#68 · Primary category: AI Agents & Automation

Vibe-Trading

ai-agent algorithmic-trading backtesting fintech llm mcp multi-agent python quantitative-finance trading

"Vibe-Trading: Your Personal Trading Agent"

Project last updated:08/29/26

GitHub Stars

32.1K

Forks

5.2K

Contributors

150

License

MIT

Why we included this project

Vibe-Trading is aimed at people who trade or research markets and want an LLM that does actual work instead of just talking about it. Give it a plain-English instruction and it writes and backtests strategies, compiles research reports, and can fan out a multi-agent swarm across a research question. It is a full workspace rather than a thin wrapper: FastAPI backend, React frontend, a sandboxed code execution layer for generated strategies, and an MCP surface that exposes dozens of tools covering market data, fundamentals, valuation, and quant math. The grounding discipline stands out: every number is traced back to the tool that produced it, and the agent refuses to answer when a quote falls outside recorded OHLC evidence, which matters if you are worried about hallucinated prices. A shadow-account mode handles paper trading, scheduled research jobs keep things running on their own, and a hash-chained audit ledger records what happened, so it works both as a personal research assistant and as a scaffold for building your own trading agent. Teams evaluating agent frameworks for finance get a concrete, opinionated reference implementation to study.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category