Y-Research-SBU/QuantHarness

What it solves

QuantHarness is designed to automate the complex process of technical analysis for high-frequency trading. It replaces manual chart reading and indicator calculation with a multi-agent system that can process both raw price data and visual charts to generate actionable trade directives.

How it works

The system uses a multi-agent architecture built with LangChain and LangGraph, requiring a multimodal LLM capable of image analysis. It employs four specialized agents:

• Indicator Agent: Calculates technical metrics like RSI, MACD, and Stochastic Oscillators from OHLC data.
• Pattern Agent: Generates price charts and analyzes visual shapes to identify familiar chart patterns.
• Trend Agent: Creates annotated K-line charts with trend channels to quantify market direction and consolidation zones.
• Decision Agent: Synthesizes the reports from the other agents to recommend specific LONG or SHORT positions, including entry/exit points and stop-loss thresholds.

Who it’s for

This tool is intended for traders and researchers interested in AI-driven market analysis across stocks, cryptocurrencies, commodities, and indices.

Highlights

• Multimodal Analysis: Combines numerical technical indicators with visual chart recognition.
• Comprehensive Tooling: Includes a Flask-based web interface for real-time data fetching via Yahoo Finance.
• Flexible LLM Support: Compatible with OpenAI, Anthropic, Qwen, and MiniMax models.
• Customizable Timeframes: Supports analysis from 1-minute intervals up to daily charts.