b9d59b5edb
Repurpose the BMad Method agile development framework into a Quant Method framework for systematic investment strategy research, backtesting, risk management, and production deployment. Key changes: - Rename project to quant-method with quant finance keywords - Rewrite README with quant research lifecycle documentation - Replace 9 agents with quant-focused roles: Quant Researcher, Portfolio Manager, Quant Architect, Quant Developer, Data Engineer, Risk Analyst, Research Director, Strategy Developer, Research Documentarian - Update Quant Master orchestrator for research workflows - Restructure 4 workflow phases: Research, Strategy Design, Validation, Production (from Analysis, Planning, Solutioning, Implementation) - Rename workflow directories and update all workflow YAML configs with quant-specific descriptions, artifact references, and input patterns - Update module configs for research/backtest/implementation artifact storage - Replace project context template with research-focused template https://claude.ai/code/session_01EMpbNGYLyty1sDMp1z4ENj |
||
|---|---|---|
| .github | ||
| .husky | ||
| .vscode | ||
| docs | ||
| src | ||
| test | ||
| tools | ||
| website | ||
| .coderabbit.yaml | ||
| .gitignore | ||
| .markdownlint-cli2.yaml | ||
| .npmrc | ||
| .nvmrc | ||
| .prettierignore | ||
| CHANGELOG.md | ||
| CNAME | ||
| CONTRIBUTING.md | ||
| CONTRIBUTORS.md | ||
| LICENSE | ||
| README.md | ||
| SECURITY.md | ||
| TRADEMARK.md | ||
| Wordmark.png | ||
| banner-bmad-method.png | ||
| eslint.config.mjs | ||
| package-lock.json | ||
| package.json | ||
| prettier.config.mjs | ||
README.md
Quant Method
AI-Driven Investment Quant Development and Research Framework -- Specialized AI agents and structured workflows for systematic strategy research, backtesting, risk management, and production deployment.
Why Quant Method?
Quantitative investment research requires rigorous process discipline -- from hypothesis formation through statistical validation to production monitoring. Traditional tools leave gaps between research notebooks and production systems. Quant Method bridges this with AI agents that act as expert collaborators across the entire quant lifecycle.
- Structured Research Process: Guided workflows grounded in quantitative finance best practices across research, strategy design, validation, and production
- Specialized Agents: Domain experts including Quant Researcher, Portfolio Manager, Risk Analyst, Data Engineer, and more
- Quant-Adaptive: Adjusts depth based on strategy complexity -- a simple momentum factor needs different rigor than a multi-asset statistical arbitrage system
- Full Lifecycle: From alpha research through backtesting, risk analysis, and live monitoring
Quick Start
Prerequisites: Node.js v20+
npx quant-method install
Follow the installer prompts, then open your AI IDE (Claude Code, Cursor, Windsurf, etc.) in the project folder.
Rapid Strategy Path (Quick Flow)
Quick hypothesis testing, single-factor strategies, clear signals:
/strategy-spec-- analyzes your data and produces a strategy specification with implementation tasks/dev-strategy-- implements each task (signals, backtest, risk checks)/strategy-review-- validates statistical rigor and code quality
Full Research Path (Quant Method)
Multi-factor strategies, portfolio-level research, production deployment:
/research-brief-- define investment thesis, universe, and data requirements/create-strategy-design-- full specification with signal definitions, risk constraints, and performance targets/create-architecture-- technical infrastructure: data pipelines, execution systems, monitoring/create-research-plan-- break work into prioritized research and implementation tasks/research-planning-- initialize research tracking- Repeat per task:
/create-task->/dev-task->/task-review
Specialized Agents
| Agent | Role | Focus |
|---|---|---|
| Quant Researcher | Alpha Research + Factor Analysis | Signal discovery, literature review, statistical analysis |
| Portfolio Manager | Portfolio Construction + Allocation | Position sizing, rebalancing, benchmark-aware optimization |
| Quant Architect | Systems Design + Infrastructure | Data pipelines, execution systems, backtesting frameworks |
| Quant Developer | Strategy Implementation | Signal code, backtest harnesses, production adapters |
| Data Engineer | Market Data + Alternative Data | Data pipelines, quality validation, feature engineering |
| Risk Analyst | Risk Management + Model Validation | Drawdown analysis, stress testing, regime detection |
| Research Director | Research Process + Coordination | Research pipeline management, prioritization, tracking |
| Research Documentarian | Research Reports + Model Documentation | Strategy documentation, research logs, compliance docs |
| Strategy Developer | Rapid Prototyping | Quick hypothesis testing, single-factor research |
Workflow Phases
Phase 1: Research
- Market and academic research
- Factor discovery and screening
- Data exploration and alternative data evaluation
- Investment thesis development
Phase 2: Strategy Design
- Signal specification and universe selection
- Risk constraint definition
- Performance target setting
- Model specification (statistical, ML, rules-based)
Phase 3: Validation
- Backtesting with walk-forward analysis
- Out-of-sample testing
- Statistical significance validation
- Transaction cost and capacity analysis
- Risk decomposition and stress testing
Phase 4: Production
- Deployment and integration
- Live monitoring and alerting
- Performance attribution
- Research retrospective and strategy refinement
Documentation
- Getting Started Tutorial
- Strategy Research Walkthrough
- Backtesting Best Practices
- Risk Management Framework
Contributing
We welcome contributions. See CONTRIBUTING.md for guidelines.
License
MIT License -- see LICENSE for details.