The NVIDIA Jetson Orin Nano Super is a compact edge AI platform with up to 67 TOPS in NVIDIA's published specification, a 1024-core Ampere GPU, and configurable power modes. It is designed for edge-inference workloads.
But turning a bare Jetson module into a functional AI assistant takes work. This guide covers everything — from choosing your hardware to having a fully working AI assistant on Telegram, WhatsApp, or Discord.
Why the Jetson Orin Nano for an AI Assistant?
Before diving into the build, let's talk about why the Jetson Orin Nano is the best platform for this:
Up to 67 TOPS of specified AI compute. TOPS is a peak hardware metric, not a direct measure of tokens per second or application quality. Real performance depends on the model, quantization, runtime, memory pressure, and power mode.
Low-power modes. At an illustrative 15W average and €0.25/kWh, continuous operation costs about €2.70/month. Compare that with the measured average draw of any alternative system; gaming-PC consumption varies too widely for one honest universal figure.
NVIDIA's CUDA and TensorRT ecosystem. Many popular frameworks and optimized runtimes support Jetson, but version compatibility, containers, custom operators, and ARM64 packages still need to be checked for each project.
8GB unified memory. CPU and GPU share the same memory pool. Quantized 7–8B models can fit in some configurations, but usable context length, speed, and stability depend on the rest of the running stack.
What You'll Need
Hardware
| Component | Recommended | Budget Option |
|---|---|---|
| Compute Module | Jetson Orin Nano Super 8GB (~$250) | Jetson Orin Nano 4GB (~$200) |
| Storage | 512GB NVMe SSD (~$40) | 256GB NVMe SSD (~$25) |
| Case | Any passive cooling case ($20-50) | 3D printed enclosure |
| Power Supply | 20W USB-C PD ($15) | Official NVIDIA PSU |
| Networking | Built-in WiFi 5 + Ethernet | Same |
Total DIY cost: $325-355
Software
- Ubuntu 22.04 (via JetPack 6.0)
- Node.js 20 LTS
- OpenClaw (source-available AI assistant platform)
- Chromium + Playwright (for browser automation)
- Whisper (speech-to-text, optional)
- Kokoro TTS (text-to-speech, optional)
Step 1: Flash JetPack OS
Download NVIDIA JetPack 6.0 from the NVIDIA developer site. Flash it to your NVMe SSD using the SDK Manager or balenaEtcher.
# After booting, update everything
sudo apt update && sudo apt upgrade -y
JetPack 6.0 includes CUDA 12.2, cuDNN 8.9, and TensorRT 8.6 — everything you need for AI inference right out of the box.
Step 2: Install Node.js
OpenClaw requires Node.js 20+. Install a current supported LTS version:
curl -fsSL https://deb.nodesource.com/setup_20.x | sudo -E bash -
sudo apt install -y nodejs
node --version # Should show v20.x
Step 3: Install OpenClaw
OpenClaw is the source-available AI assistant platform that ties everything together — messaging, browser automation, scheduling, memory, and AI model management.
# Install OpenClaw
npm install -g openclaw
# Run the setup wizard
openclaw setup
The setup wizard walks you through:
- Choosing your AI provider (Anthropic Claude, OpenAI GPT, Google Gemini, or local models)
- Connecting messaging platforms (Telegram, WhatsApp, Discord)
- Configuring browser automation
- Setting up voice pipeline (optional)
Step 4: Connect Telegram
The fastest way to interact with your AI assistant:
- Open Telegram and search for
@BotFather - Send
/newbotand follow the prompts - Copy the bot token
- Paste it into the OpenClaw setup wizard
That's it — send a message to your bot and your Jetson-powered AI responds.
Step 5: Set Up Browser Automation
This is where the Jetson really shines. Browser automation lets your AI assistant:
- Search the web and summarize results
- Fill out forms automatically
- Monitor websites for changes
- Take screenshots on command
- Extract data from any webpage
# Install Chromium and Playwright
npx playwright install chromium
OpenClaw handles the integration — just ask your AI to "search for flights to Rome" or "check if this product is in stock" and it opens a browser, navigates, and reports back.
