@@ -436,6 +464,7 @@ Vibe-Trading은 tool-heavy agent입니다. skills, backtests, memory, swarms가
vibe-trading # interactive TUI
vibe-trading run -p "..." # single run
vibe-trading serve # API server
+vibe-trading alpha list # 사전 빌드된 452개 alpha 탐색; show / bench / compare / export-manifest 서브커맨드 사용 가능
```
@@ -444,7 +473,7 @@ vibe-trading serve # API server
| Command | Description |
|---------|-------------|
| `/help` | 모든 명령 표시 |
-| `/skills` | 74개 finance skills 목록 |
+| `/skills` | 75개 finance skills 목록 |
| `/swarm` | 29개 swarm team presets 목록 |
| `/swarm run [vars_json]` | live streaming으로 swarm team 실행 |
| `/swarm list` | Swarm run history |
@@ -487,6 +516,12 @@ vibe-trading --continue "refine the strategy"
vibe-trading --upload report.pdf
```
+```bash
+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
+```
+
---
@@ -509,6 +544,25 @@ vibe-trading run -p "Backtest a momentum + value + quality multi-factor strategy
vibe-trading --pine
```
+**한 줄로 사전 빌드된 alpha zoo 벤치하기**:
+```bash
+vibe-trading alpha bench --zoo gtja191 --universe csi300 --period 2018-2025 --top 20
+```
+
+**카탈로그 탐색** 후 단일 alpha 확인:
+```bash
+vibe-trading alpha list --zoo gtja191 --theme reversal --limit 10
+vibe-trading alpha show gtja191_171
+```
+
+**zoo 인자들로 다인자 신호 구성**(Python):
+```python
+from src.skills.multi_factor.zoo_signal_engine import ZooSignalEngine
+engine = ZooSignalEngine.from_zoo(["gtja191_171", "gtja191_111", "gtja191_163"])
+panel = ... # your wide OHLCV panel
+signal = engine.compute_signal(panel)
+```
+
### 시장 리서치
```bash
@@ -579,6 +633,10 @@ vibe-trading serve --port 8899
| `GET` | `/swarm/presets` | swarm presets 목록 |
| `POST` | `/swarm/runs` | swarm run 시작 |
| `GET` | `/swarm/runs/{id}/events` | Swarm SSE stream |
+| `GET` | `/alpha/list` | zoo/theme/universe로 alpha 목록 필터링 |
+| `GET` | `/alpha/{alpha_id}` | Alpha 메타데이터 + 소스 코드 |
+| `POST` | `/alpha/bench` | Bench 작업 시작 (`job_id` 반환) |
+| `GET` | `/alpha/bench/{job_id}/stream` | SSE 진행 스트림 |
| `GET` | `/settings/llm` | Web UI LLM settings 읽기 |
| `PUT` | `/settings/llm` | local LLM settings 업데이트 |
| `GET` | `/settings/data-sources` | local data source settings 읽기 |
@@ -664,7 +722,7 @@ ClawHub에서 보기: [clawhub.ai/skills/vibe-trading](https://clawhub.ai/skills
OpenSpace — 자가 진화 스킬
-74개 finance skills는 모두 [open-space.cloud](https://open-space.cloud)에 게시되어 있으며 OpenSpace의 self-evolution engine을 통해 자율적으로 발전합니다.
+75개 finance skills는 모두 [open-space.cloud](https://open-space.cloud)에 게시되어 있으며 OpenSpace의 self-evolution engine을 통해 자율적으로 발전합니다.
OpenSpace와 함께 사용하려면 두 MCP server를 agent config에 추가하세요:
@@ -686,7 +744,7 @@ OpenSpace와 함께 사용하려면 두 MCP server를 agent config에 추가하
}
```
-OpenSpace는 74개 skills를 모두 자동 발견하여 auto-fix, auto-improve, community sharing을 활성화합니다. OpenSpace-connected agent에서 `search_skills("finance backtest")`로 Vibe-Trading skills를 검색하세요.
+OpenSpace는 75개 skills를 모두 자동 발견하여 auto-fix, auto-improve, community sharing을 활성화합니다. OpenSpace-connected agent에서 `search_skills("finance backtest")`로 Vibe-Trading skills를 검색하세요.
@@ -708,7 +766,7 @@ Vibe-Trading/
│ │ ├── agent/ # ReAct agent core
│ │ │ ├── loop.py # 5-layer compression + read/write tool batching
│ │ │ ├── context.py # system prompt + auto-recall from persistent memory
-│ │ │ ├── skills.py # skill loader (74 bundled + user-created via CRUD)
+│ │ │ ├── skills.py # skill loader (75 bundled + user-created via CRUD)
│ │ │ ├── tools.py # tool base class + registry
│ │ │ ├── memory.py # lightweight workspace state per run
│ │ │ ├── frontmatter.py # shared YAML frontmatter parser
@@ -717,16 +775,25 @@ Vibe-Trading/
│ │ ├── memory/ # Cross-session persistent memory
│ │ │ └── persistent.py # file-based memory (~/.vibe-trading/memory/)
│ │ │
-│ │ ├── tools/ # 29 auto-discovered agent tools
+│ │ ├── tools/ # 31 auto-discovered agent tools
│ │ │ ├── backtest_tool.py # run backtests
│ │ │ ├── remember_tool.py # cross-session memory (save/recall/forget)
│ │ │ ├── skill_writer_tool.py # skill CRUD (save/patch/delete/file)
│ │ │ ├── session_search_tool.py # FTS5 cross-session search
│ │ │ ├── swarm_tool.py # launch swarm teams
│ │ │ ├── web_search_tool.py # DuckDuckGo web search
-│ │ │ └── ... # bash, file I/O, factor analysis, options, etc.
+│ │ │ └── ... # bash, file I/O, factor analysis, options, alpha browser + bench, etc.
│ │ │
-│ │ ├── skills/ # 74 finance skills in 8 categories (SKILL.md each)
+│ │ ├── factors/ # Alpha Zoo — 4개 zoo에 걸친 452개 alpha
+│ │ │ ├── base.py # 19개 operator (rank/scale/ts_*/delta/decay_linear/safe_div/vwap)
+│ │ │ ├── registry.py # AST-only 메타데이터 로딩 + lazy compute + sanity gate
+│ │ │ ├── bench_runner.py # IC + alive/reversed/dead 분류
+│ │ │ └── zoo/ # qlib158 (154) + alpha101 (101) + gtja191 (191) + academic (6)
+│ │ │
+│ │ ├── api/ # FastAPI 라우트 모듈
+│ │ │ └── alpha_routes.py # /alpha/list, /alpha/{id}, /alpha/bench, SSE stream
+│ │ │
+│ │ ├── skills/ # 75 finance skills in 8 categories (SKILL.md each)
│ │ ├── swarm/ # Swarm DAG execution engine
│ │ │ └── presets/ # 29 swarm preset YAML definitions
│ │ ├── session/ # Multi-turn chat + FTS5 session search
@@ -741,13 +808,15 @@ Vibe-Trading/
│
├── frontend/ # Web UI (React 19 + Vite + TypeScript)
│ └── src/
-│ ├── pages/ # Home, Agent, RunDetail, Compare
+│ ├── pages/ # Home, Agent, AlphaZoo, RunDetail, Compare, Correlation, Settings
│ ├── components/ # chat, charts, layout
│ └── stores/ # Zustand state management
│
├── Dockerfile # Multi-stage build
├── docker-compose.yml # One-command deploy
├── pyproject.toml # Package config + CLI entrypoint
+├── tools/ # 레포 단위 CI helper
+│ └── ci_grep_gates.sh # yaml.load / 트레이드마크 / 종목별 데이터 누출 차단
└── LICENSE # MIT
```
@@ -794,7 +863,7 @@ Vibe-Trading은 **[HKUDS](https://github.com/HKUDS)** agent ecosystem의 일부
| **Data Bridge** | Bring-your-own data: local CSV/Parquet/SQL connectors with schema mapping | Planned |
| **Options Lab** | Vol surface, Greeks dashboard, payoff/scenario explorer | Planned |
| **Portfolio Studio** | Risk x-ray, constraints, turnover-aware optimizer, rebalance notes | Planned |
-| **Alpha Zoo** | Alpha101 / Alpha158 / Alpha191 factor libraries with screening + IC tests | Planned |
+| **Alpha Zoo** | 4개 zoo에 걸친 452개의 사전 빌드된 alpha 인자(Qlib 158 + Kakushadze 101 + GTJA 191 + FF5 + Carhart), 한 줄 CLI 벤치, agent 통합, Web UI | **0.1.8 출시 완료** |
| **Research Delivery** | Slack / Telegram / email-style channels로 예약 brief 전달 | Planned |
| **Community** | 공유 가능한 skills, presets, strategy cards | Exploring |
diff --git a/README_zh.md b/README_zh.md
index df81ef93..3dae3d31 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -46,13 +46,14 @@
## 📰 News
+- **2026-05-17** 🧬 **Alpha Zoo v1（0.1.8）**：内置 452 个量化 alpha，覆盖 4 个 zoo —— `qlib158`（Microsoft Qlib 的 Alpha158 特征，Apache-2.0 出处声明）、`alpha101`（Kakushadze 的 "101 Formulaic Alphas"，从 arXiv:1601.00991 论文公式重写）、`gtja191`（国君证券 2014 短周期交易型因子研报）、`academic`（Fama-French 5 因子 + Carhart 动量的价格代理实现）。一行 CLI 就能在自己的 universe 上跑横评：`vibe-trading alpha bench --zoo gtja191 --universe csi300 --period 2018-2025`。配套设施包括 AST 纯函数门禁、lookahead 防护测试、`pytest-socket` 网络隔离、每个 zoo 一份 LICENSE.md、社区贡献用的 DCO 签名流程；Alpha Library 自动渲染上线 [vibetrading.wiki/alpha-library/](https://vibetrading.wiki/alpha-library/)；Research Lab 同步发布 [《191 个 GTJA alpha 哪些在 2026 还能用》](https://vibetrading.wiki/research-lab/posts/alpha-191-in-2026.html)。
- **2026-05-16** 🧪 **研究主干更新**：新增后端 Hypothesis Registry，提供 `create_hypothesis`、`update_hypothesis`、`link_backtest`、`search_hypotheses`；外部内容读取工具现在会附加 warning-only 的 `security_warnings`；Shadow Account 扫描也从旧的日历 phase stub 升级为确定性的 OHLCV 特征评估。
- **2026-05-15** 🪪 Run 详情页现在会在 metrics 和 artifacts 旁边渲染 Trust Layer 的 run card，把 2026-05-12 已落地的 `run_card.json` 工作补齐到 UI 一侧。`PersistentMemory.add()` 也根据 #108/#109/#110 的 triage，在长度限制、空 / 纯空白 name、以及 C0/C1 控制字节三条路径上做了加固（[#112](https://github.com/HKUDS/Vibe-Trading/pull/112)，感谢 @Teerapat-Vatpitak）。
-- **2026-05-14** 🌐 公开 Wiki 已上线 [vibetrading.wiki](https://vibetrading.wiki/)，包含 docs、tutorials、Research Lab 和 Alpha Library，并通过 Cloudflare Pages 部署。持久记忆也可以通过 CLI 使用 `vibe-trading memory list/show/search/forget` 检查（[#102](https://github.com/HKUDS/Vibe-Trading/pull/102)，感谢 @Teerapat-Vatpitak）；记忆 tokenizer/slug 现在支持泰语、阿拉伯语、希伯来语和西里尔文字（[#104](https://github.com/HKUDS/Vibe-Trading/pull/104)）。
更早的更新
+- **2026-05-14** 🌐 公开 Wiki 已上线 [vibetrading.wiki](https://vibetrading.wiki/)，包含 docs、tutorials、Research Lab 和 Alpha Library，并通过 Cloudflare Pages 部署。持久记忆也可以通过 CLI 使用 `vibe-trading memory list/show/search/forget` 检查（[#102](https://github.com/HKUDS/Vibe-Trading/pull/102)，感谢 @Teerapat-Vatpitak）；记忆 tokenizer/slug 现在支持泰语、阿拉伯语、希伯来语和西里尔文字（[#104](https://github.com/HKUDS/Vibe-Trading/pull/104)）。
- **2026-05-13** 🧭 Swarm 运行现在会用已获取的市场数据为 worker 提供依据，并生成更清晰的持久化报告（[#93](https://github.com/HKUDS/Vibe-Trading/pull/93)，[#84](https://github.com/HKUDS/Vibe-Trading/pull/84)）。
- **2026-05-12** 🧾 回测现在会随 artifacts 一起输出 `run_card.json` 和 `run_card.md`，便于复现实验研究。
- **2026-05-11** 🧭 **记忆 slug、swarm 统计与 CLI 预检**：持久记忆在生成文件 slug 时会保留 CJK 字符，避免中文/日文/韩文笔记发生静默文件名冲突（[#95](https://github.com/HKUDS/Vibe-Trading/pull/95)，感谢 @voidborne-d）。Swarm 运行总量现在优先采用 provider 返回的 token 用量，并保留原有估算作为 fallback（[#94](https://github.com/HKUDS/Vibe-Trading/pull/94)，感谢 @Teerapat-Vatpitak）。CLI 运行界面也新增了启动预检，用于发现常见环境问题（[#96](https://github.com/HKUDS/Vibe-Trading/pull/96)，感谢 @ykykj）。
@@ -154,6 +155,7 @@ Vibe-Trading 是一个开源研究工作台，用于把金融问题转化为可
| **改进重复研究** | 持久记忆和可编辑 skills 将有用流程变成可复用工作流。 |
| **运行分析师团队** | 面向投资、量化、加密、宏观和风控工作流的多智能体研究评审。 |
| **交付可用成果** | 报告、TradingView Pine Script、TDX、MetaTrader 5、MCP tools，以及可延续的研究 sessions。 |
+| **跑预置 alpha zoo 横评** | 452 个 alpha 因子（Qlib 158 + Kakushadze 101 + GTJA 191 + FF5 + Carhart），一行 CLI 在你选的 universe 上算 IC + IR + alive/reversed/dead 分类 |
---
@@ -161,7 +163,12 @@ Vibe-Trading 是一个开源研究工作台，用于把金融问题转化为可
```bash
pip install vibe-trading-ai
+
+# 自然语言研究
vibe-trading run -p "Backtest a BTC-USDT 20/50 moving-average strategy for 2024, summarize return and drawdown, then export the report"
+
+# 一行 CLI 跑预置 alpha zoo 横评
+vibe-trading alpha bench --zoo gtja191 --universe csi300 --period 2018-2025 --top 20
```
```bash
@@ -211,9 +218,9 @@ vibe-trading run -p "Analyze my trading behavior, extract my shadow strategy, an
为保持主 README 易读，详细清单折叠在下方。需要检查可用构件时可展开查看。
-Finance Skill Library 8 个类别中的 74 个 skills
+Finance Skill Library 8 个类别中的 75 个 skills
-- 📊 74 个专业金融 skills，分布在 8 个类别中
+- 📊 75 个专业金融 skills，分布在 8 个类别中
- 🌐 覆盖传统市场、加密与 DeFi
- 🔬 从数据源到量化研究的完整能力链路
@@ -225,7 +232,7 @@ vibe-trading run -p "Analyze my trading behavior, extract my shadow strategy, an
| Asset Class | 9 | `options-strategy`, `options-advanced`, `convertible-bond`, `etf-analysis`, `asset-allocation`, `sector-rotation` |
| Crypto | 7 | `perp-funding-basis`, `liquidation-heatmap`, `stablecoin-flow`, `defi-yield`, `onchain-analysis` |
| Flow | 7 | `hk-connect-flow`, `us-etf-flow`, `edgar-sec-filings`, `financial-statement`, `adr-hshare` |
-| Tool | 10 | `backtest-diagnose`, `report-generate`, `pine-script`, `doc-reader`, `web-reader`, `vnpy-export` |
+| Tool | 11 | `backtest-diagnose`, `report-generate`, `pine-script`, `doc-reader`, `web-reader`, `vnpy-export`, `alpha-zoo` |
| Risk Analysis | 1 | `ashare-pre-st-filter` |
@@ -255,6 +262,26 @@ vibe-trading run -p "Analyze my trading behavior, extract my shadow strategy, an
+
+Alpha Zoo 452 个预置 alpha，覆盖 4 个 zoo
+
+- 🧬 452 个横截面 alpha，算子层即禁用 lookahead
+- 📈 一条 CLI 命令完成 IC + IR + alive/reversed/dead 分类
+- 🔬 AST 纯函数门禁 + 300 行 lookahead 哨兵测试 + `pytest-socket` 网络阻断
+- 📦 Qlib 部分附 Apache-2 出处声明；每个 zoo 一份 `LICENSE.md`，声明公式属于数学内容
+- 🤝 社区 PR 走 Developer Certificate of Origin (DCO) 签名流程
+
+| Zoo | 数量 | 来源 | 许可 |
+|-----|------|------|------|
+| **qlib158** | 154 | Microsoft Qlib `Alpha158`（Apache-2.0，锁定 commit） | Apache-2.0 |
+| **alpha101** | 101 | Kakushadze (2015), "101 Formulaic Alphas", arXiv:1601.00991 | 公式属于数学内容 |
+| **gtja191** | 191 | 国君证券 (2014)《191 个短周期交易型 alpha 因子》研报 | 公式属于数学内容 |
+| **academic** | 6 | Fama-French 5 因子 + Carhart 动量（基于价格的代理实现） | 公开学术文献 |
+
+运行 `vibe-trading alpha list` 浏览全部因子，`vibe-trading alpha show ` 查看公式与源码，`vibe-trading alpha bench --zoo X --universe Y --period Z` 给一整个 zoo 打分。
+
+
+
## 🎬 Demo
@@ -436,6 +463,7 @@ Vibe-Trading 是高度依赖工具的智能体：skills、backtests、memory 和
vibe-trading # interactive TUI
vibe-trading run -p "..." # single run
vibe-trading serve # API server
+vibe-trading alpha list # 浏览 452 个预置 alpha；支持 show / bench / compare / export-manifest 子命令
```
@@ -444,7 +472,7 @@ vibe-trading serve # API server
| 命令 | 说明 |
|------|------|
| `/help` | 显示所有命令 |
-| `/skills` | 列出全部 74 个 finance skills |
+| `/skills` | 列出全部 75 个 finance skills |
| `/swarm` | 列出 29 个 swarm team presets |
| `/swarm run [vars_json]` | 运行一个 swarm team，并实时流式展示 |
