Crawler Summary

worldquant-alpha-crew answer-first brief

基于 CrewAI 的 WorldQuant Alpha 因子自动研究与回测系统 6个专业 AI 智能体协作 从研报到可验证公式的全自动流水线 支持网格搜索和智能优化 WorldQuant Alpha因子研究多智能体系统 6个专业AI智能体组成的自动化流水线,将研报自动加工成可验证的Alpha因子公式 $1 $1 $1 --- 🎯 核心架构 一个由7个专业AI智能体组成的流水线,像工厂一样将研报自动加工成可验证的Alpha因子公式。 智能体团队 | 智能体 | 角色 | 代码文件 | 职责 | |--------|------|----------|------| | 🕵️ **情报员** | 研报爬取 | research_crawler.py | 搜刮各类研报和策略文章,产出清洗好的文本材料 | | 📚 **合规官** | 数据管理 | data_manager.py | 掌握WorldQuant所有数据字段和操作符规范,产出权威的"语法词典" | | 🔄 **翻译官** | 策略分析 | strategy_analyst.py | 把研报文字转化成量化逻辑,产出清晰的量化策略描述 Capability contract not published. No trust telemetry is available yet. 13 GitHub stars reported by the source. Last updated 5/19/2026.

Freshness

Last checked 5/19/2026

Best For

worldquant-alpha-crew is best for crewai, multi-agent workflows where OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, GITHUB OPENCLEW, runtime-metrics, public facts pack

Claim this agent
Agent DossierGitHubSafety: 75/100

worldquant-alpha-crew

基于 CrewAI 的 WorldQuant Alpha 因子自动研究与回测系统 6个专业 AI 智能体协作 从研报到可验证公式的全自动流水线 支持网格搜索和智能优化 WorldQuant Alpha因子研究多智能体系统 6个专业AI智能体组成的自动化流水线,将研报自动加工成可验证的Alpha因子公式 $1 $1 $1 --- 🎯 核心架构 一个由7个专业AI智能体组成的流水线,像工厂一样将研报自动加工成可验证的Alpha因子公式。 智能体团队 | 智能体 | 角色 | 代码文件 | 职责 | |--------|------|----------|------| | 🕵️ **情报员** | 研报爬取 | research_crawler.py | 搜刮各类研报和策略文章,产出清洗好的文本材料 | | 📚 **合规官** | 数据管理 | data_manager.py | 掌握WorldQuant所有数据字段和操作符规范,产出权威的"语法词典" | | 🔄 **翻译官** | 策略分析 | strategy_analyst.py | 把研报文字转化成量化逻辑,产出清晰的量化策略描述

OpenClawself-declared

Public facts

6

Change events

1

Artifacts

0

Freshness

May 19, 2026

Verifiededitorial-contentNo verified compatibility signals13 GitHub stars

Capability contract not published. No trust telemetry is available yet. 13 GitHub stars reported by the source. Last updated 5/19/2026.

13 GitHub starsTrust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

May 19, 2026

Vendor

Xiao634zhang

Artifacts

0

Benchmarks

0

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Capability contract not published. No trust telemetry is available yet. 13 GitHub stars reported by the source. Last updated 5/19/2026.

Setup snapshot

git clone https://github.com/xiao634zhang/worldquant-alpha-crew.git
  1. 1

    Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.

  2. 2

    Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content
Vendor (1)

Vendor

Xiao634zhang

profilemedium
Observed May 12, 2026Source linkProvenance
Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium
Observed May 12, 2026Source linkProvenance
Adoption (2)

Adoption signal

13 GitHub stars

profilemedium
Observed May 19, 2026Source linkProvenance

Adoption signal

11 GitHub stars

profilemedium
Observed May 12, 2026Source linkProvenance
Security (1)

Handshake status

UNKNOWN

trustmedium
Observed unknownSource linkProvenance
Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium
Observed Apr 15, 2026Source linkProvenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB OPENCLEW

Extracted files

0

Examples

6

Snippets

0

Languages

python

Executable Examples

text

【输入】研报/想法
    ↓
情报员 → 收集资料
    ↓
合规官 → 提供规范
    ↓
翻译官 → 理解逻辑
    ↓
程序员 → 编写公式 + 参数搜索(网格搜索)
    ↓
测试员 → 测试效果
    ↓
评审官 → 评估质量
    ↓
是否满足条件?
    ↓ 否 → 优化建议 → 程序员 → 优化公式 → 返回测试
    ↓ 是
【输出】有效的Alpha因子 + 完整报告

bash

git clone <repository-url>
cd wq自动化

bash

conda env create -f environment.yml
conda activate alpha_research

bash

pip install -r requirements.txt

yaml

worldquant:
  api_key: "YOUR_API_KEY"

ai:
  api_key: "YOUR_DEEPSEEK_KEY"

bash

run_with_env.bat python main.py

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB OPENCLEW

Docs source

GITHUB OPENCLEW

Editorial quality

ready

基于 CrewAI 的 WorldQuant Alpha 因子自动研究与回测系统 6个专业 AI 智能体协作 从研报到可验证公式的全自动流水线 支持网格搜索和智能优化 WorldQuant Alpha因子研究多智能体系统 6个专业AI智能体组成的自动化流水线,将研报自动加工成可验证的Alpha因子公式 $1 $1 $1 --- 🎯 核心架构 一个由7个专业AI智能体组成的流水线,像工厂一样将研报自动加工成可验证的Alpha因子公式。 智能体团队 | 智能体 | 角色 | 代码文件 | 职责 | |--------|------|----------|------| | 🕵️ **情报员** | 研报爬取 | research_crawler.py | 搜刮各类研报和策略文章,产出清洗好的文本材料 | | 📚 **合规官** | 数据管理 | data_manager.py | 掌握WorldQuant所有数据字段和操作符规范,产出权威的"语法词典" | | 🔄 **翻译官** | 策略分析 | strategy_analyst.py | 把研报文字转化成量化逻辑,产出清晰的量化策略描述

Full README

WorldQuant Alpha因子研究多智能体系统

6个专业AI智能体组成的自动化流水线,将研报自动加工成可验证的Alpha因子公式

Python CrewAI License


🎯 核心架构

一个由7个专业AI智能体组成的流水线,像工厂一样将研报自动加工成可验证的Alpha因子公式。

智能体团队

| 智能体 | 角色 | 代码文件 | 职责 | |--------|------|----------|------| | 🕵️ 情报员 | 研报爬取 | research_crawler.py | 搜刮各类研报和策略文章,产出清洗好的文本材料 | | 📚 合规官 | 数据管理 | data_manager.py | 掌握WorldQuant所有数据字段和操作符规范,产出权威的"语法词典" | | 🔄 翻译官 | 策略分析 | strategy_analyst.py | 把研报文字转化成量化逻辑,产出清晰的量化策略描述 | | 💻 程序员 | Alpha工程师 | alpha_engineer.py | 把量化逻辑变成WorldQuant公式,产出合规的Alpha因子代码,支持网格搜索和公式优化 | | 🧪 测试员 | 回测师 | backtester.py | 在WorldQuant平台测试公式效果,产出回测结果报告 | | 📊 评审官 | 评审员 | critic.py | 评估回测结果,提改进建议,产出质量评分+优化建议 |

工作流程

【输入】研报/想法
    ↓
情报员 → 收集资料
    ↓
合规官 → 提供规范
    ↓
翻译官 → 理解逻辑
    ↓
程序员 → 编写公式 + 参数搜索(网格搜索)
    ↓
测试员 → 测试效果
    ↓
评审官 → 评估质量
    ↓
是否满足条件?
    ↓ 否 → 优化建议 → 程序员 → 优化公式 → 返回测试
    ↓ 是
【输出】有效的Alpha因子 + 完整报告

✨ 关键特点

  • 🤖 全自动:从想法到验证无人干预
  • 📝 守规矩:严格遵守WorldQuant语法
  • 💾 有记忆:记录所有步骤,可追溯
  • 🎓 能学习:失败案例反馈优化
  • 🔧 可扩展:随时增加新数据源、新策略
  • 🎯 参数优化:网格搜索自动寻找最优settings
  • 📊 智能评估:AI深度分析回测结果
  • 🔄 迭代优化:自动优化公式直到满足条件
  • 📈 历史追踪:完整记录优化历史,支持回滚

💡 系统价值

  • 🌱 对新手:帮你把想法快速变成可测试的公式
  • 🏆 对老手:批量处理研报,发现新策略
  • 👥 对团队:标准化研究流程,积累知识库

本质:一个24小时不休息、不出错、严格守规的数字量化研究员团队。


🚀 快速开始

环境要求

  • Python 3.11+
  • Conda (推荐)

安装步骤

  1. 克隆项目
git clone <repository-url>
cd wq自动化
  1. 创建Conda环境
conda env create -f environment.yml
conda activate alpha_research

或者手动安装依赖:

pip install -r requirements.txt
  1. 配置文件 编辑 config.yaml,设置API密钥:
worldquant:
  api_key: "YOUR_API_KEY"

ai:
  api_key: "YOUR_DEEPSEEK_KEY"

启动项目(重要)

由于CrewAI框架需要OpenAI兼容的环境变量,请使用提供的启动脚本:

Windows:

run_with_env.bat python main.py

Linux/Mac:

chmod +x run_with_env.sh
./run_with_env.sh python main.py

启动脚本会自动设置:

  • OPENAI_API_KEY:从config.yaml读取的DeepSeek密钥
  • OPENAI_API_BASE:DeepSeek API地址
  • PYTHONIOENCODING:UTF-8编码(解决中文乱码)

注意:

  • 不要直接运行 python main.py,否则会报错
  • 如果遇到中文乱码,使用启动脚本即可解决

📁 项目结构

wq自动化/
├── agents/                      # 7个智能体实现
│   ├── base_agent.py           # 基础智能体类
│   ├── research_crawler.py     # 🕵️ 情报员:研报爬取
│   ├── data_manager.py         # 📚 合规官:数据管理
│   ├── strategy_analyst.py     # 🔄 翻译官:策略分析
│   ├── alpha_engineer.py       # 💻 程序员:公式生成
│   ├── backtester.py           # 🧪 测试员:回测执行
│   ├── critic.py               # 📊 评审官:质量评估
│   └── grid_search_agent.py    # 🔍 优化师:网格搜索
├── tools/                       # 工具函数
│   ├── ai_client.py            # AI客户端
│   ├── web_scraper.py          # 网页爬虫
│   └── worldquant_client.py    # WorldQuant客户端
├── utils/                       # 工具函数
│   ├── config_loader.py        # 配置加载
│   ├── logger.py               # 日志配置
│   └── optimization_history.py # 优化历史记录
├── schemas/                     # 数据规范
│   └── __init__.py
├── tests/                       # 测试文件
│   ├── test_alpha_engineer_fixed.py   # Alpha工程师测试
│   ├── test_backtester_complete.py    # 回测师测试
│   ├── test_critic.py                 # 评论员测试
│   └── test_full_workflow.py          # 完整工作流测试
├── examples/                    # 示例代码
│   ├── agent_workflow_example.py      # 智能体交互示例
│   ├── example_grid_search.py         # 网格搜索示例
│   └── example_optimization_history.py # 优化历史示例
├── scripts/                     # 辅助脚本
│   ├── fetch_data_specs.py      # 获取数据规范
│   ├── fetch_operators.py       # 获取操作符
│   ├── generate_field_mapping.py # 生成字段映射
│   ├── monitor_progress.py      # 监控进度
│   └── continue_backtest.py     # 继续回测
├── logs/                        # 日志文件目录
├── results/                     # 结果存储目录
├── __pycache__/                 # Python缓存
├── crew.py                      # CrewAI协调器
├── main.py                      # 主程序入口
├── batch_backtest.py            # 批量回测脚本
├── machine_lib.py               # 参考代码
├── config.yaml                  # 配置文件
├── requirements.txt             # 依赖包列表
├── environment.yml              # Conda环境配置
├── worldquant_specs.json        # WorldQuant数据规范
├── worldquant_operators.json    # WorldQuant操作符
├── run_with_env.bat             # Windows启动脚本
├── run_with_env.sh              # Linux/Mac启动脚本
├── README.md                    # 项目说明
└── .gitignore                   # Git忽略规则

