Skip to main content
ClaudeWave
HKUDS avatar
HKUDS

Vibe-Trading

Ver en GitHub

"Vibe-Trading: Your Personal Trading Agent"

Subagents28.4k estrellas4.6k forksPythonMITActualizado today
Nota editorial

Vibe-Trading is a multi-agent Python framework that gives Claude and other LLMs a full suite of quantitative trading tools through a single pip install (`vibe-trading-ai`). It connects to Claude via MCP, meaning Claude Code and Claude Desktop can invoke its tools directly, and it also exposes a FastAPI backend with a React 19 frontend for chat-based interaction. The agent system includes named swarm presets such as an investment committee, quant desk, and risk committee, each with real-time per-worker status cards streamed into the chat timeline. An Alpha Zoo module houses over 191 backtestable alphas that can be benchmarked head-to-head using IC mean, information ratio, and IC-positive ratio metrics. A Shadow Account feature lets users simulate trades without real capital. The project targets retail traders, quant researchers, and developers who want to wire LLM reasoning into algorithmic trading workflows without building execution, backtesting, or data infrastructure from scratch.

ClaudeWave Trust Score
100/100
Verified
Passed
  • Open-source license (MIT)
  • Actively maintained (<30d)
  • Healthy fork ratio
  • Clear description
  • Topics declared
  • Documented (README)
Last scanned: 6/11/2026
Install as a Claude Code subagent
Method: Clone
Terminal
git clone https://github.com/HKUDS/Vibe-Trading && cp Vibe-Trading/*.md ~/.claude/agents/
1. Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
2. Start a new Claude Code session to load the agents.
3. Delegate work to them with the Task/Agent tool or by name.

24 items en este repositorio

Professional finance research toolkit — backtesting (7 engines + benchmark comparison panel), factor analysis, Alpha Zoo (452 pre-built alphas across qlib158/alpha101/gtja191/academic), options pricing, 79 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest → render) across 18 market-data sources (tushare, yfinance, okx, akshare, baostock, tencent, mootdx, ccxt, futu, local, eastmoney, sina, stooq, yahoo, plus optional-key finnhub/alphavantage/tiingo/fmp).

Instalar

ADR/H-share/A-share cross-listing premium analysis — track pricing gaps between US-listed ADRs, HK-listed H-shares, and A-shares for arbitrage signals, dual-listing valuation, and delisting risk assessment.

Instalar
akshareSkill

AKShare financial data aggregator (18k+ stars). Free, no API key. Covers A-shares, US, HK, futures, macro, forex. Primary fallback for tushare and yfinance.

Instalar

Browse and bench the bundled alpha zoos — prebuilt cross-sectional factor libraries (Kakushadze 101, GTJA 191, Qlib 158, Fama-French / Carhart). Use when the user asks "which alphas exist", wants metadata on a named alpha, or wants to run IC/IR on a whole zoo over a universe.

Instalar

A 股 ST/*ST 风险预测框架 — 基于最新中报/三季报或业绩预告/快报,预测下一财年是否会因营收、利润、净资产、分红不达标而被风险警示,并将新浪监管处罚记录作为独立证据面纳入风险等级。仅适用于 A 股,不预测财务造假。

Instalar

Asset allocation theory and optimizer usage — MPT / Black-Litterman / risk budgeting / all-weather strategy, including guides for 4 optimizers and rebalancing rules.

Instalar

Diagnose failed or underperforming backtests, locate the root cause, and fix the issue

Instalar

Behavioral finance applications: theories of overreaction and underreaction, behavioral explanations for momentum and reversal, investor sentiment cycles, cognitive-bias checklists, and debiasing quantitative strategies.

Instalar

Candlestick pattern recognition engine, pure pandas vectorized implementation of 15 classic candlestick patterns (5 single-candle + 5 double-candle + 4 triple-candle + 1 trend confirmation), generating a composite signal from bullish/bearish pattern scores.

Instalar
ccxtSkill

CCXT unified crypto exchange library (100+ exchanges). Free public market data. Fallback when OKX is unavailable.

