Multi-Agents LLM Financial Trading Framework

103K stars, so clearly it's popular. Has anyone here used it, and what are the outcomes like, and importantly, who is the target audience for this?

I can see the intention behind crawling social media and news feeds to determine some 'evidence', but am not sure if that's the best approach or even if an LLM is the best way to get an assessment, or whether having so many input sources is a good idea.

In case there is interest, I've got a fork with some custom improvements like timeout handling, date validation, stop-loss direction checks, and extra utility helpers.

https://github.com/skanga/TradingAgents

I'll also be merging the upstream commits ASAP

I do not understand the value of multi agent approach? Isn't a single agent with a good harness better than any multi agent env?

I think multi-agent (eg _different_ underlying LLMs) everything is really the future. Code produced via multi-agent workflows and reviews seems noticeably better. I've been experimenting with a multi-agent message board recently: https://github.com/pjlsergeant/dogpark

nightmare horseshit, don't waste your tokens