| `/swarm list` | Swarm 运行历史 |
@@ -485,6 +513,9 @@ vibe-trading --pine # Export indicators (TradingView + TDX +
vibe-trading --trace
vibe-trading --continue "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
```
@@ -509,6 +540,25 @@ vibe-trading run -p "Backtest a momentum + value + quality multi-factor strategy
vibe-trading --pine
```
+**一行命令横评预置 alpha zoo**：
+```bash
+vibe-trading alpha bench --zoo gtja191 --universe csi300 --period 2018-2025 --top 20
+```
+
+**浏览目录** + 查看单个 alpha：
+```bash
+vibe-trading alpha list --zoo gtja191 --theme reversal --limit 10
+vibe-trading alpha show gtja191_171
+```
+
+**用 zoo 因子组合多因子信号**（Python）：
+```python
+from src.skills.multi_factor.zoo_signal_engine import ZooSignalEngine
+engine = ZooSignalEngine.from_zoo(["gtja191_171", "gtja191_111", "gtja191_163"])
+panel = ... # your wide OHLCV panel
+signal = engine.compute_signal(panel)
+```
+
### Market Research
```bash
@@ -579,6 +629,10 @@ vibe-trading serve --port 8899
| `GET` | `/swarm/presets` | 列出 swarm presets |
| `POST` | `/swarm/runs` | 启动 swarm run |
| `GET` | `/swarm/runs/{id}/events` | Swarm SSE stream |
+| `GET` | `/alpha/list` | 按 zoo/theme/universe 过滤列出 alpha |
+| `GET` | `/alpha/{alpha_id}` | Alpha 元数据 + 源代码 |
+| `POST` | `/alpha/bench` | 启动一个 bench job（返回 `job_id`） |
+| `GET` | `/alpha/bench/{job_id}/stream` | SSE 进度流 |
| `GET` | `/settings/llm` | 读取 Web UI LLM settings |
| `PUT` | `/settings/llm` | 更新本地 LLM settings |
| `GET` | `/settings/data-sources` | 读取本地数据源 settings |
@@ -664,7 +718,7 @@ npx clawhub@latest install vibe-trading --force
OpenSpace — 自进化 skills
-全部 74 个 finance skills 都发布在 [open-space.cloud](https://open-space.cloud)，并通过 OpenSpace 的自进化引擎自主演进。
+全部 75 个 finance skills 都发布在 [open-space.cloud](https://open-space.cloud)，并通过 OpenSpace 的自进化引擎自主演进。
要配合 OpenSpace 使用，请将两个 MCP servers 都加入你的 agent config：
@@ -686,7 +740,7 @@ npx clawhub@latest install vibe-trading --force
}
```
-OpenSpace 会自动发现全部 74 个 skills，启用 auto-fix、auto-improve 和社区分享。在任意已连接 OpenSpace 的智能体中，可通过 `search_skills("finance backtest")` 搜索 Vibe-Trading skills。
+OpenSpace 会自动发现全部 75 个 skills，启用 auto-fix、auto-improve 和社区分享。在任意已连接 OpenSpace 的智能体中，可通过 `search_skills("finance backtest")` 搜索 Vibe-Trading skills。
@@ -699,55 +753,66 @@ OpenSpace 会自动发现全部 74 个 skills，启用 auto-fix、auto-improve
```
Vibe-Trading/
-├── agent/ # Backend (Python)
-│ ├── cli.py # CLI entrypoint — interactive TUI + subcommands
-│ ├── api_server.py # FastAPI server — runs, sessions, upload, swarm, SSE
-│ ├── mcp_server.py # MCP server — 22 tools for OpenClaw / Claude Desktop
+├── agent/ # 后端（Python）
+│ ├── cli.py # CLI 入口 —— 交互式 TUI + 子命令
+│ ├── api_server.py # FastAPI server —— runs、sessions、upload、swarm、SSE
+│ ├── mcp_server.py # MCP server —— 22 个工具，面向 OpenClaw / Claude Desktop
│ │
│ ├── src/
-│ │ ├── agent/ # ReAct agent core
-│ │ │ ├── loop.py # 5-layer compression + read/write tool batching
-│ │ │ ├── context.py # system prompt + auto-recall from persistent memory
-│ │ │ ├── skills.py # skill loader (74 bundled + user-created via CRUD)
-│ │ │ ├── tools.py # tool base class + registry
-│ │ │ ├── memory.py # lightweight workspace state per run
-│ │ │ ├── frontmatter.py # shared YAML frontmatter parser
