Building AI-powered trading systems — from reinforcement learning to local LLM inference. Supporter of open-source software and the communities that build it.
AI Trading Models — Transformer + PPO hybrid architectures for high-frequency scalping
Local LLM Integration — Running multi-agent AI systems fully offline with llama.cpp
Open-Source Tools — Pine Script strategies and Python frameworks for the trading community
Full Trading Systems — End-to-end pipelines from data collection to live execution
| Repo | Description | Stack |
|---|---|---|
| TPT | Scalping model for BTCUSDT (1m) — Transformer + PPO hybrid, 13.06 risk-reward ratio | Python · PyTorch · Stable-Baselines3 |
| PortfolioWatch | Telegram bot für Crypto-Portfolio-Tracking, Alerts, RSI/MACD Alerts | Python · aiogram · CoinGecko API |
| VAMOStrategy | Volatility-Adjusted Momentum Oscillator für TradingView Bitcoin Scalping | Pine Script v6 |
| OBV-RSI-VWAP-Strategy | OBV + RSI + VWAP Kombinations-Strategie für TradingView | Pine Script v6 |
I believe in open source — using it, improving it, and giving back.
| Project | Contribution |
|---|---|
| TradingAgents ⭐ 34k | Added llama.cpp local LLM support — run multi-agent stock analysis fully offline via .env config |
| OpenStock ⭐ 9.9k | Updated deps, fixed Inngest v4 API, force-dynamic for auth routes — resolved 28 vulnerabilities, migrated Inngest v3→v4 breaking changes |
Market Data → Feature Engineering → Model Training → Backtesting → Live Execution
(CCXT) (TA-Lib, pandas) (PyTorch, PPO) (custom env) (Binance API)
From raw kline data to a running strategy — built and maintained independently.
Python · PyTorch · Stable-Baselines3 · llama.cpp · LangChain · Pine Script v6
Transformer · PPO · TA-Lib · CCXT · Binance API · yfinance
Premium models & collaborations → tpt.requests@pm.me
Mastodon → @TPTBusiness@mastodon.social
⚠️ All content is for educational purposes. Past performance does not guarantee future results.