olaxbt/ai-market-maker

Agentic AI Hedge Fund OS (AIMM)

What it solves

AI-Market-Maker provides a professional, hedge-fund-style trading stack for cryptocurrency. It moves beyond simple trading bots by implementing a multi-agent system with strict risk governance, quant-grade backtesting, and full traceability to ensure trading decisions are disciplined and reproducible.

How it works

The system uses a LangGraph orchestration layer to manage a workflow of specialist AI trading agents (acting as "trading desks"). The process follows these steps:

  1. Market Scan: Tier-0 desks (Technical Analysis, Macro, Pattern Recognition, etc.) analyze data.
  2. Risk & Debate: The system evaluates risk context and allows for optional debate between desks.
  3. Signal Arbitration: A weighted mathematical approach, optionally enhanced by LLM-based Chain-of-Thought reasoning, determines a BUY, SELL, or HOLD intent.
  4. Portfolio & Execution: A proposal is generated and must pass through a "Risk Guard"—a hard veto layer that can block any trade before it is executed on venues like the Binance Testnet.

Who it’s for

This project is designed for crypto hedge funds, quantitative traders, and developers looking to build agentic trading systems with built-in risk management and rigorous backtesting frameworks.

Highlights

  • Hard Risk Governance: A dedicated Risk Guard with final veto power over all executions.
  • Multi-Agent Architecture: Specialist desks for news sentiment, whale behavior, liquidity flow, and macro-economic data.
  • Quant Discipline: Built-in benchmarks against buy-and-hold strategies and detailed performance metrics (Sharpe, Sortino).
  • Reproducible Data: Uses pinned historical data (OHLCV, funding, macro) with SHA256 manifests to ensure backtests are consistent.
  • Modern Tooling: Includes a Next.js dashboard for telemetry, traces, and research results.

Related

  • Project
    EthanXiang777/circuit-framework

    A multi-agent AI research and paper-trading framework for cryptocurrency that uses specialized analysts and a deterministic risk engine to simulate trades.

  • Project
    TauricResearch/TradingAgents

    A multi-agent LLM framework that simulates a professional trading firm's workflow to analyze markets and make informed 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
    virattt/ai-hedge-fund

    A proof-of-concept AI-powered hedge fund framework for simulating and backtesting AI-driven trading decisions using financial data and LLMs.

  • Project
    KylinMountain/TradingAgents-AShare

    A multi-agent AI system that simulates a professional investment research institution to provide deep analysis and trading suggestions for the A-share market.