Step 6: Voice Pipeline (Optional)
For a truly hands-free experience, set up on-device voice processing:
# Whisper for speech-to-text (runs on GPU)
pip3 install faster-whisper
# Kokoro for text-to-speech
pip3 install kokoro-tts
Both can run locally on the Jetson, so a fully local voice pipeline does not need to send audio to a cloud speech provider. Language coverage and latency depend on the selected model, version, and configuration.
Step 7: Configure for 24/7 Operation
Your AI assistant should run always-on:
# Create systemd service
sudo systemctl enable openclaw
sudo systemctl start openclaw
# Verify it's running
openclaw status
Set up automatic recovery so it restarts after power outages or crashes. The Jetson Orin Nano's 15W draw means you can run it on a small UPS for hours of battery backup.
What Can Your Jetson AI Assistant Actually Do?
Once everything is set up, here's what's possible:
Daily assistant tasks:
- "Summarize my unread emails"
- "What's on my calendar today?"
- "Set a reminder for 3 PM"
- "Find the cheapest flight from Berlin to London next weekend"
Browser automation:
- "Monitor this eBay listing and tell me if the price drops"
- "Fill out this job application form with my details"
- "Take a screenshot of my website's homepage"
Smart home integration:
- "Turn off the living room lights"
- "Set the thermostat to 20°C"
- Works with Home Assistant, MQTT, and REST APIs
Development tasks:
- "Review this pull request"
- "Run the test suite and tell me what failed"
- "Help me debug this Python script"
Performance Benchmarks
Real-world performance on the Jetson Orin Nano Super 8GB:
| Task | Speed | Notes |
|---|---|---|
| Qwen2.5 3B inference | ~23 tok/s | Conversational speed |
| Phi-3 Mini 3.8B inference | ~22 tok/s | Conversational speed |
| 7-8B class inference | ~10 tok/s | Usable, tight in 8GB |
| Whisper speech-to-text | Real-time | No perceivable delay |
| Kokoro TTS | Real-time | Natural-sounding output |
| Browser page load | 2-5 seconds | Full Chromium rendering |
| Web search + summary | 10-15 seconds | End-to-end |
Measured throughput figures and the full methodology behind them are published in our production ClawBox benchmark run. For whether a model can reliably drive an agent — a different question from raw speed — see the local LLM agent benchmarks.
For tasks requiring frontier model intelligence (complex reasoning, large context windows, multimodal work), OpenClaw supports BYOK (Bring Your Own Key) — route to the leading cloud models, OpenAI GPT, Anthropic Claude, or Google Gemini, while keeping your data, memory, and automation local.
The DIY vs Pre-Built Decision
Building from scratch takes 3-4 hours and costs $325-355. You learn a lot and have full control.
If you'd rather skip the assembly, ClawBox is a pre-built Jetson Orin Nano AI assistant with OpenClaw, browser automation, voice components, enclosure, power supply, and 512GB NVMe storage prepared in advance. The €549 hardware price includes the integrated system and guided onboarding; optional AI plans and external providers are separate.
Either way, the Jetson Orin Nano is the best platform for a personal AI assistant in 2026. Nothing else gives you 67 TOPS at 15W with full CUDA support.
Troubleshooting Common Issues
"Model loading is slow" — Make sure you're using the NVMe SSD, not a microSD card. NVMe is 10-50x faster for model loading.
"Browser automation crashes" — Increase swap space: sudo fallocate -l 4G /swapfile && sudo mkswap /swapfile && sudo swapon /swapfile
"WiFi keeps disconnecting" — Use Ethernet for always-on operation. WiFi power management can cause drops. Disable it: sudo iw dev wlan0 set power_save off
"Out of memory with larger models" — Stick to 7-8B parameter models. For larger models, use BYOK to route to cloud APIs.
What's Next?
Once your Jetson AI assistant is running:
- Install skills from ClawHub — 580+ community-built skills for everything from weather to stock trading
- Set up proactive monitoring — have your AI check your email, calendar, and websites automatically
- Connect multiple platforms — use one AI across Telegram, WhatsApp, and Discord simultaneously
- Build custom skills — Python-based skill system lets you automate anything
The Jetson Orin Nano is a practical foundation for a compact, always-on, local-first assistant when its memory and performance limits match your workload. Compare current board pricing, storage, cooling, power supply, setup time, and alternative mini-PC options before choosing.