能力标签
Vibe交易智能体
🛠
AI工具

Vibe交易智能体

基于 Python · 开源 AI 工具,GitHub 社区精选
英文名:Vibe-Trading
⭐ 7.2k Stars 🍴 1.4k Forks 💻 Python 📄 MIT 🏷 AI 7.8分
7.8AI 综合评分
交易自动化算法交易MCP工具量化回测LLM应用
✦ AI Skill Hub 推荐

经 AI Skill Hub 精选评估,Vibe交易智能体 获评「推荐使用」。已获得 7.2k 颗 GitHub Star,这款AI工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.8 分,适合有一定技术背景的用户使用。

📚 深度解析

Vibe交易智能体 是一款基于 Python 的开源工具,在 GitHub 上收获 7k+ Star,是交易自动化、算法交易、MCP工具、量化回测领域中的优质开源项目。开源工具的最大优势在于代码完全透明,你可以审计每一行代码的安全性,也可以根据自身需求进行二次开发和定制。

**为什么要使用开源工具而非商业 SaaS?**
对于个人开发者和有隐私需求的用户,本地部署的开源工具意味着数据不离本机,不受第三方服务商的数据政策约束。同时,开源工具通常没有使用次数限制和月度费用,一次安装即可长期使用,对于高频使用场景的总拥有成本(TCO)远低于订阅制商业工具。

**安装与环境准备**
Vibe交易智能体 依赖 Python 运行环境。建议通过 pyenv(Python)或 nvm(Node.js)管理 Python 版本,避免全局环境污染。对于新手用户,推荐先创建虚拟环境(python -m venv venv && source venv/bin/activate),再安装依赖,这样即使出现问题也可以随时删除虚拟环境重新开始,不影响系统稳定性。

**社区与维护**
GitHub Issue 和 Discussion 是获取帮助的最快渠道。在提问前建议先检查 Closed Issues(已关闭的问题),大多数常见问题都已有解答。遇到 Bug 时,提供 pip list 的输出、完整错误堆栈和最小可复现示例,能显著提高开发者响应速度。AI Skill Hub 将持续追踪 Vibe交易智能体 的版本更新,及时通知重要功能变化。

📋 工具概览

Vibe交易智能体 是一款基于 Python 开发的开源工具,专注于 交易自动化、算法交易、MCP工具 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。

GitHub Stars
⭐ 7.2k
开发语言
Python
支持平台
Windows / macOS / Linux
维护状态
持续维护,定期更新
开源协议
MIT
AI 综合评分
7.8 分
工具类型
AI工具
Forks
1.4k

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理,如需查看完整原始文档请访问底部「原始来源」。

Vibe交易智能体 是一款基于 Python 开发的开源工具,专注于 交易自动化、算法交易、MCP工具 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。

📌 核心特色
  • 开源免费,支持本地部署,数据完全自主可控
  • 活跃的 GitHub 开源社区,持续迭代更新
  • 提供详细文档和使用示例,新手友好
  • 支持自定义配置,灵活适配不同使用环境
  • 可作为基础组件集成进现有技术栈或进行二次开发
🎯 主要使用场景
  • 本地部署运行,保护数据隐私,满足合规要求
  • 自定义集成到现有系统,扩展技术栈能力
  • 作为开源基础组件进行商业化二次开发
以下安装命令基于项目开发语言和类型自动生成,实际以官方 README 为准。
安装命令
# 方式一:pip 安装(推荐)
pip install vibe-trading

# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate
pip install vibe-trading

# 方式三:从源码安装(获取最新功能)
git clone https://github.com/HKUDS/Vibe-Trading
cd Vibe-Trading
pip install -e .

# 验证安装
python -c "import vibe_trading; print('安装成功')"
📋 安装步骤说明
  1. 访问 GitHub 仓库页面
  2. 按照 README 文档完成依赖安装
  3. 根据系统环境完成初始化配置
  4. 参考官方示例或文档开始使用
  5. 遇到问题可在 GitHub Issues 中查找解答
以下用法示例由 AI Skill Hub 整理,涵盖最常见的使用场景。
常用命令 / 代码示例
# 命令行使用
vibe-trading --help

