DEV Community: ILIA CHERKASOV

I built a Multi-Agent AI Trading Signal Bot for OKX Futures in Python

ILIA CHERKASOV — Wed, 20 May 2026 18:23:05 +0000

For the past few weeks I've been building something more ambitious than my usual bots — an AI-powered crypto futures signal system for OKX.

Not an auto-trader. A smart analyst that thinks, then asks you to decide.

What it does

torgBot scans 60 OKX perpetual swap pairs every 5 minutes, detects chart patterns, scores them 0–10, and sends a Telegram signal with:

Candlestick chart PNG (mplfinance)
Entry price, Stop Loss, TP1 / TP2 / TP3
R:R ratio, funding rate, Fear & Greed index
Full AI analysis text

The multi-agent architecture

This is the part I'm most proud of. Four agents work together:

News Agent — checks if any crypto news could impact the trade
Whale Watcher — detects large player activity via OI and funding
Analyst Agent — scores the pattern quality (0–10)
Orchestrator — combines all inputs and makes the final GO/SKIP call

# Simplified orchestrator logic
decision = orchestrator.evaluate(
    pattern_score=analyst.score,
    whale_signal=whale_watcher.signal,
    news_risk=news_agent.risk_level,
    market_context={"btc_trend": btc, "fg": fear_greed}
)

Pattern detection (5 types)

Double Bottom / Double Top
Head & Shoulders
Bull / Bear Flags
ABCD Pattern

Each pattern gets scored on: R:R ratio · Volume · HTF confirmation · Fibonacci levels · Open Interest · Funding Rate

Real-time dashboard

Built a WebSocket dashboard (port 8766) that shows all agents working in real time — which pairs are being scanned, what each agent decided, and why.

Tech stack

Python 3.11, aiogram 3.x
ccxt → OKX perpetual swaps
Cerebras qwen-3-235b (LLM reasoning)
Google Gemini (visual chart analysis)
mplfinance + matplotlib (chart generation)
APScheduler (scan every 5 min)
aiosqlite (trade tracking)

Example signal output

СЕТАП: EWY/USDT PERP · 4H Long
Pattern: Double Bottom (forming) | Score: 9.2/10

Price:     176.9200
BUY LIMIT: 173.9600  (-1.7%)
Stop:      171.1766  (-1.6%)
TP1:       192.1000  (+10.4%)
TP2:       203.3105  (+16.9%)
TP3:       221.4505  (+27.3%)

R:R 1:6.5 | Horizon: 5–14 days
F&G: 25 — Extreme Fear | Mode: Trend

AI: Pattern confirmed. Analyst recommends entry.
Market in trend mode, no news or whale risks.

Analytics. Decision is yours.

Key design decision

The bot never trades automatically. It analyzes, scores, explains — and always ends with: "Decision is yours."

I believe AI should assist traders, not replace their judgment.

What's next

Backtesting module
Multi-exchange support (Binance, Bybit)
Portfolio tracker integration

The full source is available on Gumroad if you want to run your own instance: torgBot OKX

Happy to answer questions about the architecture or any part of the implementation!

I built a Telegram Broadcast Bot in Python — send messages to all subscribers instantly

ILIA CHERKASOV — Mon, 18 May 2026 19:39:17 +0000

I built a mass messaging bot for Telegram in Python. Business owners can send updates, promotions, and news to ALL subscribers with one click!

What it does

Perfect for shops, restaurants, bloggers, gyms:

📢 One-click subscribe / unsubscribe for users
📨 Broadcast text, photos, videos, documents
📊 Delivery stats (sent / failed / success rate)
👥 Subscriber list with usernames
📋 Broadcast history
🔔 Admin notified on every new subscriber
💾 No database needed — simple JSON file

Tech stack

Python 3.10+
python-telegram-bot v20 (async)
JSON for storage

Setup takes 5 minutes

Create bot via @botfather
Add token to .env file
pip install -r requirements.txt
python bot.py

Get the source code

👉 https://cherkasov1.gumroad.com/l/telegram-broadcast-bot

Happy to answer any questions in the comments!

I built a Telegram Shop Bot in Python — full e-commerce in Telegram

ILIA CHERKASOV — Mon, 18 May 2026 19:37:37 +0000

I built a fully functional e-commerce shop bot for Telegram in Python. No website needed — customers browse, add to cart, and order right in Telegram!

What it does

Perfect for online stores, local shops, dropshipping:

🛍 Product catalog with categories
🛒 Shopping cart — add, remove, clear
✅ Full checkout flow (name, phone, address)
📦 Order history for customers
🔧 Admin panel — view & confirm orders
🔔 Instant admin notification on every order
➕ Add/remove products without coding
💾 No database needed — simple JSON file

Tech stack

Python 3.10+
python-telegram-bot v20 (async)
JSON for storage

Setup takes 5 minutes

Create bot via @botfather
Add token to .env file
pip install -r requirements.txt
python bot.py

Get the source code

👉 https://cherkasov1.gumroad.com/l/telegram-shop-bot

Happy to answer any questions in the comments!

I built a Telegram Booking Bot in Python — here's how it works

ILIA CHERKASOV — Mon, 18 May 2026 19:32:16 +0000

I recently built a fully functional Telegram appointment booking bot in Python and wanted to share how it works.

What it does

Perfect for barbershops, salons, doctors, tutors — any service business:

📅 Browse services with prices & duration
🗓 Choose date from next 7 working days
⏰ Pick available time slots (booked slots hidden automatically)
✅ Booking confirmation with full summary
🔧 Admin panel with daily schedule
🔔 Instant admin notifications on every booking
❌ Cancel bookings
💾 No database needed — simple JSON file

Tech stack

Python 3.10+
python-telegram-bot v20 (async)
JSON for storage

Setup takes 5 minutes

Create bot via @botfather
Add token to .env file
pip install -r requirements.txt
python bot.py

Get the source code

Full source code available here:
👉 https://cherkasov1.gumroad.com/l/telegram-booking-bot

Happy to answer any questions in the comments!