Alpacaruns is a safety-first autonomous trading system that combines LLM-powered agents with a deterministic mixture-of-experts strategy engine. It analyzes market data through technical, sentiment, trend, momentum, volatility, volume, pairs-trading, breakout, and seasonality signals, then aggregates specialist decisions using performance-weighted voting and volatility-regime awareness. Every proposed trade passes through a shared fail-closed risk validator, regardless of whether it originates from an AI agent, automated strategy, or manual command. The system enforces position and portfolio limits, confidence and factor thresholds, trading-session rules, options constraints, and daily, weekly, and total drawdown kill switches. Orders execute through Alpaca’s paper-trading API, with the AI execution agent using the official Alpaca MCP server. All fills are streamed, deduplicated, and recorded in a JSONL trade journal for reliable P&L reporting. Model providers are pluggable, supporting local llama.cpp-compatible models, Gemini, and Oxlo.ai without code changes. Alpacaruns is intentionally paper-only and prioritizes transparent controls, explainable decisions, adaptive expert weighting, and safe failure over aggressive automation. Its options overlay gracefully falls back to equities when unavailable on free-tier market data plans.
Category tags: