FinRL is a reinforcement learning framework designed for the development, training, and backtesting of automated trading strategies. It functions as a quantitative finance toolkit that integrates deep learning algorithms with financial market simulations to address complex portfolio management and asset allocation tasks. The platform provides an end-to-end pipeline for transforming raw market data into actionable trading models. The project distinguishes itself through a layered, modular architecture that separates data processing, environment simulation, and agent training. This design allow
Nautilus Trader is a high-performance algorithmic trading framework built in Rust, designed for the development, backtesting, and live execution of automated trading strategies. It provides a comprehensive platform for managing multi-asset portfolios and interacting with diverse financial markets through a standardized connectivity suite. The system is engineered to handle high-frequency data processing and complex order execution while maintaining precise numerical accuracy across various asset classes. The framework distinguishes itself through an architecture centered on deterministic even
m3 is a distributed time series database designed for high-resolution metrics and high-cardinality data management. It functions as a scalable storage system and a multi-cluster query engine, providing a distributed metrics aggregator capable of downsampling and summarizing data before it is committed to storage. The project distinguishes itself through a coordinated cluster model using etcd for node membership and shard placement. It supports multiple ingestion protocols, including the Prometheus remote write protocol, InfluxDB line protocol, and Graphite Carbon plaintext protocol, and provi
Tribeca is a Node.js cryptocurrency trading platform designed for high-frequency trading and automated market making. It functions as a low-latency execution engine that automates the process of providing liquidity and capturing price spreads across multiple cryptocurrency exchanges. The system employs a connectivity layer to stream real-time market data and execute trades via persistent network connections. It uses an adapter-based integration to normalize diverse venue APIs into a unified format, allowing for coordinated activity across several different cryptocurrency venues. The platform
Kungfu is a high-performance quantitative trading framework and algorithmic execution engine. It provides a development kit for writing trading logic and a dedicated in-memory financial time-series database for recording and analyzing tick-by-tick market data with high temporal accuracy.
Die Hauptfunktionen von kungfu-origin/kungfu sind: Low-Latency Trading Infrastructures, Market Trading Integrations, Quantitative Trading Platforms, Trading Execution Engines, Time Series Data Storage, Financial Tick Databases, High-Precision Time Series Storage, Memory-Mapped Time Series Storage.
Open-Source-Alternativen zu kungfu-origin/kungfu sind unter anderem: ai4finance-foundation/finrl — FinRL is a reinforcement learning framework designed for the development, training, and backtesting of automated… nautechsystems/nautilus_trader — Nautilus Trader is a high-performance algorithmic trading framework built in Rust, designed for the development,… opentsdb/opentsdb — OpenTSDB is a distributed time series database and metrics engine designed for storing and managing massive volumes of… michaelgrosner/tribeca — Tribeca is a Node.js cryptocurrency trading platform designed for high-frequency trading and automated market making.… m3db/m3 — m3 is a distributed time series database designed for high-resolution metrics and high-cardinality data management. It… shidenggui/easytrader — Easytrader is a quantitative trading automation framework and brokerage API wrapper designed to programmatically…