# 基本用法
vibe-trading input_file -o output_file

# Python 代码中调用
import vibe_trading

# 示例
result = vibe_trading.process("input")
print(result)
以下配置示例基于典型使用场景生成,具体参数请参照官方文档调整。
配置示例
# vibe-trading 配置文件示例(config.yml)
app:
  name: "vibe-trading"
  debug: false
  log_level: "INFO"

# 运行时指定配置文件
vibe-trading --config config.yml

# 或通过环境变量配置
export VIBE_TRADING_API_KEY="your-key"
export VIBE_TRADING_OUTPUT_DIR="./output"
📑 README 深度解析 真实文档 完整度 87/100 查看 GitHub 原文 →
以下内容由系统直接从 GitHub README 解析整理,保留代码块、表格与列表结构。

简介

<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>

Vibe-Trading: Your Personal Trading Agent

<p align="center"> <b>One Command to Empower Your Agent with Comprehensive Trading Capabilities</b> </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/2vDYc2w5"><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>

---

✨ Key Features

Self-improving trading agent

🔍 Self-Improving Trading Agent

• Natural-language market research
• Strategy drafts and file/web analysis
• Memory-backed workflows
Multi-agent trading teams

🐝 Multi-Agent Trading Teams

• Investment, quant, crypto, and risk teams
• Streaming progress and persisted reports
• Workers grounded with fetched market data
Cross-market data and backtesting

📊 Cross-Market Data & Backtesting

• A/HK/US equities, crypto, futures, and forex
• Data fallback and composite backtests
• PIT data, validation, and run cards
Shadow Account

👥 Shadow Account

• Broker-journal behavior diagnostics
• Rule-based Shadow Account comparisons
• Exportable audit reports and strategy code

🔩 Detailed Capabilities

Detailed inventories are folded below to keep the main README scannable. Open them when you want to inspect the available building blocks.

<details> <summary><b>Finance Skill Library</b> <sub>77 skills across 8 categories</sub></summary>

  • 📊 77 specialized finance skills organized into 8 categories
  • 🌐 Complete coverage from traditional markets to crypto & DeFi
  • 🔬 Comprehensive capabilities spanning data sourcing to quantitative research
CategorySkillsExamples
Data Source7data-routing, tushare, yfinance, okx-market, akshare, mootdx, ccxt
Strategy17strategy-generate, cross-market-strategy, technical-basic, candlestick, ichimoku, elliott-wave, smc, multi-factor, ml-strategy
Analysis17factor-research, macro-analysis, global-macro, valuation-model, earnings-forecast, credit-analysis, dividend-analysis
Asset Class9options-strategy, options-advanced, convertible-bond, etf-analysis, asset-allocation, sector-rotation
Crypto7perp-funding-basis, liquidation-heatmap, stablecoin-flow, defi-yield, onchain-analysis
Flow7hk-connect-flow, us-etf-flow, edgar-sec-filings, financial-statement, adr-hshare
Tool11backtest-diagnose, report-generate, pine-script, doc-reader, web-reader, vnpy-export, alpha-zoo
Risk Analysis1ashare-pre-st-filter

</details>

<details> <summary><b>Preset Trading Teams</b> <sub>29 swarm presets</sub></summary>

  • 🏢 29 ready-to-use agent teams
  • ⚡ Pre-configured finance workflows
  • 🎯 Investment, trading & risk management presets
PresetWorkflow
investment_committeeBull/bear debate → risk review → PM final call
global_equities_deskA-share + HK/US + crypto researcher → global strategist
crypto_trading_deskFunding/basis + liquidation + flow → risk manager
earnings_research_deskFundamental + revision + options → earnings strategist
macro_rates_fx_deskRates + FX + commodity → macro PM
quant_strategy_deskScreening + factor research → backtest → risk audit
technical_analysis_panelClassic TA + Ichimoku + harmonic + Elliott + SMC → consensus
risk_committeeDrawdown + tail risk + regime review → sign-off
global_allocation_committeeA-shares + crypto + HK/US → cross-market allocation

<sub>Plus 20+ additional specialist presets — run vibe-trading --swarm-presets to explore all.

