TradingAgents
TradingAgents is a multi-agent framework that simulates a trading firm of LLM analysts, researchers, and managers to evaluate stock trades for researchers and developers.
What it is good for
- Testing trading ideas against simulated analyst and researcher debates
- Reviewing stock fundamentals, news, and technical signals in one report
- Backtesting trading decisions over a range of tickers and dates
- Comparing how different language models reason about market data
At a glance
- Who it is for
- Setup
- Requires programming
Level 5 of 5. You need to write code to use it.
- Cost
- Free and open source
- Type
- Framework or SDK
- Tasks
- Works with
- FRED, Alpha Vantage, Yahoo Finance, SEC EDGAR, OpenAI, Anthropic
Momentum
- Rank this week
- #7 in builder tools
- Best rank
- #7 week 44, 2026
- Stars gained last week
- +4,861
- GitHub stars
- 119,754
GitHub numbers as of Nov 2, 2026. Updated weekly.
Ranking history
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is TradingAgents free?
- Yes. It is free and open source (Apache-2.0 license).
- Do I need to know how to code to use TradingAgents?
- Yes. You need to write code to use it.
- What does TradingAgents work with?
- According to its own documentation, it works with FRED, Alpha Vantage, Yahoo Finance, SEC EDGAR, OpenAI, and Anthropic.
- What is TradingAgents good for?
- Testing trading ideas against simulated analyst and researcher debates, reviewing stock fundamentals, news, and technical signals in one report, backtesting trading decisions over a range of tickers and dates, and comparing how different language models reason about market data.
Similar agents
- OpenMetadata
OpenMetadata is an open-source data catalog and metadata platform that gives people and AI assistants trusted context about company data.
- ChatLab
ChatLab is a desktop app that analyzes your exported chat history from WhatsApp, Telegram, Discord and others, with AI agents that search and summarize it, all stored on your own machine.
- tick-stock-panel
TSP is a self-hosted A-share quant workbench that lets investors build strategies, run backtests, and monitor stocks for individuals who write their own rules.
- tradingview-mcp
tradingview-mcp is an MCP server that gives AI assistants market data, screeners, technical analysis and backtests for stocks, crypto, forex and futures.
- Vibe-Research
Vibe-Research is a self-hosted stock research workbench that uses an AI agent for A-share, US and HK stock analysis for investors and analysts.
- easy-stock
easy-stock is a desktop app that helps A-share traders research stocks, track sector themes, and review the market with AI for active investors in China.