-│ │ │ └── trace.py # execution trace writer
+│ │ ├── agent/ # ReAct agent 内核
+│ │ │ ├── loop.py # 5 层上下文压缩 + 读/写工具批处理
+│ │ │ ├── context.py # system prompt + 持久记忆自动召回
+│ │ │ ├── skills.py # skill loader（75 个内置 + 通过 CRUD 创建的用户 skill）
+│ │ │ ├── tools.py # tool 基类 + 注册表
+│ │ │ ├── memory.py # 每个 run 的轻量 workspace 状态
+│ │ │ ├── frontmatter.py # 共享的 YAML frontmatter 解析器
+│ │ │ └── trace.py # 执行 trace 写入器
│ │ │
-│ │ ├── memory/ # Cross-session persistent memory
-│ │ │ └── persistent.py # file-based memory (~/.vibe-trading/memory/)
+│ │ ├── memory/ # 跨 session 持久记忆
+│ │ │ └── persistent.py # 基于文件的记忆（~/.vibe-trading/memory/）
│ │ │
-│ │ ├── tools/ # 29 auto-discovered agent tools
-│ │ │ ├── backtest_tool.py # run backtests
-│ │ │ ├── remember_tool.py # cross-session memory (save/recall/forget)
-│ │ │ ├── skill_writer_tool.py # skill CRUD (save/patch/delete/file)
-│ │ │ ├── session_search_tool.py # FTS5 cross-session search
-│ │ │ ├── swarm_tool.py # launch swarm teams
-│ │ │ ├── web_search_tool.py # DuckDuckGo web search
-│ │ │ └── ... # bash, file I/O, factor analysis, options, etc.
+│ │ ├── tools/ # 31 个自动发现的 agent 工具
+│ │ │ ├── backtest_tool.py # 运行回测
+│ │ │ ├── remember_tool.py # 跨 session 记忆（save/recall/forget）
+│ │ │ ├── skill_writer_tool.py # skill CRUD（save/patch/delete/file）
+│ │ │ ├── session_search_tool.py # FTS5 跨 session 搜索
+│ │ │ ├── swarm_tool.py # 启动 swarm team
+│ │ │ ├── web_search_tool.py # DuckDuckGo 网络搜索
+│ │ │ └── ... # bash、文件 I/O、因子分析、期权、alpha 浏览 + 横评等
│ │ │
-│ │ ├── skills/ # 74 finance skills in 8 categories (SKILL.md each)
-│ │ ├── swarm/ # Swarm DAG execution engine
-│ │ │ └── presets/ # 29 swarm preset YAML definitions
-│ │ ├── session/ # Multi-turn chat + FTS5 session search
-│ │ └── providers/ # LLM provider abstraction
+│ │ ├── factors/ # Alpha Zoo —— 4 个 zoo 共 452 个 alpha
+│ │ │ ├── base.py # 19 个算子（rank/scale/ts_*/delta/decay_linear/safe_div/vwap）
+│ │ │ ├── registry.py # 纯 AST 元数据加载 + 惰性计算 + sanity 校验
+│ │ │ ├── bench_runner.py # IC + alive/reversed/dead 分类
+│ │ │ └── zoo/ # qlib158 (154) + alpha101 (101) + gtja191 (191) + academic (6)
+│ │ │
+│ │ ├── api/ # FastAPI 路由模块
+│ │ │ └── alpha_routes.py # /alpha/list、/alpha/{id}、/alpha/bench、SSE 流
+│ │ │
+│ │ ├── skills/ # 8 个类别共 75 个 finance skills（每个一份 SKILL.md）
+│ │ ├── swarm/ # Swarm DAG 执行引擎
+│ │ │ └── presets/ # 29 个 swarm preset YAML 定义
+│ │ ├── session/ # 多轮对话 + FTS5 session 搜索
+│ │ └── providers/ # LLM provider 抽象层
│ │
-│ └── backtest/ # Backtest engines
-│ ├── engines/ # 7 engines + composite cross-market engine + options_portfolio
-│ ├── loaders/ # 6 sources: tushare, okx, yfinance, akshare, ccxt, futu
+│ └── backtest/ # 回测引擎
+│ ├── engines/ # 7 个引擎 + 跨市场 composite 引擎 + options_portfolio
+│ ├── loaders/ # 6 个数据源：tushare、okx、yfinance、akshare、ccxt、futu
│ │ ├── base.py # DataLoader Protocol
-│ │ └── registry.py # Registry + auto-fallback chains
-│ └── optimizers/ # MVO, equal vol, max div, risk parity
+│ │ └── registry.py # Registry + 自动 fallback 链路
+│ └── optimizers/ # MVO、equal vol、max div、risk parity
│
-├── frontend/ # Web UI (React 19 + Vite + TypeScript)
+├── frontend/ # Web UI（React 19 + Vite + TypeScript）
│ └── src/
-│ ├── pages/ # Home, Agent, RunDetail, Compare