🔧 配置说明

config.yaml

# WorldQuant平台配置
worldquant:
  api_key: "YOUR_API_KEY"
  base_url: "https://api.worldquantbrain.com"
  timeout: 30

# AI模型配置
ai:
  api_key: "YOUR_DEEPSEEK_KEY"
  model: "deepseek-chat"
  temperature: 0.1

# 日志配置
logging:
  level: "INFO"
  file: "logs/alpha_research.log"
  max_size_mb: 10
  backup_count: 5

# 研报爬取配置
crawler:
  timeout: 30
  retry_times: 3

# 回测配置
backtest:
  default_universe: "all"
  start_date: "2020-01-01"
  end_date: "2024-12-31"
  frequency: "daily"
  benchmark: "000300.SH"

  # WorldQuant提交条件标准
  submission_criteria:
    fitness: 1.0                    # 适配度 ≥1.0
    sharpe_ratio: 1.25              # 夏普比率 ≥1.25
    turnover_min: 0.01              # 换手率 ≥1%
    turnover_max: 0.70              # 换手率 ≤70%
    max_weight: 0.10                # 最大股票权重 <10%
    correlation_threshold: 0.7      # 与现有因子相关性 <0.7

  # WorldQuant回测settings配置
  settings:
    instrumentType: "EQUITY"        # 证券类型
    region: "USA"                   # 区域:USA/CHN/HKG/JPN/EUR/ASI/GLB等
    universe: "TOP3000"             # 股票池:TOP3000/TOP1000/TOP500/TOP200/ALL等
    delay: 1                        # 延迟:1(D1,使用昨日数据) 或 0(D0,使用当日估算)
    decay: 20                       # 衰减:正整数,如4, 5, 10, 20等
    neutralization: "SECTOR"        # 中性化:MARKET/INDUSTRY/SUBINDUSTRY/SECTOR/NONE
    truncation: 0.08                # 截断:小数,如0.01(1%), 0.08(8%)
    pasteurization: "ON"            # 巴氏处理:ON/OFF
    testPeriod: "P2Y"               # 测试周期:P0Y(样本内)/P1Y/P2Y/P3Y(样本外)
    unitHandling: "VERIFY"          # 单位处理:VERIFY
    nanHandling: "ON"               # 空值处理:ON/OFF
    language: "FASTEXPR"            # 表达式语言
    visualization: false            # 可视化

  # 网格搜索参数范围
  grid_search:
    enabled: true
    decay: [5, 10, 15, 20, 25, 30]
    neutralization: ["MARKET", "INDUSTRY", "SUBINDUSTRY", "SECTOR"]
    truncation: [0.01, 0.05, 0.08, 0.10]
    max_iterations: 10
    improvement_threshold: 0.05

🔄 批量回测功能

回测师智能体支持批量回测功能,可以高效地处理大量Alpha公式。

功能特点

  • 分组回测:将公式分成N个一组(默认每组3条),并发提交到WorldQuant平台
  • 登录重试:自动检测会话过期(4小时后),自动重新登录
  • 进度保存:实时保存回测进度到 batch_backtest_progress.json
  • 断点续传:中断后可从任意组继续执行
  • 并发处理:自动处理429并发限制错误,等待30秒后重试

使用方法

基本批量回测

# 使用默认参数(每组3条)
python batch_backtest.py

# 自定义参数
python batch_backtest.py --group-size 3 --formula-file your_formulas.json

断点续传

如果回测过程中断,可以从指定组继续:

# 从第5组继续
python batch_backtest.py --start-group 5 --group-size 3

参数说明

| 参数 | 默认值 | 说明 | |------|--------|------| | --formula-file | test_50_reports_with_new_engineer.json | 公式文件路径 | | --group-size | 3 | 每组公式数量(建议3) | | --start-group | 0 | 起始组索引(用于断点续传) | | --decay | 20 | 衰减参数 | | --region | USA | 区域 | | --universe | TOP3000 | 股票池 | | --neutralization | SECTOR | 中性化方式 |

