원클릭으로
quanux-hft-execution-node
Ultra-low latency C++ execution engine ("Hyper-Node") for high-frequency trading strategies.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Ultra-low latency C++ execution engine ("Hyper-Node") for high-frequency trading strategies.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Reference for OS and Kernel parameter optimization on the QuanuX Edge.
Reference for using the QuanuX Control CLI (quanuxctl).
Official Figma Developer MCP integration for QuanuX. Allows agents to inspect designs, extract variables, and generate code from Figma files.
The authoritative "School of Architecture" for building QuanuX Extensions (Sidecars). Enforces the QXP protocol, Go runtime preference, and privacy-first security model.
Instructions for operating and configuring the SignalR Bridge for TopstepX.
Guidelines for adding functions to the AST translation map for QuanuX-Annex duckdb transpiler
| name | QuanuX HFT Execution Node |
| description | Ultra-low latency C++ execution engine ("Hyper-Node") for high-frequency trading strategies. |
This directory (execution-node/cpp) contains the source code for the QuanuX High-Frequency Trading (HFT) Execution Engine. It is designed to run on bare-metal servers (Linux) with kernel-bypass networking and thread-per-core isolation to achieve nanosecond-level latency.
Key Characteristic: Inverted Data Flow Unlike traditional system where the server streams data to the node, the Hyper-Node connects directly to the exchange (or FPGA) and streams market data back to the QuanuX Grid via NATS.
graph TD
Exchange[Exchange / FPGA] -->|Direct Feed (C++)| MDE[MarketDataEngine]
MDE -->|Ring Buffer (Nanoseconds)| Strategy[Strategy Engine]
MDE -->|Async| Nats[NatsBridge]
Strategy -->|Signals| OG[Order Gateway]
Strategy -->|OrderUpdate| Nats
Nats -->|market.data.*| Grid[QuanuX Grid / UI]
Nats -->|node.telemetry.*| Risk[Risk Manager]
MarketDataEngine (src/market_data_engine.cpp)quanux_rithmic, quanux_databento) dynamically.MarketUpdate structs to a lock-free SPSC (Single-Producer Single-Consumer) Ring Buffer for the Strategy.NatsBridge for the UI/Grid.Engine (src/engine.cpp)io_uring (on Linux) for non-blocking I/O.pthread_setaffinity_np) to avoid OS context switches.Strategy (include/strategy_interface.h)extern "C") for maximum stability and compatibility..so) and loaded at runtime.on_market_data(ctx, update): Called on every tick.on_order_update(ctx, update): Called on fills/acks.on_signal(ctx, signal): (Optional) External signals.NatsBridge (src/nats_bridge.cpp)market.data.<symbol>: Live ticker stream for the Grid.node.telemetry.fills: Real-time fill reports and PnL.node.heartbeat: System health.io_uring and CPU pinning) or macOS (Dev).mkdir build && cd build
cmake -DCMAKE_BUILD_TYPE=Release ..
make -j$(nproc)
The build automatically fetches dependencies (NATS C client) via FetchContent.
Strategies implement the interface defined in include/strategy_interface.h.
Example my_strategy.cpp:
#include "strategy_interface.h"
#include <iostream>
struct StrategyContext {
int position;
};
void on_market_data(StrategyContext* ctx, const MarketUpdate* update) {
if (update->price > 100 && ctx->position == 0) {
// Buy Logic
}
}
extern "C" Strategy* create_strategy() {
static Strategy s = {
.name = "MomentumAlpha",
.on_market_data = on_market_data,
// ...
};
return &s;
}