Y-Research-SBU/QuantHarness

Official Repository for 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.

Related

  • Project
    TauricResearch/TradingAgents

    A multi-agent LLM framework that simulates a professional trading firm's workflow to analyze market conditions and inform trading decisions.

  • Project
    gameworkerkim/vibe-investing

    A comprehensive AI-driven investment ecosystem that combines multi-LLM agentic pipelines, quant regime classifiers, and corporate disclosure monitors to optimize financial decision-making.

  • Project
    hsliuping/TradingAgents-CN

    TradingAgents‑CN Community Edition is a hybrid‑licensed platform that uses multiple LLM‑driven agents to research Chinese A‑share stocks. It offers debate‑style single‑stock analysis, natural‑language screening, a paper‑trading sandbox, and free learning courses. Built with FastAPI, Vue 3, MongoDB, and Redis, the core engine is Apache‑2.0 while the application layer is source‑available for non‑commercial use.

  • Project
    AI4Finance-Foundation/FinRobot

    FinRobot is an open‑source, multi‑agent AI platform for high‑stakes financial analysis. It separates deterministic Python‑based valuation (DCF, LBO, etc.) from LLM‑generated narration, orchestrates specialized agents (data, analysis, modeling, synthesis, reporting, plus debate agents), and ships three versions: a production desktop app (V2), a self‑hosted web report generator (V1), and an educational AutoGen library (V0). The system integrates multiple market data sources, provides 56 analyst playbooks, and can be run locally via a CLI, a browser UI, or a native Tauri desktop client.

  • Project
    charliedream1/ai_quant_trade

    The repository is a genuine AI‑focused quantitative‑trading platform, offering data pipelines, alpha‑mining tools, AI/LLM strategy examples, live‑trading helpers, and a curated resource hub.