Instalar
chanlunSkill

基于缠论(缠中说禅)的形态识别引擎,使用czsc库自动检测K线分型、笔、中枢,并生成一买/一卖/二买/二卖/三买/三卖等买卖点信号。支持多周期分析和形态分类(3/5/7/9/11笔形态)。

Instalar

Commodity analysis (oil supply-demand balance / gold pricing / copper as an economic predictor / inventory cycles / futures premium-discount structure / seasonality), generating directional commodity signals.

Instalar

A股可转债分析——转股/纯债/期权三维估值、下修/强赎/回售博弈、双低策略与转债轮动选债框架

Instalar

公司事件驱动分析:并购套利价差计算、大股东增减持信号、股权激励解读、定增配股影响评估、A股ST/退市预警

Instalar

Correlation and cointegration analysis — co-movement discovery, deep return-correlation analysis, sector clustering, realized correlation, Engle-Granger / Johansen cointegration, half-life, Kalman dynamic hedge ratio, cross-market linkage analysis, and pair-trading signal generation

Instalar

固收与信用分析:信用债评级、利差分析、违约风险评估、城投债研究、可转债定价与策略。

Instalar

Write signal_engine.py for portfolios spanning multiple markets (A-shares + crypto, equity + forex, etc.)

Instalar

Crypto-derivatives strategies — perpetual funding-rate arbitrage, futures term-structure contango/backwardation trading, and option volatility-smile / Greeks analysis.

Instalar

The single ROUTER for every data need. Load this skill BEFORE any backtest, data-fetch, or research task to pick the best available source/tool, honour auth (env) requirements, and avoid ban-risk providers.

Instalar

DeFi yield analysis and optimization — lending rates, LP yields, staking returns, yield farming strategies, risk-adjusted yield comparison, and protocol-level sustainability assessment.

Instalar

Dividend stock analysis for income, dividend-growth, and shareholder-return strategies, including yield quality, payout sustainability, ex-dividend mechanics, and yield-trap checks.

Instalar

Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the `read_document` tool.

Instalar

盈利预测与一致预期分析(自上而下/自下而上预测法/SUE/PEAD/分析师预期修正),捕捉业绩超预期交易机会。

Instalar

Earnings estimate revisions, guidance analysis, and post-earnings drift (PEAD) — track analyst consensus changes, earnings surprise patterns, and management guidance shifts for US/HK equities.

Instalar
Casos de uso

Resumen de Subagents

<p align="center">
  <b>English</b> | <a href="README_zh.md">中文</a> | <a href="README_ja.md">日本語</a> | <a href="README_ko.md">한국어</a> | <a href="README_ar.md">العربية</a>
</p>

<p align="center">
  <img src="assets/icon.png" width="120" alt="Vibe-Trading Logo"/>
</p>

<h1 align="center">Vibe-Trading: Your Personal Trading Agent</h1>

<p align="center">
  <b>One Command to Empower Your Agent with Comprehensive Trading Capabilities</b>
</p>

<p align="center">
  <a href="https://trendshift.io/repositories/25527" target="_blank"><img src="https://trendshift.io/api/badge/repositories/25527" alt="HKUDS%2FVibe-Trading | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
</p>

<p align="center">
  <img src="https://img.shields.io/badge/Python-3.11%2B-3776AB?style=flat&logo=python&logoColor=white" alt="Python">
  <img src="https://img.shields.io/badge/Backend-FastAPI-009688?style=flat" alt="FastAPI">
  <img src="https://img.shields.io/badge/Frontend-React%2019-61DAFB?style=flat&logo=react&logoColor=white" alt="React">
  <a href="https://pypi.org/project/vibe-trading-ai/"><img src="https://img.shields.io/pypi/v/vibe-trading-ai?style=flat&logo=pypi&logoColor=white" alt="PyPI"></a>
  <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-yellow?style=flat" alt="License"></a>
  <br>
  <a href="https://github.com/HKUDS/.github/blob/main/profile/README.md"><img src="https://img.shields.io/badge/Feishu-Group-E9DBFC?style=flat-square&logo=feishu&logoColor=white" alt="Feishu"></a>
  <a href="https://github.com/HKUDS/.github/blob/main/profile/README.md"><img src="https://img.shields.io/badge/WeChat-Group-C5EAB4?style=flat-square&logo=wechat&logoColor=white" alt="WeChat"></a>
  <a href="https://discord.gg/6TdQnT5xcF"><img src="https://img.shields.io/badge/Discord-Join-7289DA?style=flat-square&logo=discord&logoColor=white" alt="Discord"></a>
</p>