</sub>

</details>

<details> <summary><b>Alpha Zoo</b> <sub>452 pre-built quant alphas across 4 zoos</sub></summary>

  • 🧬 452 cross-sectional alphas, lookahead-banned at the operator layer
  • 📈 IC + IR + alive/reversed/dead categorisation in one CLI command
  • 🔬 AST purity gate + 300-row lookahead sentinel test + pytest-socket network kill-switch
  • 📦 Apache-2 attribution for Qlib; per-zoo LICENSE.md declaring formulas as mathematical content
  • 🤝 Developer Certificate of Origin (DCO) sign-off workflow for community PRs
ZooCountSourceLicense
**qlib158**154Microsoft Qlib Alpha158 (Apache-2.0, commit-pinned)Apache-2.0
**alpha101**101Kakushadze (2015), "101 Formulaic Alphas", arXiv:1601.00991Formulas are mathematical content
**gtja191**191Guotai Junan (2014), "191 Short-period Trading Alpha Factors"Formulas are mathematical content
**academic**6Fama-French 5 + Carhart momentum (price-based proxies)Public academic literature

Run vibe-trading alpha list to browse, vibe-trading alpha show <id> for formulas + source, vibe-trading alpha bench --zoo X --universe Y --period Z to score a whole zoo.

</details>

Prerequisites

  • An LLM API key from any supported provider — or run locally with Ollama (no key needed)
  • Python 3.11+ for Path B
  • Docker for Path A
  • OpenAI Codex can also be used with ChatGPT OAuth: set LANGCHAIN_PROVIDER=openai-codex, then run vibe-trading provider login openai-codex. This does not use OPENAI_API_KEY.
Supported LLM providers: OpenRouter, OpenAI, DeepSeek, Gemini, Groq, DashScope/Qwen, Zhipu, Moonshot/Kimi, MiniMax, Xiaomi MIMO, Z.ai, Ollama (local). See .env.example for config.
Tip: All markets work without any API keys thanks to automatic fallback. yfinance (HK/US), OKX (crypto), mootdx (A-shares, TCP-direct, no IP throttle), and AKShare (A-shares, US, HK, futures, forex) are all free. Tushare token is optional — mootdx is the preferred no-token A-share fallback, with AKShare as a broader backup.

One-line install (PyPI)

pip install vibe-trading-ai

Then run a first research task:

vibe-trading init
vibe-trading run -p "Backtest a BTC-USDT 20/50 moving-average strategy for 2024 and summarize return and drawdown"
Package name vs commands: The PyPI package is vibe-trading-ai. Once installed, you get three commands: | Command | Purpose | |---------|---------| | vibe-trading | Interactive CLI / TUI | | vibe-trading serve | Launch FastAPI web server | | vibe-trading-mcp | Start MCP server (for Claude Desktop, OpenClaw, Cursor, etc.) |
vibe-trading init              # interactive .env setup
vibe-trading                   # launch CLI
vibe-trading serve --port 8899 # launch web UI
vibe-trading-mcp               # start MCP server (stdio)

Path A: Docker (zero setup)

```bash git clone https://github.com/HKUDS/Vibe-Trading.git cd Vibe-Trading cp agent/.env.example agent/.env

Path B: Local install

```bash git clone https://github.com/HKUDS/Vibe-Trading.git cd Vibe-Trading python -m venv .venv

