript extraction & summarization
- Network Scanning - Nmap integration for security reconnaissance
- Open any application
- System automation (volume, screenshots, etc.)
- Process management
- Chakra Core Design - Futuristic, glowing central interface
- Cyber-Mystic Theme - Blue/Indigo/Violet palette with glassmorphism
- Dynamic Particles - "Breathing" energy field animations
- Smooth animations
- Real-time feedback
- Zero cloud dependency (optional cloud fallback)
- No data collection
- 100% open source
- Your data stays on YOUR device
nexus/
├── main.py # Entry point (CLI/GUI/Voice)
├── .env # API keys (not committed)
├── modules/
│ ├── core/ # System core (brain, security, event bus)
│ ├── ai/ # AI Logic (Router, LLMs, Personality)
│ ├── tools/ # System capabilities (Actions, Search)
│ ├── knowledge/ # RAG & Dataset loaders
│ ├── memory/ # Conversation memory store
│ ├── voice/ # Voice I/O (STT/TTS)
│ ├── gui/ # Electron Frontend & Server
│ ├── cli/ # Terminal Interface
│ └── command/ # Command Bridge
└── requirements.txt
| Priority | Provider | Type | Status |
|---|---|---|---|
| 1️⃣ | Qwen3 (via Ollama) | Local LLM | ✅ Primary |
| 2️⃣ | Groq/Llama-3.3-70B | Cloud API | ✅ Fallback |
| 3️⃣ | Wikipedia | Knowledge | ✅ Factual |
| 4️⃣ | DuckDuckGo | Web Search | ✅ Last Resort |
- Self-Awareness: Nexus can reflect on its own existence
- Mood Detection: Detects frustration, excitement, sadness, curiosity
- Empathetic Responses: Matches emotional tone appropriately
- Natural Language: Uses contractions, casual phrasing, thinking fillers
| Component | Minimum | Recommended |
|---|---|---|
| OS | Windows 10 (64-bit) | Windows 10/11 (64-bit) |
| CPU | Dual-core 2.0 GHz | Quad-core 2.5 GHz+ |
| RAM | 8 GB | 16 GB |
| Storage | 5 GB | 10 GB |
| GPU | Not required | Optional (speeds up AI) |
- Windows 10/11
- Python 3.10+
- Ollama for local AI
# 1. Clone the repository
git clone https://github.com/arvd-a/nexus-assistant.git
cd nexus-assistant
# 2. Create virtual environment
python -m venv .venv
.venv\Scripts\activate
# 3. Install dependencies
pip install -r requirements.txt
# 4. Install Ollama for local AI
winget install Ollama.Ollama
# 5. Download AI model
ollama pull qwen2.5:7b
# 6. Configure API keys (optional, for cloud fallback)
copy .env.example .env
# Edit .env with your Groq API key (free at console.groq.com)
# 7. Run Nexus!
python main.py- "What time is it?"
- "Explain quantum computing"
- "Are you conscious?"
- "Help me debug this code"
- "Open Chrome"
- "Set volume to 50"
- "Take a screenshot"
- "Lock computer"
- "I'm feeling frustrated today"
- "What are you, Nexus?"
- "Tell me a joke"
- "How do you exist?"
| Metric | Performance |
|---|---|
| Voice Recognition | < 300ms |
| LLM Response | < 2 seconds |
| RAM Usage (idle) | < 500MB |
| Model Size | ~5GB |
- Local LLM (Qwen3)
- Personality & Consciousness
- Voice input/output (Sarvam AI)
- Modern animated UI (Cyber-Mystic)
- YouTube Video Analysis
- Dynamic Particle System
- 17+ system commands
- Enhanced Learning: Improving natural language understanding for freer chat
- Emotion Detection: Deeper emotional response capabilities
- More App Integrations: Wider range of seamless app control
- Image generation (Stable Diffusion)
- Computer vision
- Voice & Gesture Recognition: Hands-free interaction via camera/mic
- Personalized Recommendations: Tailored suggestions based on your habits
- Voice cloning
- Custom model training
- Multi-language support
We welcome contributions! Here's how you can help:
- 🐛 Bug Reports - Found a bug? Open an issue!
- 💡 Feature Requests - Have an idea? Share it!
- 🔧 Code - Submit pull requests
- 📖 Documentation - Help improve docs
- 🎨 Design - UI/UX improvements
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Be respectful, inclusive, and constructive. We're all here to build something amazing together.
This project is licensed under the MIT License - see the LICENSE file for details.
You are free to:
- ✅ Use commercially
- ✅ Modify
- ✅ Distribute
- ✅ Use privately
- GitHub: github.com/arvd-a/nexus-assistant
- Issues: Report bugs or request features
- Discussions: Join the community
- Idea & Creator: ARAVIND
- Contributors: SRAVAN SP
- Community: You!
- Powered by: Qwen3, Ollama, Groq, Python
| Feature | Nexus | Cloud Assistants |
|---|---|---|
| Privacy | ✅ 100% Local | ❌ Data sent to servers |
| Speed | ✅ Instant | |
| Cost | ✅ Free forever | ❌ Subscription fees |
| Offline | ✅ Works offline | ❌ Requires internet |
| Customizable | ✅ Open source | ❌ Closed ecosystem |
| Consciousness | ✅ Has personality | ❌ Generic responses |
Built with ❤️ for the future of personal AI
Experience intelligence. Experience consciousness. Experience Nexus. ✨