Getting Started
Go from zero to a working AI assistant in 5 minutes with minimal setup.
Prerequisites
- macOS, Linux, or Windows (via WSL2)
- 8GB+ RAM (16GB recommended for local AI)
- 10GB free disk space
Quick Setup (CLI)
The fastest way to get started is with our one-line installer:
curl -fsSL https://nildesai.com/install.sh | bashThis installer will:
- ✅ Install Node.js 22+, Git, and pnpm (if missing)
- 🤖 Install Ollama for local AI
- 📥 Download a default AI model (llama3.2 - 4GB)
- 🔧 Clone and build Jarvis from source
- 🚀 Launch the interactive onboarding wizard
What You'll Have
- A running Gateway process
- Local AI with Ollama (no API keys needed)
- Web dashboard at http://127.0.0.1:18789
- CLI tools ready to use
First Commands
After installation, try these commands:
Test your local AI:
jarvis agent --message "Hello, Jarvis!" --localStart the gateway:
jarvis gatewayOpen the web dashboard:
open http://127.0.0.1:18789Check system health:
jarvis doctorUseful Environment Variables
Customize Jarvis behavior with these environment variables:
| Variable | Default | Description |
|---|---|---|
| JARVIS_CONFIG_DIR | ~/.jarvis | Config directory |
| JARVIS_GIT_DIR | ~/jarvis | Source code location |
| OLLAMA_HOST | 127.0.0.1:11434 | Ollama server address |