进度文件

进度会自动保存到 batch_backtest_progress.json,包含:

  • 当前组索引
  • 已完成的组列表
  • 回测结果

结果文件

结果会保存到 batch_backtest_results_YYYYMMDD_HHMMSS.json,包含每组回测的详细信息。

代码示例

from agents.backtester import BacktesterAgent

# 创建回测师智能体
backtester = BacktesterAgent()

# 运行批量回测
results = backtester.run_batch_backtest(
    formula_file='test_50_reports_with_new_engineer.json',
    group_size=3,  # 每组3条公式
    start_group=0  # 从第0组开始
)

# 查看结果
for result in results:
    print(f"组 {result['group_index']}: {result['status']}")

注意事项

  1. 并发限制:WorldQuant平台对并发回测有限制,建议每组3条公式
  2. 会话过期:平台会话4小时后自动过期,系统会自动重新登录
  3. 组间延迟:每组完成后会等待10秒再处理下一组,避免触发限制
  4. 进度保存:每组完成后立即保存进度,确保不丢失数据

🔍 网格搜索功能

网格搜索智能体支持自动寻找最优的回测参数组合,提升Alpha因子的表现。

功能特点

  • 参数空间探索:系统性搜索decay、neutralization、truncation等参数的组合
  • 自动优化:自动执行回测并评估结果,选择最优参数
  • 自适应搜索:支持多轮搜索,根据结果动态调整搜索范围
  • 参数敏感性分析:分析单个参数对因子表现的影响
  • 历史记录:所有搜索过程自动记录,支持回滚和对比

使用方法

基础网格搜索

from agents.grid_search_agent import GridSearchAgent

# 初始化网格搜索智能体
grid_search = GridSearchAgent()

# 执行网格搜索
result = grid_search.search_best_settings(
    formula="rank(ts_mean(returns, 20))",
    original_logic="价格动量策略",
    strategy_key="momentum_strategy",
    custom_ranges={
        'decay': [10, 15, 20, 25, 30],
        'neutralization': ['MARKET', 'INDUSTRY', 'SECTOR'],
        'truncation': [0.01, 0.05, 0.08]
    },
    max_iterations=10
)

# 查看结果
if result["success"]:
    print(f"最优settings: {result['best_settings']}")
    print(f"最优适配度: {result['best_fitness_score']:.2%}")

自适应搜索

# 执行自适应搜索(多轮优化)
adaptive_result = grid_search.adaptive_search(
    formula="rank(ts_mean(returns, 20))",
    original_logic="价格动量策略",
    strategy_key="momentum_strategy_adaptive",
    max_iterations=20
)

参数敏感性分析

# 分析decay参数的敏感性
sensitivity = grid_search.analyze_parameter_sensitivity(
    formula="rank(ts_mean(returns, 20))",
    original_logic="价格动量策略",
    base_settings={...},
    parameter='decay',
    values=[5, 10, 15, 20, 25, 30, 35, 40]
)

配置说明

在config.yaml中配置网格搜索参数:

backtest:
  grid_search:
    enabled: true
    decay: [5, 10, 15, 20, 25, 30]
    neutralization: ["MARKET", "INDUSTRY", "SUBINDUSTRY", "SECTOR"]
    truncation: [0.01, 0.05, 0.08, 0.10]
    max_iterations: 10
    improvement_threshold: 0.05

参数说明

| 参数 | 说明 | |------|------| | decay | 衰减参数,影响持仓时间和换手率 | | neutralization | 中性化方式,如MARKET、INDUSTRY、SECTOR | | truncation | 截断阈值,控制单只股票最大权重 | | max_iterations | 最大迭代次数 | | improvement_threshold | 改进阈值,用于提前终止搜索 |

