Show HN: VibeTrade – Trading Harness for Claude

Sobre

Post-Opus 4.6, LLMs feel much better at using bash, code, local files, and tools.<p>So I kept coming back to a simple question: if a model can use a computer reasonably well, why can’t I just give it my broker account, a strategy, and let it trade?<p>My conclusion is that the blocker is not model capability in the abstract. It is the system around the model.<p>A raw LLM breaks on a few practical things almost immediately:<p>• no persistent operating memory across sessions • no trustworthy record