TauricResearch/TradingAgents
TradingAgents is an open-source multi-agent financial trading framework leveraging large language models to simulate real-world trading firm dynamics and collaboratively make informed trading decisions.
Awesome AI Agents › Financial & Trading Systems
The project "gym-fx" is a Forex trading simulator environment designed for OpenAI Gym, enabling users to test and optimize custom trading agents in a simulated forex market. It provides a configurable environment where initial capital, spread (dynamic or dataset-based), and trading parameters such as take-profit, stop-loss, and order volume can be adjusted. The environment supports both discrete and continuous action spaces, allowing agents to perform actions like buying, selling, closing orders, or doing nothing, with optional control over take-profit, stop-loss, and order volume percentages. Observations provided to the agent include a concatenation of vectors representing recent timeseries data, equity and its variation, order status, time opened, order profit and its variation, drawdown metrics, and volume in pips. This rich observation space helps the agent make informed trading decisions based on historical and current market data. The reward function is designed to encourage profitable trading by averaging the area under the equity curve and balance variation, promoting strategies that maintain and grow capital over time. The project also includes tools for generating datasets from Metatrader 4 (MT4) using MQL4 scripts, facilitating the creation of realistic historical data for training and testing agents. Installation instructions cover dependency setup, cloning the repository, setting environment variables, and running the optimizer script to start training agents. Overall, gym-fx serves as a comprehensive platform for developing, testing, and optimizing forex trading strategies using reinforcement learning within the OpenAI Gym framework. It is particularly useful for researchers and developers interested in algorithmic trading and financial machine learning, providing a flexible and extensible environment to simulate real-world forex trading scenarios.
https://github.com/harveybc/gym-fx
TradingAgents is an open-source multi-agent financial trading framework leveraging large language models to simulate real-world trading firm dynamics and collaboratively make informed trading decisions.
Vibe-Trading is an AI-powered personal trading agent leveraging LLMs for comprehensive algorithmic trading, backtesting, and multi-agent financial market analysis.
FinceptTerminal is an advanced C++/Qt6/Python-based desktop application providing comprehensive financial analytics, investment research, and real-time trading capabilities with AI agents and exten...
Hummingbot is an open-source framework for building and deploying high-frequency crypto trading bots on various centralized and decentralized exchanges.
ValueCell is a community-driven, multi-agent platform that leverages AI to provide comprehensive financial applications including stock research, automated trading, and market analysis across multiple global markets.
Python library for building, backtesting and live-trading algorithmic strategies, with a built-in LLM agent runtime whose agents query market, filings and macro data tools and can place broker orders.
A Stock Trading Bot that uses Deep Q-Learning, a form of Deep Reinforcement Learning, to learn and execute trading strategies based on historical stock market data.
Config-driven backtesting framework for algorithmic trading built on Backtrader, shipping 20+ strategies, multi-market data fetching and an MCP server that lets AI assistants run backtests.