mirror of
https://github.com/NicolasBohn/NexQuant.git
synced 2026-07-27 15:37:44 +00:00
TPTBusiness
cbe1c52e00
Rename all source files, scripts, tests, documentation, and configuration from Predix/predix to NexQuant/nexquant across the entire codebase.
4.7 KiB
4.7 KiB
NexQuant v1.0.0 Release Notes
Release Date: 2026-04-02
Tag: v1.0.0
🎉 Overview
Initial release of NexQuant - an autonomous AI-powered quantitative trading agent for EUR/USD forex markets.
✨ Added
Autonomous Factor Generation
- 110+ EURUSD factors generated autonomously using LLMs
- Multi-agent debate system (Bull/Bear/Neutral analysts)
- Stanley Druckenmiller-style macro analysis agent
- Market regime detection using Hurst Exponent
- Session-aware analysis (Asian/London/NY sessions)
Backtesting Engine
- IC (Information Coefficient) calculation
- Sharpe Ratio, Sortino Ratio, Calmar Ratio
- Max Drawdown with start/end dates
- Win Rate, Total Trades tracking
- Transaction cost modeling (1.5 bps spread)
- Forward return calculation
Results Database
- SQLite database for tracking all backtest results
- Tables: factors, backtest_runs, backtest_metrics, daily_returns, loop_results
- Queries for top factors by Sharpe/IC
- Aggregate statistics
- Foreign key integrity
Risk Management
- Correlation matrix between factors
- Portfolio optimization (Mean-Variance, Risk Parity)
- Position sizing with volatility adjustment
- Risk limits (position size, leverage, drawdown)
- Advanced risk manager with custom thresholds
Dashboards & UI
- Web Dashboard (Flask + HTML) with live progress
- CLI Dashboard (Rich library) for terminal
- Real-time macro data (EURUSD, DXY, Volatility)
- Session info with recommendations
- Memory statistics (Win-Rate, PnL, Sharpe)
Testing Infrastructure
- 97 unit tests with 98.77% code coverage
- Edge case testing for all metrics
- Integration tests for full workflows
- pytest configuration
- Test fixtures for mock data
Documentation
- Comprehensive QWEN.md (development guide)
- ATTRIBUTION.md (usage guidelines)
- README.md (installation, quick start)
- All code comments in English
- Git commit guidelines (English-only)
Developer Experience
- English-only commit messages policy
- Clean git history (all German messages translated)
- .gitignore for sensitive files (.env, logs, results, etc.)
- Makefile for common tasks
- Pre-commit hooks support
🔧 Changed
- Rebranded from RD-Agent to NexQuant for EUR/USD quantitative trading
- Updated project metadata for NexQuantAI organization
- All code comments translated to English
- Removed 'Inspired by' comments, added comprehensive Acknowledgments
- Enhanced .gitignore for better file management
- Removed test configuration files from root directory
- Cleaned up log files and test artifacts from git history
🛡️ Fixed
- Removed all Chinese stock references, replaced with EUR/USD 1min FX data
- Migrated to 1min EURUSD data (2020-2026)
- Injected MultiIndex warning into factor interface prompt
- Fixed Embedding Context Length errors with intelligent chunking
- Fixed LLM connection errors with multi-provider fallback
- Fixed division by zero in volatility calculations
- Fixed NaN handling in correlation matrices
📦 Dependencies
Core
- Python 3.10/3.11
- PyTorch for deep learning
- Qlib for backtesting
- Flask for web dashboard
- Rich/Typer for CLI
- pytest for testing (98.77% coverage)
Additional
- pandas, numpy for data processing
- SQLite for database
- yfinance for live market data
- langchain, langgraph for agent workflows
📊 Statistics
| Metric | Value |
|---|---|
| Lines of Code | ~15,000+ |
| Files | 100+ |
| Commits | 20+ |
| Contributors | 1 |
| Test Coverage | 98.77% |
| Tests Passed | 97/97 |
| Factors Generated | 110+ |
🙏 Acknowledgments
This release builds upon and is inspired by:
- Microsoft RD-Agent (MIT License) - Foundation for autonomous R&D framework
- TradingAgents (Apache 2.0 License) - Multi-agent debate patterns
- ai-hedge-fund - Macro analysis and risk management concepts
All code in NexQuant v1.0.0 is originally written and independently implemented.
📝 License
MIT License - See LICENSE file for details.
Attribution Requirements
If you use this code or concepts in your project, you must:
- Include the MIT License text
- Keep the copyright notice: "Copyright (c) 2025 NexQuant Team"
- Provide attribution to the original project
See ATTRIBUTION.md for detailed guidelines.
🔗 Links
- GitHub Release: https://github.com/TPTBusiness/NexQuant/releases/tag/v1.0.0
- Main Changelog: ../CHANGELOG.md
- Attribution Guidelines: ../ATTRIBUTION.md
- Installation Guide: ../README.md#installation
- Quick Start: ../README.md#quick-start
Made with ❤️ by NexQuant Team
For detailed usage guidelines, see README.md