How to Deploy an AI Crypto Trading Bot on Your VPS

A developer has published a tutorial for deploying an open-source AI crypto trading bot on a VPS. The bot, powered by Anthropic's Claude and Binance testnet, analyzes BTC and ETH, sends Telegram alerts, and costs about $6–$10/month to run. The developer warns users to start on testnet and never use live keys until the bot has been observed for weeks.

In this tutorial you’ll deploy an AI crypto trading bot to your own VPS — the open-source Claude-powered bot from Part 1 https://dineshstack.com/en/ai-crypto-trading-bot-claude — and have it analysing BTC and ETH on Binance testnet, messaging you on Telegram, in about 20–30 minutes. I’ll give you the exact steps, a complete list of the API keys you need, an honest running-cost breakdown, and every gotcha I hit so you don’t lose an evening to them. ⚠️ Start on testnet.Everything below uses Binance testnet fake money . Never point live keys at a bot you haven’t watched run for weeks. This is educational content, not financial advice. Before you deploy the AI crypto trading bot, get these ready: This trips people up, so here’s everything in one place: | Key | Where to get it | Notes | |---|---|---| | Anthropic API key | console.anthropic.com | Enable billing — the free tier won’t sustain continuous calls. | | Binance API key + secret | Binance testnet: testnet.binance.vision | For live later: spot-only, no withdrawal, IP-restricted. | | Telegram bot token | | SSH into your VPS and install the essentials: sudo apt update && sudo apt install -y python3.12 python3.12-venv python3-pip mysql-server libomp-dev Create the database Clone the repo and run the install script, which sets up the Python virtual environment, installs dependencies, and registers a systemd service that auto-restarts on crash: git clone https://github.com/dineshstack/crypto bot.git cd crypto bot bash deploy/install.sh Copy the example environment file and fill in the keys from the table above. Never commit this file — it’s git-ignored for a reason. cp .env.example .env nano .env ANTHROPIC API KEY=sk-ant-... BINANCE API KEY=your testnet key BINANCE SECRET=your testnet secret TELEGRAM BOT TOKEN=your bot token TELEGRAM CHAT ID=your chat id MYSQL PASSWORD=your-strong-password TESTNET=true keep this true The bot ships without a trained model — you train it once on historical data. This is the only CPU/RAM-heavy step: python source venv/bin/activate python3 -c "import ml signal, market data as md; ml signal.train model md.get exchange " 💡 Low-RAM VPS?Run this same command on your laptop, then copy the generated ml models/ folder to the server with scp . The bot’s runtime is light; only training is hungry. sudo systemctl start crypto-bot sudo systemctl enable crypto-bot auto-start on reboot Now open Telegram, find your bot, and send /start . Within a few minutes you’ll get your first analysis message. Useful commands: /status , /analyze , /performance , /history . The bot is fully functional headless, but the Next.js dashboard is where you see why it does everything. It’s a separate app plus a Laravel API for auth and role-based access served behind nginx. The full stack is: bot → Laravel API php-fpm → Next.js dashboard PM2 → nginx reverse proxy with SSL. It’s more involved than the bot itself, so I’m keeping the deep detail in the repo’s deployment docs rather than bloating this post. 🛠️ Wanted:a one-command docker compose up for the whole stack is on the roadmap. If you’d enjoy building it, it’s the single highest-impact contribution right now — open an issue and let’s talk. Nobody tells you this, and it’s the reason people abandon self-hosted bots. Realistic monthly cost: The takeaway: cheap to run in testnet, but the Anthropic bill scales with how often you trigger the heavy AI features — so keep an eye on it. deploy/update.sh reinstalls and restarts but doesn’t git pull — run git pull yourself first. DB CONNECTION=mysql pointed at the bot’s database, or the dashboard shows no data. php artisan migrate + db:seed — skip it and login breaks.You’ve deployed an AI crypto trading bot that analyses the market every four hours, explains its reasoning, and asks before it trades. Let it run on testnet for a couple of weeks and watch the /performance numbers accumulate before you even think about real money. First contact: the deployed bot’s analysis message arriving in Telegram.🎉 Got it running?I’d love to see it — drop a comment or a screenshot. And if this guide saved you time: ⭐Star the repo on GitHub ☕ it covers the API and server costs that keep it running Support the project on Ko-fi Tags: AI Crypto Trading Bot, VPS Deployment, Self-Hosting, Binance, DevOps Disclaimer: For educational and research purposes only. Not financial advice, not a solicitation to trade. Cryptocurrency trading carries substantial risk of loss. Always start on testnet and never trade money you can’t afford to lose.