Vibe-Trading
A local finance research app with terminal and web interfaces, cross-market backtests and trade reviews. Uses OpenRouter for AI by default; MIT licensed.
Vibe-Trading is an installed Python research app with terminal and web interfaces for traders and analysts testing strategies or reviewing trades. The workspace runs on your machine, but its AI requests go to OpenRouter by default. Research also fetches external market data and web content.
Backtests cover global equities, crypto, futures, forex and options portfolios, including strategies spanning markets. Results include benchmark comparisons, validation records and exportable strategy code. Investment, quant, macro, crypto and risk agent teams can divide up research and save reports with supporting evidence and caveats.
Shadow Account examines broker journals, identifies trading behavior and extracts rules for comparison with counterfactual backtests. Document analysis covers office files and PDFs; a vision model interprets chart screenshots. Research can also examine SEC 13F holdings and ETF constituents. Persistent memory and editable skills let later sessions reuse research context.
The read-only portfolio view combines holdings from selected broker connections, stores snapshots locally and supports CSV exports and risk analysis. Broker compatibility varies, and a failed source is excluded from totals with the snapshot marked incomplete.
The project is open source under MIT, with REST and MCP access alongside its user interfaces. Live trading is optional. It requires a broker you authorize, operates within your chosen limits and can be stopped immediately.