<p align="center">
  <a href="https://vibetrading.wiki/">Website</a> &nbsp;&middot;&nbsp;
  <a href="https://vibetrading.wiki/docs/">Docs</a> &nbsp;&middot;&nbsp;
  <a href="#-news">News</a> &nbsp;&middot;&nbsp;
  <a href="#-key-features">Features</a> &nbsp;&middot;&nbsp;
  <a href="#-shadow-account">Shadow Account</a> &nbsp;&middot;&nbsp;
  <a href="#-demo">Demo</a> &nbsp;&middot;&nbsp;
  <a href="#-quick-start">Quick Start</a> &nbsp;&middot;&nbsp;
  <a href="#-examples">Examples</a> &nbsp;&middot;&nbsp;
  <a href="#-api-server">API / MCP</a> &nbsp;&middot;&nbsp;
  <a href="#-roadmap">Roadmap</a> &nbsp;&middot;&nbsp;
  <a href="#contributing">Contributing</a>
</p>

<p align="center">
  <a href="#-quick-start"><img src="assets/pip-install.svg" height="45" alt="pip install vibe-trading-ai"></a>
</p>

---

## 📰 News

> ⚠️ **Security warning:** The X account `VibeTrading_HKU`, Virtuals project `101845`, and token contract `0x640BDBF77b6447E8b7DB7894cED84BD1c40571f4` are not official Vibe-Trading assets. We have never launched or endorsed any token or memecoin. Do not buy, connect a wallet, or sign anything. [Details](SECURITY.md#official-channels--impersonation).

- **2026-07-28** 🔧 **Next-gen Claude models unblocked + sign-safe returns**: Claude models that deprecate the `temperature` field (opus-4-7, opus-5, sonnet-5) now work — the adapter drops the field when the API rejects it, retries once, and remembers the model, so no per-release patch is needed ([#890](https://github.com/HKUDS/Vibe-Trading/pull/890), closes [#856](https://github.com/HKUDS/Vibe-Trading/issues/856), thanks @yagnikpipaliya). Non-interactive `vibe-trading run` now injects a host session id: research-goal tools previously failed on every call while the run still reported success ([#885](https://github.com/HKUDS/Vibe-Trading/issues/885)). Buy-and-hold returns are sign-safe — a near-zero prior close no longer explodes the compounded benchmark, and an exact-zero close no longer yields `inf`/`nan` ([#872](https://github.com/HKUDS/Vibe-Trading/issues/872), thanks @darkknight4563). The frontend moves to **Node 22 + React Router 8**, clearing a high-severity advisory.
- **2026-07-27** 🔧 **Correlation integrity + vn.py 4.0 export repair + an encoding batch**: The rolling correlation matrix no longer forward-fills missing closes — a halted session was being scored as a fabricated 0% return against the peer's real move, distorting the matrix ([#873](https://github.com/HKUDS/Vibe-Trading/pull/873), thanks @ddy4633). The **vn.py export** skill is repaired for the vn.py 4.x layout, where `vnpy.app.cta_strategy` no longer exists upstream — templates now import from `vnpy_ctastrategy` ([#869](https://github.com/HKUDS/Vibe-Trading/pull/869), thanks @y85998607). Plus a six-fix batch: UTF-16 BOM decoding in the document reader and trade-journal CSVs, currency symbols stripped before numeric coercion, `BTCUSDT`-style symbols inferred as crypto, lowercase `1h`/`1d` intervals annualized correctly, and CJK characters preserved in skill directory slugs ([#862](https://github.com/HKUDS/Vibe-Trading/pull/862), [#863](https://github.com/HKUDS/Vibe-Trading/pull/863), [#864](https://github.com/HKUDS/Vibe-Trading/pull/864), [#865](https://github.com/HKUDS/Vibe-Trading/pull/865), [#866](https://github.com/HKUDS/Vibe-Trading/pull/866), [#868](https://github.com/HKUDS/Vibe-Trading/pull/868), thanks @santhreal).
- **2026-07-26** 🔒 **Dependency lock + universe transparency**: Docker’s hash-locked install works again, with a new CI lock check ([#858](https://github.com/HKUDS/Vibe-Trading/pull/858), closes [#847](https://github.com/HKUDS/Vibe-Trading/issues/847)). `alpha bench` now discloses CSI300/SP500 sources, counts, degraded fallbacks, and survivorship bias ([#859](https://github.com/HKUDS/Vibe-Trading/pull/859), closes [#845](https://github.com/HKUDS/Vibe-Trading/issues/845)). Actions and five frontend dependencies were also refreshed ([#850](https://github.com/HKUDS/Vibe-Trading/pull/850)–[#852](https://github.com/HKUDS/Vibe-Trading/pull/852)).

