An AI-powered desktop assistant inspired by Iron Man's Jarvis, built with Python.
Voice-controlled, extensible, and capable of managing your PC through natural language.
- Voice Recognition — Real-time speech-to-text via custom STT engine
- AI Brain — GPT-powered conversational intelligence with memory and personality
- Smart Intent Classification — Offline intent classifier for instant command routing
- App Control — Open, close, and manage Windows applications by voice
- Spotify Integration — Play songs, albums, control playback hands-free
- Browser Automation — Search Google/YouTube, manage tabs
- Camera Control — Open camera, take photos, record video
- Screen Control — Screenshots, screen management
- Notes Mode — Dictate text directly into Notepad
- Weather & Scheduling — Check weather, manage schedules and alarms
- System Controls — Volume, brightness, window management
- WhatsApp Automation — Send messages via WhatsApp
Jarvis/
├── Automation/ # App launching, browser, music, scrolling, tab control
├── Brain/ # GPT brain, intent classifier, personality engine
├── Data/ # Dialogue data and response templates
├── Features/ # Brightness, volume, IP lookup, jokes, health checks
├── NetHyTechSTT/ # Speech-to-text listener engine
├── New/ # Data fetching utilities
├── Real_Time/ # Real-time Google search modules
├── TextToImage/ # AI image generation
├── TextToSpeech/ # TTS engine (pyttsx3-based)
├── Time_Operations/ # Scheduling, alarms, time-based alerts
├── Tools/ # System tools (apps, browser, camera, clipboard, etc.)
├── Vision/ # Computer vision modules
├── Weather_Check/ # Weather lookup
├── Whatsapp_automation/# WhatsApp messaging
│
├── jarvis.py # Entry point — boots all threads
├── co_brain.py # Core command router and voice loop
├── internet_check.py # Online/offline detection
├── Alert.py # Desktop notification alerts
├── ui.py # UI interface
├── setup.py # Dependency installer
├── requirements.txt # Python dependencies
├── LICENSE # GPL-3.0 License
└── .gitignore
- Python 3.11+
- Windows 10/11
- Microphone for voice input
# Clone the repository
git clone https://github.com/abhilashg-cell/Jarvis-0.1.git
cd Jarvis-0.1
# Create virtual environment
python -m venv .venv
.venv\Scripts\activate
# Install dependencies
pip install -r requirements.txtCreate a .env file in the project root:
OPENAI_API_KEY=your_openai_api_key_herepython jarvis.py| Component | Technology |
|---|---|
| Language | Python 3.11+ |
| AI Engine | OpenAI GPT API |
| Speech-to-Text | Custom STT (NetHyTechSTT) |
| Text-to-Speech | pyttsx3 |
| Vision | OpenCV |
| Browser | Selenium + ChromeDriver |
| Desktop Control | pyautogui, psutil, pycaw, comtypes |
| Notifications | winotify |
This project is licensed under the GNU General Public License v3.0 — see the LICENSE file for details.
Abhilash G
GitHub