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
whchien/ai-trader
AI-Trader is a Python backtesting framework built on Backtrader that packages strategy development, historical data handling and LLM integration into one command-line tool. Backtests are described in version-controllable YAML files that declare broker cash and commission, the data file and date range, the strategy class and its parameters, and a position sizer, which makes runs reproducible. The ai-trader CLI exposes run for config-driven backtests, quick for a one-off run against an arbitrary CSV, fetch for downloading market data and a data subcommand group for listing, inspecting and cleaning the local cache. Data covers US stocks, Taiwan stocks, cryptocurrencies and forex; results can be written to CSV, to a SQLite store for fast repeated runs, or to both, with the cached path avoiding a network call on subsequent fetches. Over twenty strategies ship with the project, ranging from classic indicator crossovers such as CrossSMAStrategy to adaptive models, and custom strategies can be added through documented helpers. A Python API mirrors the CLI: run_backtest takes a strategy class, a data source, starting cash and strategy parameters, and a step-by-step example script shows the lower-level assembly for finer control. The agent-facing part is a built-in MCP server started with python -m ai_trader.mcp and registered in an MCP client configuration such as Claude Desktop, after which an assistant can fetch market data, launch backtests and analyze strategy results through natural-language requests instead of shell commands. The project is distributed on PyPI for CLI and library use, while a source checkout is recommended to get the example configurations, sample data and scripts. It is licensed under GPL-3.0, requires Python 3.11 or newer, and documentation is available in English and Chinese. It targets quantitative traders and developers who want an agent-accessible backtesting engine.
https://github.com/whchien/ai-trader
Also in Financial & Trading Systems
HKUDS/Vibe-Trading
Vibe-Trading is an AI-powered personal trading agent leveraging LLMs for comprehensive algorithmic trading, backtesting, and multi-agent financial market analysis.
Fincept-Corporation/FinceptTerminal
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/hummingbot
Hummingbot is an open-source framework for building and deploying high-frequency crypto trading bots on various centralized and decentralized exchanges.
ValueCell-ai/valuecell
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.
Lumiwealth/lumibot
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.
pskrunner14/trading-bot
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.
goat-sdk/goat
GOAT is the leading agentic finance toolkit enabling AI agents to autonomously perform payments, investments, tokenization, and financial operations using blockchain and cryptocurrency infrastructure.