In this tutorial you’ll deploy an AI crypto trading bot to your own VPS — the open-source Claude-powered bot from Part 1 — 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:
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 generatedml_models/
folder to the server withscp
. 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-commanddocker 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.