by Miasyster
Agent-driven alpha factory — LLM autonomously designs, backtests, and submits factors to WorldQuant BRAIN
# Add to your Claude Code skills
git clone https://github.com/Miasyster/QuantGPTLast scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T15:06:37.517Z",
"npmAuditRan": true,
"pipAuditRan": true
}QuantGPT is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by Miasyster. Agent-driven alpha factory — LLM autonomously designs, backtests, and submits factors to WorldQuant BRAIN. It has 349 GitHub stars.
Yes. QuantGPT passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/Miasyster/QuantGPT" and add it to your Claude Code skills directory (see the Installation section above).
QuantGPT is primarily written in Python. It is open-source under Miasyster on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh QuantGPT against similar tools.
No comments yet. Be the first to share your thoughts!
Agent-Driven Factor Research Engine — Autonomous Mining, Independent Validation on QuantGPT Cloud
LLM Agent 自治因子挖矿 → 批量回测 → 多维评分 → 反过拟合验证 → QuantGPT Cloud 独立验证 + 样本外跟踪 | 全程零人工干预
Quick Start · Architecture · API Docs · MCP Guide · Factor Mining · Roadmap · Contributing
WeChat / 微信交流群: Add quantgpt_ai on WeChat to join the community
QuantGPT is an agent-driven factor research engine — not a backtest library, not a chatbot wrapper. It gives an LLM Agent (Claude, via MCP) a complete toolkit to autonomously discover, evaluate, iterate, and validate alpha factors, with zero human intervention per research cycle. Factors that pass local validation are automatically uploaded to QuantGPT Cloud for independent verification and out-of-sample tracking — ensuring research results are reproducible and auditable.
The core architecture:
LLM Agent (Claude Code / Claude Desktop)
│
├── MCP Tools (15 个) ← Agent 的工具箱
│ ├── run_backtest ← 全市场分组回测
│ ├── score_factor ← 0-100 综合评分
│ ├── diagnose_factor ← 失败模式诊断
│ ├── run_anti_overfit ← 4 项反过拟合检验
│ ├── run_rolling_validation ← Walk-forward 验证
│ ├── validate_expression ← 语法校验
│ ├── list_operators ← 60+ 算子文档
│ ├── list_universes ← 股票池和基准
│ ├── wq_brain_submit ← WQ BRAIN 单因子提交
│ ├── wq_brain_batch_submit ← 批量参数扫描提交
│ ├── wq_brain_submit_by_ids ← 按 ID 提交
│ ├── wq_brain_list_alphas ← 查询已提交 alpha
│ ├── wq_brain_check_alphas ← 检查 alpha 状态
│ └── wq_brain_finalize_submissions ← 最终提交确认
│
├── QuantGPT Cloud ← 独立验证平台 (quant-gpt.com)
│ ├── A 级因子自动上传
│ ├── 独立 IC/IR/Turnover 验证
│ ├── 样本外实时跟踪
│ ├── 因子去重(Self-Correlation 检测)
│ └── 公开可审计的研究记录
│
├── Evolution Engine ← 因子进化引擎
│ ├── MutationEngine (8 方向突变)
│ ├── CrossoverEngine (高分因子交叉)
│ ├── MetaEvolutionSelector (自适应策略)
│ └── TrajectoryAnalyzer (轨迹分析)
│
├── WQ BRAIN Integration ← WorldQuant 直连(可选)
│ ├── Dollar-neutral 模拟
│ └── 一键正式提交
│
└── Knowledge Base ← 跨会话知识积累
├── rules/ (已验证规则)
├── findings/ (经验发现)
└── failures/ (已证伪路径)
传统工具(包括 ChatGPT + 回测库)的模式是:人类想因子 → 工具跑回测 → 人类看结果。Agent 是执行者,人类是决策者。
QuantGPT 的模式是:人类定义目标 → Agent 自治研究 → 人类审阅产出。Agent 是研究者,人类是审阅者。
这不是接口层的区别(自然语言 vs. 代码),而是决策权的区别。Agent 自主决定:探索哪个方向、生成什么表达式、评估哪些指标、何时迭代、何时放弃、何时提交。
| Metric | Value |
|---|---|
| 累计回测任务 | 370+ |
| 单轮迭代(8 候选因子) | ~15 分钟 |
| 表达式算子 | 60+(含非线性、三元、技术指标) |
| Cloud 独立验证 | A 级因子自动上传 quant-gpt.com 验证 + 样本外跟踪 |
| WQ BRAIN 提交(可选) | 3 个因子 IS 全部 PASS,已提交(最佳 Fitness 1.26) |
QuantGPT 产出的因子通过两层验证:本地多维评分 + QuantGPT Cloud 独立 IC/IR 验证。高质量因子还可选提交至 WQ BRAIN。以下 3 个因子已通过 WQ BRAIN IS 检测并正式提交:
| Factor | Expression | WQ Sharpe | WQ Fitness | WQ Returns | IS Tests | Status |
|---|---|---|---|---|---|---|
| Debt-Momentum Composite | -1 * rank(ts_av_diff(close, 10)) + rank(debt / enterprise_value) |
1.77 | 1.26 | 20.18% | ALL PASS | Submitted |
| VWAP Decay Reversal | -1 * rank(ts_decay_linear(close / vwap, 10)) |
1.69 | 1.07 | 18.63% | ALL PASS | Submitted |
| Returns-Volume Momentum | -1 * rank(ts_decay_linear(returns * volume / adv20, 5)) |
1.60 | 1.03 | 24.15% | ALL PASS | Submitted |
3 个因子代表不同的 alpha 来源:Debt-Momentum 结合动量反转与基本面(债务/企业价值),行业中性化;VWAP Decay Reversal 捕捉价格偏离 VWAP 的衰减回归,市场中性化;Returns-Volume Momentum 捕捉收益率与相对成交量的衰减动量,市场中性化。全程 Agent 自治完成。
This is QuantGPT's defining capability.
Agent 读知识库、设计假设、批量实验、分析结果、积累知识、自我迭代,每个结论经过双模型交叉验证。A 级因子自动上传 QuantGPT Cloud 独立验证,建立可审计的样本外跟踪记录。
┌─────────────────────────────┐
│ Research Notes & Knowledge │
│ (Rules / Findings / Fails) │
└──────────┬──────────────────┘
│ read
▼
┌──────────┐ ┌──────────────────────────┐ ┌──────────────────┐
│ Phase 0 │───▶│ Phase 1: Factor Design │───▶│ Phase 2: Batch │
│ Context │ │ Hypothesis → Expression │ │ Backtest (10-20 │
│ Loading │ │ 1-3 candidates per idea │ │ concurrent) │
└──────────┘ └──────────────────────────┘ └────────┬─────────┘
│
┌─────────────────────────┘
▼
┌──────────────────────────────────────────┐
│ Phase 3: Four-Step Analysis │
│ │
│ ① Fact Collection (metrics vs baseline) │
│ ② Independent Judgment (Agent) │
│ ③ Cross-Review (DeepSeek Reasoner) │
│ ④ Consensus or Divergence Resolution │
└──────────────────┬───────────────────────┘
│
┌──────────────┴──────────────┐
▼ ▼
┌─────────────────┐ ┌──────────────────┐
│ Phase 4: Update │ │ Phase 5: Stop? │
│ Notes + Knowledge│ │ Converged / │
│ Base │◀────────│ Time / Rounds │
└─────────────────┘ └──────────────────┘
│ │ no
│ └──▶ back to Phase 1
▼
┌──────────────────┐
│ Phase 6: Report │
│ A/B factors + │
│ new knowledge │
└──────────────────┘
Dual-LLM Cross-Review
每个结论性判断(采用/不采用/关闭方向)必须经过第二个 LLM 独立评审。把事实数据和第一个模型的推理链一起发给 DeepSeek Reasoner,要求独立评估推理是否合理、是否有遗漏角度。
共识 → 直接输出。分歧 → 呈现双方证据,采用更保守结论。
这解决了单模型因子研究的核心问题:confirmation bias。
Persistent Knowledge Base
research_notes/knowledge/
├── rules/ ← 已验证的稳定规则(必须遵守)
├── findings/ ← 经验发现(参考)
└── failures/ ← 已证伪路径(禁止重复)
知识库跨会话积累。第 10 次研究会话可以直接利用前 9 次的所有发现,避免重复实验,遵守已验证规则,绕开已证伪路径。
这不是 chat history——是结构化的研究资产。
Batch Concurrent Evaluation
单次提交 10-20 个因子表达式,并发回测 + 三波重试。结果按 fitness 降序排列。hs300 fitness < 0.1 时自动跳过 csi500 验证,节省算力。
from scripts.factor_miner import batch_evaluate
results = batch_evaluate(
server, expressions, params,
max_concurrent=10
)
Research Discipline (Enforced)
不是建议,是硬性规则:
上面 Validated Results 中的因子就是这个流程的产出。 多轮迭代,A 级因子自动上传 QuantGPT Cloud 独立验证。完整方法论见 Factor Mining Guide。
┌────────────────────────────────────────────────────────────────────┐
│ QuantGPT Research Engine │
├─────────────┬──────────────────────────────┬───────────────────────┤
│ │ Core Engine │ │
│ Agent │ ┌──────────────────────┐ │ Data Layer │
│ Interface │ │ Expression Parser │ │ ┌─────────────────┐ │
│ │ │ 60+ operators │ │ │ baostock (free) │ │
│ MCP Tools │ │ Cloud + WQ compat. │ │ │ akshare (free) │ │
│ REST API │ └──────────┬───────────┘ │ │ PolarDB (opt) │ │