awesome-quant

Real-time and historical Hyperliquid and Lighter market data through REST, WebSocket, MCP, SDKs, CLI, and replay, with a permanent free tier.

Track institutional investor 13F holdings with AI-powered analysis, position change alerts, and filing summaries.

AI stock-research API returning structured analysis (investment thesis, valuation verdict, insider-signal read, earnings, bull-vs-bear, moat, watchlist ranking) for US equities from Polygon/Finnhub/FMP data. Optimized for LLM agents; free tier.

Natural-language strategy builder that generates, backtests and forward-tests an algorithm from a plain-English description, deploys it to the user's own broker account across forex, crypto, metals, indices, CFDs and equities on 15 brokers (Interactive Brokers, Binance, Bybit, Oanda, Coinbase, IC Markets, Pepperstone and others), and lets creators sell strategies on its AlgoNetwork marketplace without revealing the underlying logic. Permanent free tier: 2 backtests and 40 assistant messages a month, no payment details required.

Independent statistical assay office for trading signals and backtests: deflated Sharpe with cumulative trial accounting, probability of backtest overfitting (PBO/CPCV), leakage forensics, placebo tests against matched synthetic null worlds, and pre-registration with Merkle-anchored timestamps — deterministic, Ed25519-signed verdicts anyone can replay. Free demo; hosted API and MCP server. Methodology audit, not investment advice.

Local-first agent-native quant CLI with Optuna TPE optimization, walk-forward testing, anti-overfitting guards, and TradingView Pine v6 code generation. Free trial available.

Implementation of

All the answers for exercises from Advances in Financial Machine Learning by Dr Marco Lopez de Parodo.

Jupyter Notebooks and code for the book Artificial Intelligence in Finance (O'Reilly) by Yves Hilpisch.

Source code for Algorithmic Trading with Python (2020) by Chris Conlan.

A catalog of algorithmic trading libraries, frameworks, strategies, and educational materials.

Background and resources on Automatic Differentiation (AD) / Adjoint Algorithmic Differentitation (AAD).

US Treasury price quote math: parse and format 32nds quotes (105-16+), ticks, and basis points; zero dependencies.

A Python based library to model cashflow for structured product like Asset-backed securities (ABS) and Mortgage-backed securities (MBS).

This package includes pricing function for selected American call options with underlying assets that generate payouts.

Multi-factor quantitative stock analysis MCP server for US, HK, and CN A-share markets. Transparent 0-100 scoring from 40+ indicators. Listed on Official MCP Registry.

SOFR compounding-in-arrears per ARRC/ISDA conventions (lookback, observation shift, lockout) and the SOFR Index method; reproduces the NY Fed's published averages.

Credit Default Swap Functions.

Async Algorithmic Trading Engine.

Multi-agent LLM trading analysis where 12 AI agents (analysts, debaters, risk manager) debate stock picks in real-time, supporting US equities and China A-shares.

This is an execution engine for algo trading.

Library of 501 agentskills.io-format skills giving AI coding agents trading-infrastructure playbooks for order idempotency, look-ahead-bias elimination, kill switches, execution algorithms and point-in-time data, each with a standalone Python reference implementation and its own unittest suite.

MCP server returning composite crypto trade verdicts (direction, confidence, regime) across 5 perpetual-futures venues, with cross-venue funding-rate arbitrage and an on-chain Merkle-verified track record. Free tier.

MCP server wrapping the AlphaForge CLI for AI-agent-native backtesting, Optuna TPE optimization, and walk-forward testing of trading strategies from Claude Desktop, Cursor, or Claude Code.

Obtain pre market and after hours stock prices for a given symbol.

x402-paid crypto and market data API platform: 54 services, 97 endpoints, 37 MCP tools. Real-time prices, technical indicators, on-chain data, and market intelligence with on-chain USDC payments on Base.

AkShare is an elegant and simple financial data interface library for Python, built for human beings!

Python interface for retrieving real-time and historical prices from Alpaca API as well as trade execution.

CLI + MCP server for SEC 13F institutional holdings, Form 4 insider trading, and smart money convergence signals (tickers where hedge funds and company insiders are both buying). Free anonymous tier, no signup required.

A python wrapper for Alpha Vantage API for financial data.

Pre-analyzed financial news via REST API and MCP for AI agents: per-ticker impact and sentiment, a category, and a 1-10 relevance score on every story, plus structured SEC Form 4 insider data. Free tier, no card.

Sentiment analysis and report generation package for financial assets and securities utilizing GPT models.

LLM-powered A-share stock analysis via P2P agent collaboration. Technical analysis (MA60, volume-price patterns, golden eye), deep research reports using proprietary methodology, and market state summaries. Analysis logic stays private via Skill-as-API protocol.

Performance analysis of predictive alpha factors.

Performance analysis of predictive (alpha) stock factors.

AI skills for quantitative factor research: discover, evaluate, mine, backtest, and monitor factors through any AI coding assistant. Supports A-share, HK, and US markets.

Covariance matrix estimation via factor models.

Solutions for enhancing portfolio diversification and replications of seminal papers with R, most of which are discussed in one of the best investment references of the recent decade, Expected Returns: An Investors Guide to Harvesting Market Rewards by Antti Ilmanen.

The FactorAnalytics package contains fitting and analysis methods for the three main types of factor models used in conjunction with portfolio construction, optimization and risk management, namely fundamental factor models, time series factor models and statistical factor models.

ARCH models in Python.

Python package for timeseries analysis and manipulation.

High-performance ETF pattern matching via DTW with cosine pre-filtering. 43× DTW and 58× pattern-match speedup over pure Python using pybind11/C++20. Includes Jupyter notebook with full algorithm walkthrough.

Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.