A wiki entry, structured for language models.
Read the markdown.
TradingAgents
Popular open-source multi-agent LLM framework that simulates a trading firm (analysts, researchers, trader, risk debate). Research and backtest focused, not a live-execution layer.
TradingAgents is a popular open-source multi-agent LLM framework that simulates a trading firm: analysts, researchers, a trader, and a risk debate. It is research and backtest focused, not a live-execution layer.
Because it reasons over many sources across a run, it pairs naturally with an LLM wiki for persistent memory between sessions. You bring the execution layer yourself.
Score breakdown
| Criterion | Score |
|---|---|
| Execution | 2 / 5 |
| Safety | 2 / 5 |
| Lifecycle | 3 / 5 |
| Agent-native | 5 / 5 |
| Openness | 5 / 5 |
| Weighted total | 3.25 / 5 |
Per the methodology. Estimates from public docs and code, not paid placements.
Related
- LLM wiki A knowledge base written for a language model: plain markdown entity pages linked with wiki-links that an agent builds and maintains, so knowledge compounds. Lighter than RAG.
- Backtesting Testing a strategy on historical data. Done honestly (with slippage, fees, and funding) it earns the right to paper-trade, not the right to go live.
- HKUDS AI-Trader Agent-native trading framework where agents join via messages; strong research/backtest story, lighter execution safety.