Discover tools for AI investment research

Open-source crypto trading bot with a UI and DCA and grid strategies

It uses one architecture for research, deterministic simulation, and live execution, with Python controlling strategy logic.

It represents financial contracts and their valuation in a structured way, such as defining options from an underlying asset and expiry.

Its Flask backend and React frontend display DataFrames, Series, and index objects, with integration for Python terminals and notebooks.

AI-oriented Kalshi CLI with probability estimates, order-book edge, Kelly sizing, and risk gates

It provides order-flow charts, footprint and L2 heatmap views, volume bubbles, and selected market-flow analytics.

It uses mathematical optimization to allocate portfolios across bonds, commodities, crypto, currencies, funds, and stocks.

It provides financial-instrument and model components for building pricing, trading, and risk-analysis applications.

It supports multiple data feeds, strategies, and timeframes, with indicators, broker simulation, and charting.

Build machine-learning-based quantitative research flows that bring data preparation, feature and model experiments, and strategy evaluation into one research platform. Start with the project examples, then adapt them to data you are authorized to use and your own hypotheses.

Who it suitsResearchers and developers comfortable with Python who want to run machine-learning quant experiments.

Coding required: Coding required

It supports time-, volume-, or custom information-based aggregation rules and extensible candle components.

It includes a strategy-optimization workflow; the repository notes that later development shifted to TensorTrade.

It includes equities, ETFs, funds, indices, currencies, cryptocurrencies, and money markets for filtering and lookup.

Crypto trading decision project using ensemble machine-learning methods

Connect proprietary, licensed, or public financial sources to downstream research applications. It can serve as data infrastructure that prepares and exposes data to Python workflows, research interfaces, or API consumers, especially when a team is building its own data flow.

Who it suitsData engineers connecting financial sources for internal research applications.

Coding required: Coding required

The README describes configurable copy-trading and token-sniping flows, along with sell-logic settings.

OpenBB research copilot for dashboard data with SQL, cited answers, and optional MCP

Build and run automated trading bots using connectors for centralized or decentralized venues and strategies configured by the user. Developers can explore venue integrations and deployment patterns, checking the current documentation for the exact supported venues.

Who it suitsDevelopers and algorithmic traders who want to configure venue connectors and build automated strategies.

Supports live execution

It provides financial models and numerical tools for quantitative research and pricing tasks in TensorFlow workflows.

Self-hosted agent for Polymarket, Kalshi, Opinion, and Binance; paper or shadow mode is default