智能量化框架 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 8.0 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
智能量化框架 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
智能量化框架 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install inalpha
# 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 inalpha
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/mirror29/inalpha
cd inalpha
pip install -e .
# 验证安装
python -c "import inalpha; print('安装成功')"
# 命令行使用
inalpha --help
# 基本用法
inalpha input_file -o output_file
# Python 代码中调用
import inalpha
# 示例
result = inalpha.process("input")
print(result)
# inalpha 配置文件示例(config.yml) app: name: "inalpha" debug: false log_level: "INFO" # 运行时指定配置文件 inalpha --config config.yml # 或通过环境变量配置 export INALPHA_API_KEY="your-key" export INALPHA_OUTPUT_DIR="./output"
<img src="assets/mascot-avatar.png" alt="Inalpha" width="200" />
<p><strong>Quant agents that evolve under audit.</strong></p>
<p><em>An oracle that keeps a ledger.</em></p>
<p>Factor timing · Multi-perspective research · Factor lab · Risk engine · Strategy evolution · Machine-approved orders · Omikuji</p>
<p> <strong>English</strong> | <a href="README.zh-CN.md">中文</a> </p>
<p> <a href="LICENSE"><img src="https://img.shields.io/badge/license-AGPL--3.0-C8463C.svg" alt="License" /></a> <img src="https://img.shields.io/badge/status-alpha%20·%20Phase%20D--12-9E7B4B.svg" alt="Phase" /> <img src="https://img.shields.io/badge/built%20with-Mastra%20%2B%20FastAPI-D4A744.svg" alt="Built with" /> <img src="https://img.shields.io/badge/python-3.12+-1A1714.svg" alt="Python" /> <img src="https://img.shields.io/badge/typescript-5.x-1A1714.svg" alt="TypeScript" /> </p>
<p><em>Every factor proposed, every strategy mutated, every order routed — logged, versioned, reviewable. Agents pick the currently-effective factors to time entries, write the strategies, and evolve them; the LLM writes the code, and the engineering harness signs every decision.</em></p>
<p>Inalpha is a <strong>professional quant agent framework</strong> — an open-source system where LLM agents research (with a panel of investing legends), pick the factors that work <em>now</em>, write and evolve strategy code, and route every order through machine approval, all under an <strong>audit-grade engineering harness</strong>. A unified kernel (one strategy codebase — swap only the Clock and Gateway), multi-market routing (crypto, US equities, A-shares, global indices, macro), and a Claude Code-style hooks/permissions/plan-exec layer back it — built for teams that demand <strong>every decision be provable and every order path be unreachable by the LLM directly</strong>.</p>
</div>
---
Inalpha is a professional quant agent framework, governed by engineering discipline. It treats LLM agents not as black-box signal generators, but as code-writing collaborators bounded by hooks, permissions, plan-then-execute approval, and a one-shot signature on every order path.
**Agents pick the factors that work now.** Instead of a hard-coded indicator set, they rank factors by time-series Rank IC and surface the ones currently effective (factor.timing), then use that to back research and timing. Data itself is source-attributed by default — as_of-stamped and freshness-checked — so agents don't quietly reason on stale data.
Several capability lines sit on top of that harness:
Strategy protocol contract) precede any candidate run; multi-objective fitness (Sharpe + Calmar − turnover − drawdown) so no metric can be gamed alone.trade.create_plan → approve → execute_plan with a single-use, TTL-bound approval_token; the LLM has no direct path to placing an order, and every step is logged into the audit trail.The name combines Inari (the Japanese fox deity of prosperity) with alpha (the quant term for excess return) — a companion that reads your direction and keeps every step on the record.
Status: Inalpha is in alpha (Phase D-12 — factor-library closure: 79 factors with lineage & decay watch (alert-only, no auto-trim), a restricted-DSL factor-discovery L1, and a three-party research debate — on top of D-11 multi-market paper trading (cross-currency cash + a live runner that auto-runs promoted strategies on live bars), D-10 multi-market data, and D-9 LLM-authored strategies + risk engine). Read the code, weigh in on design — do not run this against real money (real-money trading is out of scope).
---
Each capability below is built so the work it produces is auditable from day one — not retrofitted later.
pnpm i # Node packages (packages/orchestration)
uv sync # Python packages (services/_shared, data, paper, research, factor)
A single .env at the repo root is read by Mastra (TS) and all Python services. Copy the template and fill in the LLM provider you want to use:
cp .env.example .env
Inside .env, set LLM_PROVIDER to one of deepseek | anthropic | openai | gemini | kimi | zhipu | ollama and fill in the matching key.
Defaults pick each vendor's current flagship as of 2026-05. Override with LLM_MODEL=... if you want a reasoning / cheaper variant.
| Provider | env var | Default model (2026-05) | Get a key |
|---|---|---|---|
deepseek | DEEPSEEK_API_KEY | deepseek-v4-pro | [platform.deepseek.com](https://platform.deepseek.com) |
anthropic | ANTHROPIC_API_KEY | claude-opus-4-8 | [console.anthropic.com](https://console.anthropic.com) |
openai | OPENAI_API_KEY | gpt-5.5 | [platform.openai.com](https://platform.openai.com) |
gemini | GEMINI_API_KEY | gemini-3-pro | [aistudio.google.com](https://aistudio.google.com) |
kimi | KIMI_API_KEY | kimi-k2.6 | [platform.moonshot.ai](https://platform.moonshot.ai) |
zhipu | ZHIPU_API_KEY | glm-5.2 | [open.bigmodel.cn](https://open.bigmodel.cn) |
ollama | — (local) | llama4 | ollama pull llama4 |
Override the default model by setting LLM_MODEL=... in the same file. Mastra and services/research both read this one file — no per-service config to juggle.
Already have keys inservices/*/.envorpackages/orchestration/.envfrom earlier? Those still work as cwd-level overrides while you migrate. Once you copy them up into the root.env, the per-service files can be deleted.
Optional · FRED key for macro factors. The factor library's macro factors (macro.* — rates, term & credit spreads, CPI, payrolls, real-economy, sentiment) read FRED data via venue=fred. Set FRED_API_KEY in .env to enable them — it's free and instant. Without a key the connector simply isn't registered and macro factors degrade gracefully (price/volume factors are unaffected). Note: macro factors are computed only at timeframe=1d/1wk — they're filtered out on intraday bars (monthly series would be a step function), so request 1d to see them.
高质量的开源AI工作流框架,适合量化交易和投资策略
该工具使用 AGPL-3.0 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
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。
⚠️ AGPL 3.0 — 最严格的 Copyleft,网络服务端使用也需开源,SaaS 使用受限。
经综合评估,智能量化框架 在Agent工作流赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | inalpha |
| Topics | ai-agentalgorithmic-tradingbacktestingfactor-investing |
| GitHub | https://github.com/mirror29/inalpha |
| License | AGPL-3.0 |
| 语言 | Python |
收录时间:2026-07-02 · 更新时间:2026-07-02 · License:AGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端