⚡ Quick Example

```bash pip install vibe-trading-ai

🚀 Quick Start

💡 Examples

Quick start

Create ~/.vibe-trading/agent.json:

{
  "mcpServers": {
    "my-server": {
      "command": "uvx",
      "args": ["my-mcp-server"]
    }
  }
}

Run any CLI command — tools from my-server are automatically injected into the agent's registry after local tools:

vibe-trading run "use my-server to do X"

🎬 Demo

https://github.com/user-attachments/assets/4e4dcb80-7358-4b9a-92f0-1e29612e6e86

</td> <td width="50%">

https://github.com/user-attachments/assets/3754a414-c3ee-464f-b1e8-78e1a74fbd30

</td> </tr> <tr> <td colspan="2" align="center"><sub>☝️ Natural-language backtest & multi-agent swarm debate — Web UI + CLI</sub></td> </tr> </table> </div>

---

Edit agent/.env — uncomment your LLM provider and set API key

docker compose up --build ```

Open http://localhost:8899. Backend + frontend in one container.

Docker publishes the backend on 127.0.0.1:8899 by default and runs the app as a non-root container user. If you intentionally expose the API beyond your own machine, set a strong API_AUTH_KEY and send Authorization: Bearer <key> from clients.

.venv\Scripts\Activate.ps1 # Windows PowerShell

pip install -e . cp agent/.env.example agent/.env # Edit — set your LLM provider API key vibe-trading # Launch interactive TUI


<details>
<summary><b>Start web UI (optional)</b></summary>
bash

🧠 Environment Variables

Copy agent/.env.example to agent/.env and uncomment the provider block you want. Each provider needs 3-4 variables:

VariableRequiredDescription
LANGCHAIN_PROVIDERYesProvider name (openrouter, deepseek, groq, ollama, etc.)
<PROVIDER>_API_KEYYes*API key (OPENROUTER_API_KEY, DEEPSEEK_API_KEY, etc.)
<PROVIDER>_BASE_URLYesAPI endpoint URL
LANGCHAIN_MODEL_NAMEYesModel name (e.g. deepseek-v4-pro)
TUSHARE_TOKENNoTushare Pro token for A-share data (falls back to AKShare)
TIMEOUT_SECONDSNoLLM call timeout, default 120s
API_AUTH_KEYRecommended for network deploymentsBearer token required when the API is reachable from non-local clients
VIBE_TRADING_ENABLE_SHELL_TOOLSNoExplicit opt-in for shell-capable tools in remote API/MCP-SSE style deployments
VIBE_TRADING_ALLOWED_FILE_ROOTSNoExtra comma-separated roots for document and broker-journal imports
VIBE_TRADING_ALLOWED_RUN_ROOTSNoExtra comma-separated roots for generated-code run directories

<sub>* Ollama does not require an API key. OpenAI Codex uses ChatGPT OAuth and stores tokens via oauth-cli-kit, not in agent/.env.</sub>

Free data (no key needed): A-shares via AKShare, HK/US equities via yfinance, crypto via OKX, 100+ crypto exchanges via CCXT. The system automatically selects the best available source for each market.

Web UI Settings

The Web UI Settings page lets local users update the LLM provider/model, base URL, generation parameters, reasoning effort, and optional market data credentials such as the Tushare token. Settings are persisted to agent/.env; provider defaults are loaded from agent/src/providers/llm_providers.json.

Settings reads are side-effect free: GET /settings/llm and GET /settings/data-sources never create agent/.env, and they only return project-relative paths. Settings reads and writes can expose credential state or update credentials/runtime environment, so they require API_AUTH_KEY when configured. If API_AUTH_KEY is unset for dev mode, settings access is accepted only from loopback clients.

---

Config reference

FieldTypeDefaultDescription
typestringinferred for stdio; required for HTTPOmit for stdio, or set to sse / streamableHttp for URL-based servers.
commandstringrequired for stdioExecutable to spawn for stdio servers. Invalid for sse / streamableHttp servers.
argsarray[]Command-line arguments for stdio servers only.
envobject{}Extra environment variables merged into the subprocess env for stdio servers only.
urlstringrequired for sse / streamableHttpRemote SSE / streamable HTTP endpoint URL. Not used for stdio servers.
headersobject{}Extra HTTP headers for sse / streamableHttp servers only.
toolTimeoutnumber30Per-tool call timeout in seconds
enabledToolsarray["*"]Tool allowlist. Use ["*"] to expose all tools from the server

Config file location: ~/.vibe-trading/agent.json (JSON or YAML).

For URL-based transports, type is required. The agent no longer guesses between SSE and streamable HTTP from the URL suffix.

Terminal 1: API server

