[bingwu1995]

I've been testing it on a few specific workflows.

Found it actually performs well for data analysis and running automated checks (cron-style tasks). Because the reasoning layer seems reliable so far, I've hooked it up to a simulation account (paper trading) to backtest the execution in real-time.

It’s good enough to monitor the market, but I’m keeping it sandboxed until I see consistent behavior over a longer timeframe.

https://github.com/SYNR-AI/ClawStreet