运行示例

# 运行网格搜索示例
python examples/example_grid_search.py

📊 优化历史记录

优化历史记录管理器支持记录、查询和回滚Alpha因子的优化历史。

功能特点

  • 完整记录:记录每次优化的详细信息(公式、settings、回测结果、评估结果)
  • 适配度计算:自动计算综合评分,评估因子表现
  • 最佳查询:快速查询最佳公式
  • 趋势分析:查看优化趋势,了解改进过程
  • 版本回滚:支持回滚到任意历史版本
  • 报告导出:导出优化报告,便于分析

使用方法

记录优化历史

from utils.optimization_history import OptimizationHistory

# 初始化优化历史记录管理器
history = OptimizationHistory("optimization_history.json")

# 开始新的优化
optimization_id = history.start_optimization(
    strategy_key="my_strategy",
    original_logic="价格动量策略",
    original_formula="rank(ts_mean(returns, 20))",
    fields_used=["returns"]
)

# 记录优化迭代
history.record_iteration(
    strategy_key="my_strategy",
    optimization_id=optimization_id,
    iteration=1,
    formula="rank(ts_mean(returns, 20))",
    formula_name="alpha_v1",
    settings={"decay": 20, "neutralization": "SECTOR", "truncation": 0.08},
    backtest_result={"success": True, "performance": {...}},
    evaluation={"overall_rating": "良好", "score": 65, "is_valid": False},
    optimization_reason="初始公式"
)

查询最佳公式

# 查询最佳公式
best = history.get_best_formula("my_strategy", optimization_id)
print(f"最佳公式: {best['formula_name']}")
print(f"适配度: {best['fitness_score']:.2f}")

查看优化趋势

# 查看优化趋势
trend = history.get_optimization_trend("my_strategy", optimization_id)
for t in trend:
    print(f"迭代{t['iteration']}: 适配度={t['fitness_score']:.2f}, 夏普比率={t['sharpe_ratio']:.2f}")

回滚到指定版本

# 回滚到第2个版本
version_2 = history.rollback_to_version("my_strategy", optimization_id, 2)

导出优化报告

# 导出优化报告
report = history.export_report("optimization_report.json")

运行示例

# 运行优化历史示例
python examples/example_optimization_history.py

📊 使用示例

示例1:从研报文本生成Alpha因子

from crew import AlphaResearchCrew

# 初始化团队
crew = AlphaResearchCrew()

# 输入研报
report = """
根据近期市场表现,小市值股票在牛市中表现优于大市值股票。
特别是市值在50亿以下、市盈率低于30倍的股票,未来一个月有较高超额收益。
"""

# 执行完整流程
result = crew.execute_full_workflow({
    "text": report,
    "source": "manual_input"
})

# 查看结果
if result["success"]:
    print(f"Alpha公式: {result['summary']['formula']}")
    print(f"年化收益: {result['summary']['annual_return']:.2%}")
    print(f"夏普比率: {result['summary']['sharpe_ratio']:.2f}")
    print(f"评级: {result['summary']['overall_rating']}")

示例2:从文件加载研报

result = crew.execute_full_workflow({
    "file_path": "reports/strategy_001.txt"
})

📈 输出示例

{
  "success": true,
  "summary": {
    "formula": "rank(market_cap) * -1 * (pe_ratio < 30) * (close > ts_mean(close, 20))",
    "annual_return": 0.1587,
    "sharpe_ratio": 1.82,
    "max_drawdown": 0.1243,
    "overall_rating": "良好",
    "recommendation": "继续使用"
  },
  "workflow": {
    "step1_crawl": { "success": true, "report_text": "..." },
    "step2_analysis": { "involved_fields": ["market_cap", "pe_ratio", "close"] },
    "step3_formula": { "formula": "..." },
    "step4_validation": { "is_valid": true },
    "step5_backtest": { "performance": {...} },
    "step6_evaluation": { "overall_rating": "良好" }
  }
}

🛠️ 技术栈

  • 核心框架: CrewAI (多智能体协作)
  • AI模型: DeepSeek API (兼容OpenAI格式)
  • 数据处理: Pandas, NumPy
  • 配置管理: PyYAML, python-dotenv
  • 日志系统: Python logging with rotation
  • 数据验证: Pydantic

