FEAT NEXUS PRIME
An institutional-grade algorithmic trading platform that bridges MetaTrader 5 with an autonomous AI cortex for high-frequency data extraction, ML-driven analysis, and autonomous decision-making using the FEAT methodology.
README
🦅 FEAT NEXUS PRIME
<div align="center">
The first institutional-grade Algorithmic Trading Platform that bridges MetaTrader 5 with an Autonomous AI Córtex (Dockerized Brain + SSE + RAG).
Mission • Command Center • Architecture • Omni-Audit • Institutional DB
</div>
🎯 The Mission
NEXUS PRIME is not just an indicator or a bot; it is a Mission-Critical Ecosystem designed for high-frequency data extraction, ML-driven analysis, and autonomous decision-making using the FEAT (Form, Space, Acceleration, Time) methodology.
🎮 Command Center (One-Switch Control)
The entire system lifecycle is controlled via a unified Python Orchestrator:
nexus.bat: Initializes the "Golden Start".- Bootstraps MetaTrader 5.
- Orchestrates Docker Compose (Brain + Dashboard).
- Executes Internal Sync Audit.
- Runs the War Room Report.
- Opens the Visual Interface.
stop_nexus.bat: Executes a Graceful Shutdown.- Safe Docker teardown (Persistence guaranteed).
- Professional MT5 process termination.
check_system.bat: The Omni-Auditor on demand.
🏗️ Architecture: NEXUS PRIME
The system operates on a decentralized core-peripheral model:
- THE BRIDGE (MQL5): Native indicators (
UnifiedModel_Main.mq5,InstitutionalPVP.mq5) extraction engine with high-performance ZMQ streaming. - THE BRAIN (Docker/Python): A specialized MCP Server hosting the ML Engine, Data Collectors, and the RAG Memory (ChromaDB).
- THE PERSISTENCE (Supabase): Institutional-grade schema for high-frequency tick logging, signal auditing, and model performance tracking.
- THE VISION (Dashboard): Next.js + Framer Motion visual cockpit for real-time monitoring.
🕵️ Omni-Audit (Self-Healing)
Every component is monitored by the NEXUS Omni-Auditor. If a data blocker is detected (MT5 Offline, ZMQ Latency > 50ms, DB Sync Failed), the system generates a machine-readable REPAIR_REQUEST to trigger autonomous self-healing by the Antigravity Agent.
📊 Institutional Persistence
The database schema (institutional_schema.sql) is designed for senior quantitative analysis:
market_ticks: Nanosecond-aware price capture.feat_signals: Comprehensive audit trail with confidence scores and top-drivers.ml_inference_logs: Feature snapshots at the moment of prediction for retrospective learning.knowledge_base: RAG persistence for the autonomous agent.
⚡ Quick Start (The NEXUS Protocol)
1. Requirements
- Windows 11 (for MT5 Terminal).
- Docker Desktop.
- Python 3.12+.
2. Configuration
Fill your .env with the Supabase credentials and MT5 paths:
SUPABASE_URL=https://your-project.supabase.co
SUPABASE_KEY=your-service-role-key
MT5_PATH=C:\Program Files\LiteFinance MT5 Terminal\terminal64.exe
3. Ignition
Run the main orchestrator:
.\nexus.bat
📜 Repository Hygiene
This project follows strictly the Saneamiento Protocol:
- No binary files in Git.
- No local logs in Git.
- No environment variables in Git.
- Clean development/production branch harmonization.
<div align="center">
Built for the Next Generation of Quantitative Trading.
Powered by SrAndres629 & Antigravity Agent.
</div>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。