-│ ├── components/ # chat, charts, layout
-│ └── stores/ # Zustand state management
+│ ├── pages/ # Home、Agent、AlphaZoo、RunDetail、Compare、Correlation、Settings
+│ ├── components/ # chat、charts、layout
+│ └── stores/ # Zustand 状态管理
│
-├── Dockerfile # Multi-stage build
-├── docker-compose.yml # One-command deploy
-├── pyproject.toml # Package config + CLI entrypoint
+├── Dockerfile # 多阶段构建
+├── docker-compose.yml # 一条命令部署
+├── pyproject.toml # 包配置 + CLI entrypoint
+├── tools/ # 仓库级 CI 辅助脚本
+│ └── ci_grep_gates.sh # 拦截 yaml.load / 商标 / 个股数据泄露
└── LICENSE # MIT
```
@@ -794,7 +859,7 @@ Vibe-Trading 是 **[HKUDS](https://github.com/HKUDS)** 智能体生态的一部
| **Data Bridge** | 自带数据：本地 CSV/Parquet/SQL connectors 与 schema mapping | Planned |
| **Options Lab** | Vol surface、Greeks dashboard、payoff/scenario explorer | Planned |
| **Portfolio Studio** | Risk x-ray、constraints、turnover-aware optimizer、rebalance notes | Planned |
-| **Alpha Zoo** | Alpha101 / Alpha158 / Alpha191 factor libraries，支持 screening + IC tests | Planned |
+| **Alpha Zoo** | 452 个预置 alpha 因子（Qlib 158 + Kakushadze 101 + GTJA 191 + FF5 + Carhart），一行 CLI 跑横评，agent 集成，Web UI 浏览 | **已发布 0.1.8** |
| **Research Delivery** | 定时 briefs 到 Slack / Telegram / email-style channels | Planned |
| **Community** | 可分享的 skills、presets 和 strategy cards | Exploring |
diff --git a/agent/SKILL.md b/agent/SKILL.md
index 192adef5..5010b9e3 100644
--- a/agent/SKILL.md
+++ b/agent/SKILL.md
@@ -1,7 +1,7 @@
---
name: vibe-trading
-version: 0.1.7
-description: Professional finance research toolkit — backtesting (7 engines + benchmark comparison panel), factor analysis, options pricing, 74 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest → render) across 6 data sources (tushare, yfinance, okx, akshare, ccxt, futu).
+version: 0.1.8
+description: 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, 75 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest → render) across 6 data sources (tushare, yfinance, okx, akshare, ccxt, futu).
dependencies:
python: ">=3.11"
pip:
@@ -23,7 +23,7 @@ mcp:
# Vibe-Trading
-Professional finance research toolkit with AI-powered backtesting (7 engines), multi-agent teams, 74 specialized skills, and the Shadow Account loop — extract your implicit trading rules from a journal, backtest them across A股/港股/美股/crypto, then see where they would have served you better.
+Professional finance research toolkit with AI-powered backtesting (7 engines), multi-agent teams, 75 specialized skills, the **Alpha Zoo** (452 pre-built quantitative alphas across qlib158 / alpha101 / gtja191 / academic with one-line CLI benchmarking), and the Shadow Account loop — extract your implicit trading rules from a journal, backtest them across A股/港股/美股/crypto, then see where they would have served you better.
## Setup
@@ -53,7 +53,7 @@ Add to your agent's MCP config:
### API Key Requirements
-**21 of 22 MCP tools work with zero API keys.** After `pip install`, backtesting, market data, factor analysis, options pricing, chart patterns, web search, document reading, trade journal analysis, shadow-account extraction/backtest/report, and all 74 skills are ready to use for HK/US equities and crypto.