<details>
<summary>Earlier news</summary>

- **2026-07-25** 🔧 **Perpetual realism + MCP crash fix + a correctness batch**: USD-M perpetuals gain **margin state contracts** ([#798](https://github.com/HKUDS/Vibe-Trading/pull/798), thanks @honginp) and the engine now consumes **historical funding rates** instead of fetching-and-ignoring them ([#819](https://github.com/HKUDS/Vibe-Trading/pull/819), thanks @g0rdonL). MCP dataclass results no longer crash on a false `Circular reference detected` ([#849](https://github.com/HKUDS/Vibe-Trading/pull/849), thanks @Echoandelementwebsites), and `alpha bench` CLI/HTML forward the `_meta` survivorship disclosure ([#841](https://github.com/HKUDS/Vibe-Trading/pull/841), closes [#797](https://github.com/HKUDS/Vibe-Trading/issues/797), thanks @AmirF194). Plus 12 correctness fixes across journals, connectors, and channels ([#799](https://github.com/HKUDS/Vibe-Trading/pull/799)–[#810](https://github.com/HKUDS/Vibe-Trading/pull/810), thanks @santhreal), and a real account label in CLI balances ([#843](https://github.com/HKUDS/Vibe-Trading/pull/843), closes [#846](https://github.com/HKUDS/Vibe-Trading/issues/846), thanks @Robin1987China).
- **2026-07-24** 🔀 **Memory Tier 2, composable optimizer constraints + an interval-handling sweep**: Persistent memory gains **Tier 2 structural organization** ([#815](https://github.com/HKUDS/Vibe-Trading/pull/815), thanks @shadowinlife), and backtest optimizers accept **composable weight constraints** ([#818](https://github.com/HKUDS/Vibe-Trading/pull/818), thanks @he-yufeng). Correctness: the daily-bar validator can opt in to **non-positive prices** — opening on negative bars while still rejecting zero ([#816](https://github.com/HKUDS/Vibe-Trading/pull/816), closes [#571](https://github.com/HKUDS/Vibe-Trading/issues/571), thanks @darkknight4563). Plus a 19-PR loader **interval-normalization sweep**: lowercase `1h/4h/1d/1w` aliases accepted everywhere, unsupported intervals now fail fast instead of silently returning daily bars, Yahoo `4H` maps to `1h`, and MT5 accepts `1W/1M` ([#812](https://github.com/HKUDS/Vibe-Trading/pull/812)–[#838](https://github.com/HKUDS/Vibe-Trading/pull/838), thanks @santhreal), a trade-journal fix for Eastmoney Excel-serial dates ([#811](https://github.com/HKUDS/Vibe-Trading/pull/811), thanks @santhreal), and a README nav-anchor fix ([#840](https://github.com/HKUDS/Vibe-Trading/pull/840), thanks @dvirarad).
- **2026-07-23** 🔧 **Reliability sweep + strict alpha-bench surfaced + opt-in memory lifecycle**: A 22-PR contributor batch. A broad **reliability sweep** fixes timeframe handling end to end — yfinance `1M`→monthly (not minute), CCXT `1W`/`1M`, akshare/india-broker rejecting unsupported intervals instead of silent daily, and the Tiger/Alpaca/OKX/Shoonya/Longbridge connectors keeping `1H`/`4H` as hour bars — plus trade-journal Excel-date normalization (eastmoney float `YYYYMMDD`, Futu/Tonghuashun serial dates), finite-JSON `report_audit`, blank `holding_days` validation, and Feishu/CLI markdown table edges ([#778](https://github.com/HKUDS/Vibe-Trading/pull/778)–[#794](https://github.com/HKUDS/Vibe-Trading/pull/794), thanks @santhreal). **MT5** `trading_history` now coerces numpy scalars so JSON serialization no longer dies on `int64` ([#776](https://github.com/HKUDS/Vibe-Trading/pull/776), closes [#774](https://github.com/HKUDS/Vibe-Trading/issues/774), thanks @shadowinlife), and **PIT fundamentals** dedup restated rows and stop the snapshot regressing to an older fiscal period on a late restatement ([#772](https://github.com/HKUDS/Vibe-Trading/pull/772), closes [#771](https://github.com/HKUDS/Vibe-Trading/issues/771), thanks @klmtseng). New: **`alpha bench --strict`** finally wires the strict same-universe random-control + OOS gate that shipped unreachable since 0.1.9 ([#796](https://github.com/HKUDS/Vibe-Trading/pull/796), closes [#773](https://github.com/HKUDS/Vibe-Trading/issues/773), thanks @he-yufeng), an opt-in **memory lifecycle** (quality scoring, Ebbing
ai-agentalgorithmic-tradingbacktestingfintechllmmcpmulti-agentpythonquantitative-financetrading