📝 开发计划

  • [x] 阶段一:基础框架搭建
  • [x] 阶段二:6个智能体实现
  • [x] 阶段三:智能体集成
  • [x] 阶段四:真实API对接
  • [x] 阶段五:网格搜索功能
  • [x] 阶段六:优化历史记录
  • [x] 阶段七:Settings参数配置化
  • [x] 阶段八:AI评估优化
  • [x] 阶段九:公式自动优化
  • [ ] 阶段十:Web界面开发
  • [ ] 阶段十一:性能优化
  • [ ] 阶段十二:更多数据源集成

🤝 贡献指南

欢迎提交 Issue 和 Pull Request!

  1. Fork 本项目
  2. 创建特性分支 (git checkout -b feature/AmazingFeature)
  3. 提交更改 (git commit -m 'Add some AmazingFeature')
  4. 推送到分支 (git push origin feature/AmazingFeature)
  5. 开启 Pull Request

📄 许可证

本项目采用 MIT 许可证 - 详见 LICENSE 文件


👥 联系方式

  • 项目主页: [GitHub Repository]
  • 问题反馈: [Issues]

🙏 致谢


⭐ 如果这个项目对你有帮助,请给个 Star!

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

MissingGITHUB OPENCLEW

Contract coverage

Status

missing

Auth

None

Streaming

No

Data region

Unspecified

Protocol support

OpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.
Invocation examples
curl -s "https://www.xpersona.co/api/v1/agents/crewai-xiao634zhang-worldquant-alpha-crew/snapshot"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-xiao634zhang-worldquant-alpha-crew/contract"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-xiao634zhang-worldquant-alpha-crew/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.
No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media
No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors
Github ReposUpdated 1h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW
Machine Appendix

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://www.xpersona.co/api/v1/agents/crewai-xiao634zhang-worldquant-alpha-crew/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/crewai-xiao634zhang-worldquant-alpha-crew/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/crewai-xiao634zhang-worldquant-alpha-crew/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-xiao634zhang-worldquant-alpha-crew/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-xiao634zhang-worldquant-alpha-crew/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-xiao634zhang-worldquant-alpha-crew/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_OPENCLEW",
      "generatedAt": "2026-10-09T19:57:11.709Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "crewai",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "multi-agent",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"
}

Facts JSON

[
  {
    "factKey": "traction",
    "category": "adoption",
    "label": "Adoption signal",
    "value": "13 GitHub stars",
    "href": "https://github.com/xiao634zhang/worldquant-alpha-crew",
    "sourceUrl": "https://github.com/xiao634zhang/worldquant-alpha-crew",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-05-19T06:58:56.388Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "label": "Vendor",
    "value": "Xiao634zhang",
    "category": "vendor",
    "href": "https://github.com/xiao634zhang/worldquant-alpha-crew",
    "sourceUrl": "https://github.com/xiao634zhang/worldquant-alpha-crew",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-05-12T06:46:14.459Z",
    "isPublic": true,
    "metadata": {}
  },
  {
    "factKey": "protocols",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "category": "compatibility",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-xiao634zhang-worldquant-alpha-crew/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-xiao634zhang-worldquant-alpha-crew/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-05-12T06:46:14.459Z",
    "isPublic": true,
    "metadata": {}
  },
  {
    "factKey": "traction",
    "label": "Adoption signal",
    "value": "11 GitHub stars",
    "category": "adoption",
    "href": "https://github.com/xiao634zhang/worldquant-alpha-crew",
    "sourceUrl": "https://github.com/xiao634zhang/worldquant-alpha-crew",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-05-12T06:46:14.459Z",
    "isPublic": true,
    "metadata": {}
  },
  {
    "factKey": "docs_crawl",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "category": "integration",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true,
    "metadata": {}
  },
  {
    "factKey": "handshake_status",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "category": "security",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-xiao634zhang-worldquant-alpha-crew/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-xiao634zhang-worldquant-alpha-crew/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true,
    "metadata": {}
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true,
    "metadata": {}
  }
]

Sponsored

Ads related to worldquant-alpha-crew and adjacent AI workflows.