+**21 of 22 MCP tools work with zero API keys.** After `pip install`, backtesting, market data, factor analysis, options pricing, chart patterns, web search, document reading, trade journal analysis, shadow-account extraction/backtest/report, the Alpha Zoo (452 pre-built alphas), and all 75 skills are ready to use for HK/US equities and crypto.
| Feature | Key needed | When |
|---------|-----------|------|
@@ -99,7 +99,16 @@ Example workflow:
Use `list_swarm_presets()` to see all teams, then `run_swarm()` to execute.
-### Finance Skills (74)
+### Alpha Zoo (452 pre-built alphas)
+One-line cross-sectional IC / IR / alive-reversed-dead categorisation across four bundled zoos:
+- **qlib158** (154 alphas) — Microsoft Qlib's `Alpha158` feature handler, Apache-2.0 with pinned commit SHA.
+- **alpha101** (101 alphas) — Kakushadze (2015) "101 Formulaic Alphas" (arXiv:1601.00991), written from the paper appendix.
+- **gtja191** (191 alphas) — Guotai Junan 2014 "191 Short-period Trading Alpha Factors" research report.
+- **academic** (6 factors) — Fama-French 5 + Carhart momentum (honest price-based proxies).
+
+Each alpha ships with `__alpha_meta__` (formula LaTeX + theme + universe + warmup + columns required), guarded by an AST purity gate + 300-row lookahead sentinel test. Use the `vibe-trading alpha {list,show,bench,compare,export-manifest}` CLI, the `/alpha/*` REST routes (browser at `/alpha-zoo`), or compose multi-factor signals via `ZooSignalEngine.from_zoo(...)`.
+
+### Finance Skills (75)
Comprehensive knowledge base covering:
- Technical analysis (candlestick, Elliott wave, Ichimoku, SMC, harmonic, chanlun)
- Quantitative methods (factor research, ML strategy, pair trading, multi-factor)
@@ -116,7 +125,7 @@ Use `load_skill(name)` to access full methodology docs with code templates.
| Tool | Description | API Key |
|------|-------------|---------|
-| `list_skills` | List all 74 finance skills | None |
+| `list_skills` | List all 75 finance skills | None |
| `load_skill` | Load full skill documentation | None |
| `backtest` | Run vectorized backtest engine | None* |
| `factor_analysis` | IC/IR analysis + layered backtest | None* |
@@ -147,7 +156,7 @@ Use `load_skill(name)` to access full methodology docs with code templates.
pip install vibe-trading-ai
```
-That's it — no API keys needed for HK/US/crypto markets. Start using `backtest`, `get_market_data`, `analyze_options`, `analyze_trade_journal`, `extract_shadow_strategy`, `web_search`, and all 74 skills immediately.
+That's it — no API keys needed for HK/US/crypto markets. Start using `backtest`, `get_market_data`, `analyze_options`, `analyze_trade_journal`, `extract_shadow_strategy`, `web_search`, the **Alpha Zoo** (`vibe-trading alpha bench --zoo gtja191 --universe csi300 --period 2018-2025`), and all 75 skills immediately.
## Loading Tools from External MCP Servers
diff --git a/pyproject.toml b/pyproject.toml
index aaf6aa12..e6bb8c20 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
[project]
name = "vibe-trading-ai"
-version = "0.1.7"
+version = "0.1.8"
description = "Natural-language finance research AI agent with backtesting"
requires-python = ">=3.11"
license = "MIT"
@@ -88,11 +88,13 @@ include = ["src*", "backtest*"]
"shadow_account/templates/*.css",
]
"backtest" = ["*.py"]
+"src.factors" = ["zoo/**/*.yaml", "zoo/**/*.md", "zoo/**/NOTICE"]
[project.optional-dependencies]
dev = [
"pytest>=7.0",
"pytest-cov>=4.0",
+ "pytest-socket>=0.7.0",
]
[tool.pytest.ini_options]
diff --git a/wiki/docs/content.js b/wiki/docs/content.js
index 473bf58b..77bb75b0 100644
--- a/wiki/docs/content.js
+++ b/wiki/docs/content.js
@@ -1,9 +1,10 @@
-export const DOCS_DEFAULT_VERSION = "0.1.7";
+export const DOCS_DEFAULT_VERSION = "0.1.8";
export const DOCS_LATEST_ALIAS = "latest";
export const DOCS_DEFAULT_PAGE = "getting-started/vibe-trading-overview";
export const DOCS_VERSIONS = [
- { name: "0.1.7", label: "0.1.7 (latest)" }
+ { name: "0.1.8", label: "0.1.8 (latest)" },
+ { name: "0.1.7", label: "0.1.7" }
];
export const DOCS_STRUCTURE = [