Lo que la gente pregunta sobre Vibe-Trading

¿Qué es HKUDS/Vibe-Trading?

+

HKUDS/Vibe-Trading es subagents para el ecosistema de Claude AI. "Vibe-Trading: Your Personal Trading Agent" Tiene 28.4k estrellas en GitHub y se actualizó por última vez today.

¿Cómo se instala Vibe-Trading?

+

Puedes instalar Vibe-Trading clonando el repositorio (https://github.com/HKUDS/Vibe-Trading) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.

¿Es seguro usar HKUDS/Vibe-Trading?

+

Nuestro agente de seguridad ha analizado HKUDS/Vibe-Trading y le ha asignado un Trust Score de 100/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.

¿Quién mantiene HKUDS/Vibe-Trading?

+

HKUDS/Vibe-Trading es mantenido por HKUDS. La última actividad registrada en GitHub es de today, con 31 issues abiertos.

¿Hay alternativas a Vibe-Trading?

+

Sí. En ClaudeWave puedes explorar subagents similares en /categories/agents, ordenados por popularidad o actividad reciente.

Despliega Vibe-Trading en tu cloud

Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.

¿Mantienes este repo? Añade un badge a tu README

Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.

Featured on ClaudeWave: HKUDS/Vibe-Trading
[![Featured on ClaudeWave](https://claudewave.com/api/badge/hkuds-vibe-trading)](https://claudewave.com/repo/hkuds-vibe-trading)
<a href="https://claudewave.com/repo/hkuds-vibe-trading"><img src="https://claudewave.com/api/badge/hkuds-vibe-trading" alt="Featured on ClaudeWave: HKUDS/Vibe-Trading" width="320" height="64" /></a>

Más Subagents

Alternativas a Vibe-Trading