vibe-trading serve --port 8899

🖥 CLI Reference

The interactive TUI (vibe-trading) now uses a terminal-native transcript: a startup banner, prompt rule, previous-turn recap, live activity rail, Markdown/table rendering, and run timing all stay in the CLI. Non-interactive invocations such as vibe-trading run, pipes, and --json remain script-friendly.

vibe-trading               # interactive TUI
vibe-trading run -p "..."  # single run
vibe-trading serve         # API server
vibe-trading alpha list    # browse 452 pre-built alphas; show / bench / compare / export-manifest sub-commands available

<details> <summary><b>Slash commands inside TUI</b></summary>

CommandDescription
/helpShow all commands
/skillsList all 77 finance skills
/swarmList 29 swarm team presets
/swarm run <preset> [vars_json]Run a swarm team with live streaming
/swarm listSwarm run history
/swarm show <run_id>Swarm run details
/swarm cancel <run_id>Cancel a running swarm
/listRecent runs
/show <run_id>Run details + metrics
/code <run_id>Generated strategy code
/pine <run_id>Export indicators (TradingView + TDX + MT5)
/trace <run_id>Full execution replay
/continue <run_id> <prompt>Continue a run with new instructions
/sessionsList chat sessions
/settingsShow runtime config
/clearClear screen
/quitExit

</details>

<details> <summary><b>Single run & flags</b></summary>

vibe-trading run -p "Backtest BTC-USDT MACD strategy, last 30 days"
vibe-trading run -p "Analyze AAPL momentum" --json
vibe-trading run -f strategy.txt
echo "Backtest 000001.SZ RSI" | vibe-trading run
vibe-trading -p "your prompt"
vibe-trading --skills
vibe-trading --swarm-presets
vibe-trading --swarm-run investment_committee '{"topic":"BTC outlook"}'
vibe-trading --list
vibe-trading --show <run_id>
vibe-trading --code <run_id>
vibe-trading --pine <run_id>           # Export indicators (TradingView + TDX + MT5)
vibe-trading --trace <run_id>
vibe-trading --continue <run_id> "refine the strategy"
vibe-trading --upload report.pdf
vibe-trading alpha list --zoo gtja191 --limit 10
vibe-trading alpha show gtja191_171
vibe-trading alpha bench --zoo gtja191 --universe csi300 --period 2018-2025 --top 20

</details>

---

Save your preferences once

vibe-trading run -p "Remember: I prefer RSI-based strategies, max 10% drawdown, hold period 5–20 days"

🌐 API Server

vibe-trading serve --port 8899
MethodEndpointDescription
GET/runsList runs
GET/runs/{run_id}Run details
GET/runs/{run_id}/pineMulti-platform indicator export
POST/sessionsCreate session
POST/sessions/{id}/messagesSend message
GET/sessions/{id}/eventsSSE event stream
POST/uploadUpload PDF/file
GET/swarm/presetsList swarm presets
POST/swarm/runsStart swarm run
GET/swarm/runs/{id}/eventsSwarm SSE stream
GET/alpha/listList alphas (filter by zoo/theme/universe)
GET/alpha/{alpha_id}Alpha metadata + source code
POST/alpha/benchStart a bench job (returns job_id)
GET/alpha/bench/{job_id}/streamSSE progress stream
GET/settings/llmRead Web UI LLM settings
PUT/settings/llmUpdate local LLM settings
GET/settings/data-sourcesRead local data source settings
PUT/settings/data-sourcesUpdate local data source settings

Interactive docs: http://localhost:8899/docs

Per-session overrides (API)

When creating a session via the API you can pass mcpServers inside session.config to extend or override the global config for that session only:

{
  "config": {
    "mcpServers": {
      "research-server": {
        "command": "uvx",
        "args": ["research-mcp"],
        "enabledTools": ["search", "fetch"]
      }
    }
  }
}

🧪 Research Workflow

Most runs follow the same evidence path: route the request, load the right market context, execute tools, validate outputs, and keep the artifacts inspectable.

LayerWhat happens
**Plan**Selects the relevant finance skills, tools, data sources, and swarm preset when useful.
**Ground**Pulls A-shares, HK/US equities, crypto, futures, forex, documents, or web context through the available loaders.
**Execute**Generates testable strategy code, runs tools, and uses the matching backtest engine or analysis workflow.
**Validate**Adds metrics, benchmark comparison, Monte Carlo, Bootstrap, Walk-Forward, run cards, and warnings where applicable.
**Deliver**Returns reports, artifacts, tool traces, and exports for TradingView, TDX, MetaTrader 5, MCP clients, or later sessions.

---

Path C: MCP plugin

See MCP Plugin section below.

Swarm Workflows

