Tag: quant-trading

Multi-agent investment research framework where fundamental, sentiment, news and technical analysts, bull and bear researchers, a trader and risk managers debate a stock and produce a report and rating. Covers US, Hong Kong and A-shares. Needs Python and an LLM API key; not investment advice.

Multi-agent simulated hedge fund: agents modeled on investors like Buffett and Munger work with quant and risk modules to analyze stocks, with backtesting. Good for teaching investment frameworks. Needs Financial Datasets and model API keys; no real trading, not investment advice.

Open-source crypto trading framework: download market data, backtest and optimize strategies, and paper trade from the CLI while agents iterate on strategies. Docker recommended; strategies need Python and live trading needs exchange API keys. Backtests don't guarantee returns.

Microsoft's open-source AI quant investment research platform: the qrun command runs dataset building, model training, backtesting and evaluation from a YAML config, with many benchmark models. The official dataset is paused, so prepare market data per the README first.

Quant trading plugin from the wshobson/agents marketplace: quant analyst and risk manager subagents plus backtesting and risk metrics skills for strategy backtests, portfolio optimization and risk measures like VaR, Sharpe ratio and max drawdown. Needs local Python; not investment advice.

Trading research agent from HKU's HKUDS whose MCP server offers 70+ tools for quotes, financials, backtesting and research across A-shares, Hong Kong and US stocks and crypto. Needs local Python; HK, US and crypto research need no API key. For research only; not investment advice.

Real-time quotes for stocks, crypto, forex and futures, top gainers/losers and volume-spike screens, multi-timeframe technical analysis and strategy backtesting. No TradingView account or API key needed; community project not affiliated with TradingView.

Plugin marketplace for investment research: six plugin groups covering yfinance market data, earnings previews and recaps, DCF valuation, option payoff charts, ETF premiums, read-only news from X, Discord and other social sources, and TradingView data. Research only, not investment advice.

Finance skills for investment research: pulls quotes and financials via yfinance for DCF valuation, earnings previews and recaps, option payoff charts, and correlation and liquidity analysis, plus read-only feeds from Twitter, Discord and more. For research reference only.

Finance skills for US, Hong Kong and China A-share markets: news from 10+ sources, quotes and fundamentals, sentiment analysis, time-series forecasts, signal tracking, impact-chain diagrams and reports. Needs Python; some skills download PyTorch models. Not investment advice.

Trading workflow skills for time-constrained individual investors: market breadth and regime assessment, VCP stock screening, position sizing, trade journaling and reviews, and backtest critique. The starter path needs no paid data; screening skills need FMP or similar subscriptions.

Official Korea Investment & Securities MCP: quotes Korean and overseas stocks, futures, options and bonds, manages accounts and places orders (paper trading supported), plus API doc and sample search. Needs an account and App Key; runs via Docker or uv. Orders use real money.

Binance's official crypto skills: token info and candles, trending rankings, smart-money signals, wallet holdings and token security audits, plus spot and futures trading via binance-cli. Needs Node.js 22+; trading needs a Binance API key. Volatile and regionally regulated; not investment advice.

Lets agents use Alpaca's trading API for US stocks, options, crypto and bond quotes and news, place orders, and manage positions and watchlists. Maintained by Alpaca; needs an API key and uses paper trading by default.

Longbridge's official CLI: real-time HK and US quotes, candles, options and warrants, news and filings, positions and cash, and order placement (previewed by default, executed only on confirmation). All commands output JSON for agents. Needs a Longbridge account and browser login.

Connects AI assistants to MetaTrader 5 to check balances, quotes and positions in plain language, and to place, modify and close orders. For forex and CFD traders. Needs the MT5 terminal on Windows and a trading account; start with a demo account, as trading carries risk of loss.

Kraken exchange's official CLI: quotes and trading for crypto, tokenized US stocks, forex and futures, with a built-in MCP server and paper trading that need no API key. Experimental; live trading needs a Kraken account and API key and uses real money, so check local rules and confirm trades.

Stock analysis MCP for individual investors: quotes via yfinance, technical indicators such as RSI and MACD, screening strategies, a portfolio tracker and a trade journal. Core tools need no API key; backtesting and deep-research extensions are optional.

The MCP server (okx-trade-mcp) from OKX's official trading kit: market data and technical indicators, spot and derivatives orders, algo orders, account, earn, trading bots and news. Runs locally; trading tools need an OKX API key, market data needs no auth, and a read-only mode is available.

68 trading and quant skills focused on crypto and DeFi: market and on-chain data, technical indicators, backtesting, position sizing and risk, prediction markets, and tax tools for cost basis and wash sales. Most need Python and data API keys (often free tiers); get expert review.

Official FinLab quant skill: lets agents use FinLab data (mainly Taiwan stocks, plus US, Japan, Korea and Hong Kong) to write stock-picking strategies, run backtests and analyze factors. Needs a FinLab account (free tier has a daily data cap), Python 3.10+ and uv. Not investment advice.

Options trading skills for retail investors: scans, Greeks, spread win rates, PMCC and covered call screens, earnings risk alerts and PDF reports; with IBKR connected, analyzes positions and finds rolls. Needs Python (uv); also runs as an MCP in Claude Desktop. Get expert review.

QuantConnect's official CLI drives the open-source LEAN engine locally or in the cloud to download data, backtest and optimize quant strategies and deploy them live. Requires a paid-tier QuantConnect organization; strategies in Python or C#; local runs need Docker. Get expert review.

Self-hosted family office system: 11 specialist agents use tested Python calculators for risk, Monte Carlo and backtests, store broker CSVs in local SQLite and gate purchases with guardrails; mostly US equities. Needs Python 3.12+, uv and CLI comfort. Educational only, not investment advice.