HKUDS/Vibe-Trading

Project overview

An open-source research workspace that translates natural-language prompts into market-data loading, strategy drafting, backtesting, and report generation. It targets developers and data teams building research and analysis workflows across equities, crypto, futures, and forex markets, though it does not support real-time tick or order-book depth live trading.

Project type

MCP · AI Agent · Data Processing

Use cases

Data Analysis · Automation

Deployment

Refer to project documentation

License

MIT

Best for

• Developers and data teams who need a self-hosted or locally run application for agent-driven data analysis and automation across financial markets.

Key capabilities

• Facilitates natural-language market research, strategy drafts, file and web analysis, and memory-backed workflows.
• Coordinates investment, quant, crypto, and risk workflows with streaming progress, persisted reports, and workers grounded with fetched market data.
• Backtests across A/HK/US equities, crypto, futures, and forex with data fallback, composite backtests, PIT data validation, and run cards.
• Diagnoses broker-journal behavior, performs rule-based Shadow Account comparisons, and produces exportable audit reports and strategy code.
• Provides 461 cross-sectional alphas with lookahead banned at the operator layer and IC, IR, and alive, reversed, or dead categorization in one CLI command.
• Exposes tools over Model Context Protocol using stdio, SSE, and streamable HTTP transports.
• Runs sessions via WebSocket, Telegram, Slack, Discord, Matrix, WhatsApp, Signal, QQ/NapCat, WeChat/WeCom, Feishu/Lark, DingTalk, Teams, email, and Mochat with CLI, REST, and Web UI controls.
• Volatility surface, Greeks dashboard, and payoff and scenario explorer.

Limitations and risks

• Model Context Protocol tool execution operates serially only in version 1.
• Custom data loaders support point-in-time historical bars, but do not support real-time ticks or order-book depth.

Getting started

• Install via a one-line pip install, run the interactive initialization, and start processing prompts using the CLI, REST, or Web UI without a coding requirement.

Evidence and sources

• GitHub project description: "Vibe-Trading: Your Personal Trading Agent"
• README: Vibe-Trading is an open-source research workspace for turning finance questions into runnable analysis. It connects natural-language prompts to market-data loaders, strategy gener…
• README: <b>One Command to Empower Your Agent with Comprehensive Trading Capabilities</b>
• Release: v0.1.11 — India equity, fundamental factors, IM channels + roll-up
• README: 🔍 Self-Improving Trading Agent

Reviewed at: 2026-07-17T10:48:24Z