```bash

🔌 MCP Plugin

Vibe-Trading exposes 22 MCP tools for any MCP-compatible client. Runs as a stdio subprocess — no server setup needed. 21 of 22 tools work with zero API keys (HK/US/crypto). Only run_swarm needs an LLM key.

<details> <summary><b>Claude Desktop</b></summary>

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "vibe-trading": {
      "command": "vibe-trading-mcp"
    }
  }
}

</details>

<details> <summary><b>OpenClaw</b></summary>

Add to ~/.openclaw/config.yaml:

skills:
  - name: vibe-trading
    command: vibe-trading-mcp

</details>

<details> <summary><b>Cursor / Windsurf / other MCP clients</b></summary>

vibe-trading-mcp                  # stdio (default)
vibe-trading-mcp --transport sse  # SSE for web clients

</details>

MCP tools exposed (22): list_skills, load_skill, backtest, factor_analysis, analyze_options, pattern_recognition, get_market_data, web_search, read_url, read_document, read_file, write_file, analyze_trade_journal, extract_shadow_strategy, run_shadow_backtest, render_shadow_report, scan_shadow_signals, list_swarm_presets, run_swarm, get_swarm_status, get_run_result, list_runs.

<details> <summary><b>Install from ClawHub (one command)</b></summary>

npx clawhub@latest install vibe-trading --force
--force is required because the skill references external APIs, which triggers VirusTotal's automated scan. The code is fully open-source and safe to inspect.

This downloads the skill + MCP config into your agent's skills directory. No cloning needed.

Browse on ClawHub: clawhub.ai/skills/vibe-trading

</details>

<details> <summary><b>OpenSpace — self-evolving skills</b></summary>

All 77 finance skills are published on open-space.cloud and evolve autonomously through OpenSpace's self-evolution engine.

To use with OpenSpace, add both MCP servers to your agent config:

{
  "mcpServers": {
    "openspace": {
      "command": "openspace-mcp",
      "toolTimeout": 600,
      "env": {
        "OPENSPACE_HOST_SKILL_DIRS": "/path/to/vibe-trading/agent/src/skills",
        "OPENSPACE_WORKSPACE": "/path/to/OpenSpace"
      }
    },
    "vibe-trading": {
      "command": "vibe-trading-mcp"
    }
  }
}

OpenSpace will auto-discover all 77 skills, enabling auto-fix, auto-improve, and community sharing. Search for Vibe-Trading skills via search_skills("finance backtest") in any OpenSpace-connected agent.

</details>

---

🇨🇳 中文文档镜像 AI 翻译 2026-05-28
英文原文章节由系统翻译为中文摘要,便于快速理解。完整原文见上方 "📑 README 深度解析"。
📌 简介

Vibe-Trading 是您的个人交易智能体(Trading Agent)。通过简单的指令,即可赋予 Agent 强大的市场分析与策略执行能力,让复杂的金融研究变得触手可及。

⚡ 功能介绍

本项目具备自我进化的交易智能体能力,支持通过自然语言进行市场研究、策略草拟及文件生成。内置强大的 Finance Skill Library,包含 8 个类别、共 77 项专业金融技能,覆盖从传统市场到 Crypto 及 DeFi 的全方位能力。

📋 环境依赖

运行本项目需要准备好支持的 LLM API key,或者使用 Ollama 进行本地部署。若选择本地安装(Path B),需确保 Python 版本为 3.11+;若选择 Docker 部署(Path A),则需安装 Docker 环境。此外,也支持通过 ChatGPT OAuth 使用 OpenAI Codex。

🛠 安装步骤(Docker/pip/源码)

提供多种安装方式:1. 通过 PyPI 一键安装:`pip install vibe-trading-ai`;2. Docker 部署(零配置):克隆仓库并使用 `docker compose up --build`;3. 本地源码安装:克隆仓库后创建 `.venv` 虚拟环境并执行 `pip install -e .`。

🚀 使用教程

安装完成后,您可以使用 `vibe-trading` 命令启动交互式 TUI 界面进行任务。也可以通过 `vibe-trading run -p "任务描述"` 执行非交互式指令(如回测策略)。系统支持记忆您的偏好,例如通过指令设定风险控制参数,实现个性化交易体验。

