Cross-platform shared memory stream/buffer, header-only library for low-level IPC in C/C++ with FFI bindings for Rust, Zig and Go.

Header only high-performance cross-platform shared memory IPC library.

Code for 'Forecasting Realized Volatility with Time Series Foundation Models: A Comparison with Econometric Benchmarks' (arXiv:2607.05291)

The official code implementation for MCI-GRU: Stock Prediction Model Based on Multi-Head Cross-Attention and Improved GRU.

The code for 'A Novel Neural Architecture with Multi-level Feature Extraction Coordinated by Dendritic Classifier'

A lightweight data processing framework built on DuckDB and 3FS.

Low-level C++ performance guidelines for game-engine and embedded systems — the technique layer below the ISO C++ Core Guidelines

Learn it. Build it. Ship it for others.

A collection of skills for AI financial analysis.

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

Academic Research Skills for Claude Code: research → write → review → revise → finalize

ATLAS by General Intelligence Capital — Self-improving AI trading agents using Karpathy-style autoresearch

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

[arXiv:2510.06261] "AlphaApollo: A System for Deep Agentic Reasoning"

C++ microbenchmark challenges for HFT University

PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.

AKQuant is a high-performance quantitative research and trading framework built on Rust and Python! 开源量化回测框架

TradingAgents: Multi-Agents LLM Financial Trading Framework

Open-source implementation of AlphaEvolve

DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

Official implementation for AAAI2025: AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors

Official implementation of AlphaSAGE: Structure-Aware Alpha Mining via GFlowNets for Robust Exploration (https://arxiv.org/abs/2509.25055).

Autonomous AI development loop for Claude Code with intelligent exit detection

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models, ICLR 2025 (Outstanding Paper)

FactorMiner 是一个面向量化研究的因子挖掘工作台。V4 以配置驱动的 Python 引擎为核心，提供 FastAPI + React WebUI、CLI、可持久化的因子档案，以及可由用户工作区扩展的 GP、RL、LLM 与 NN 挖掘范式。

🤖 基于深度学习的AI量化投资系统 | Vision-Based Quantitative Trading System with Deep Learning

Drop-in PyTorch module decorator for transparent per-sample caching with Arrow IPC backend—cache frozen feature extractors once, train faster forever.