⚙️ 配置说明(含 MCP / env)

项目通过 `agent/.env` 文件进行配置。您需要根据需求取消注释对应的 LLM provider 并设置相应的 API key。若使用 Docker 部署,后端默认运行在 `127.0.0.1:8899`。若需在公网暴露 API,请务必设置强密码级的 `API_AUTH_KEY` 以确保安全。

🔌 API 说明

本项目提供灵活的接口调用方式。支持通过 `vibe-trading serve --port 8899` 启动 API 服务器。交互式 TUI 具备原生终端渲染能力,支持 Markdown 和表格展示;而对于脚本化调用,可通过 `--json` 参数获取结构化输出。

🔄 工作流/模块

系统采用严谨的研究工作流:首先进行 Plan 阶段,智能体根据请求选择相关的 Finance Skills、工具及数据源;随后执行工具并加载市场上下文;最后通过验证输出并生成可供检查的 Artifacts(研究产物),确保每一步决策都有据可查。

🎯 aiskill88 AI 点评 A 级 2026-05-16

融合LLM与量化交易的创新工具,MCP框架设计合理,功能完整,星数高表明认可度好,但交易类应用需谨慎对待。

📚 实用指南(长尾问题)
适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC,避免暴露公网
常见错误
  • API key 直接提交到 git 仓库(请用 .env 并加入 .gitignore)
  • MCP 配置路径拼错或权限不足,重启 Claude Desktop 才生效
  • Python 依赖冲突:建议用 venv / uv 隔离环境
部署方案
  • 云端托管:可放在 Vercel / Railway / Fly.io 等 PaaS 平台

⚡ 核心功能

  • 开源免费,支持本地部署,数据完全自主可控
  • 活跃的 GitHub 开源社区,持续迭代更新
  • 提供详细文档和使用示例,新手友好
  • 支持自定义配置,灵活适配不同使用环境
  • 可作为基础组件集成进现有技术栈或进行二次开发
👥 适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
⭐ 最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC,避免暴露公网
⚠️ 常见错误
  • API key 直接提交到 git 仓库(请用 .env 并加入 .gitignore)
  • MCP 配置路径拼错或权限不足,重启 Claude Desktop 才生效
  • Python 依赖冲突:建议用 venv / uv 隔离环境

👥 适合人群

AI 技术爱好者研究人员和学生开发者和工程师技术创业者

🎯 使用场景

  • 本地部署运行,保护数据隐私,满足合规要求
  • 自定义集成到现有系统,扩展技术栈能力
  • 作为开源基础组件进行商业化二次开发

⚖️ 优点与不足

✅ 优点
  • +GitHub 7.2k Star,社区高度认可
  • +MIT 协议,可免费商用
  • +完全开源免费,无授权费用
  • +本地部署,数据完全自主可控
  • +开发者社区支持,遇问题可查可问
⚠️ 不足
  • 安装和初始配置可能需要一定技术基础
  • 功能完整性通常不如成熟商业产品
  • 技术支持主要依赖开源社区,响应速度不稳定
⚠️ 使用须知

AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。

建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。

📄 License 说明

✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。

❓ 常见问题 FAQ

支持股票、期货、加密货币等多个市场,具体支持情况需查看官方文档。
💡 AI Skill Hub 点评

AI Skill Hub 点评:Vibe交易智能体 的核心功能完整,质量良好。对于AI爱好者来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。

📚 深入学习 Vibe交易智能体
查看分步骤安装教程和完整使用指南,快速上手这款工具
🌐 原始信息
原始名称 Vibe-Trading
原始描述 开源MCP工具:"Vibe-Trading: Your Personal Trading Agent"。⭐7.2k · Python
Topics 交易自动化算法交易MCP工具量化回测LLM应用
GitHub https://github.com/HKUDS/Vibe-Trading
License MIT
语言 Python
🔗 原始来源
🐙 GitHub 仓库  https://github.com/HKUDS/Vibe-Trading 🌐 官方网站  https://pypi.org/project/vibe-trading-ai/

收录时间:2026-05-13 · 更新时间:2026-05-16 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。