仓库/Skill 库

本地 Codex 反向代理：轮换代理节点池、惰性健康故障转移、每模型 292 turn-state 采集/注入。支持 macOS + Windows。Local Codex reverse proxy: rotating proxy-node pool, lazy health failover, and per-model 292 turn-state collection/injection. macOS + Windows.

FreeBuff 编码模型的 OpenAI 兼容网关。Token 池、会话生命周期、TLS stealth、嵌入式管理后台。无广告、无 CLI，只有 /v1/chat/completions。OpenAI-compatible gateway for FreeBuff coding models. Token pool, session lifecycle, TLS stealth, embedded admin dashboard. No ads, no CLI, just /v1/chat/completions.

本地 AI 注册中心——硬件、模型、recipes、模型实例与价格。Local AI registry — hardware, models, recipes, model instances, and prices

AI Max+ 395 加速：在 RTX 3060 上实测的异构 GPU PD 与异步融合层 pipeline 实验。AI Max+ 395 acceleration: measured heterogeneous GPU PD and asynchronous fused-layer pipeline experiments with RTX 3060.

类似 unix du 的命令行工具，用于统计每个文件和目录的 token 使用量a unix-like du command line tool to count token usage per files and directories

repo-map 生成由 LLM 增强的软件仓库摘要与分析，为开发者提供关于项目结构、文件用途以及跨编程语言潜在考量的洞察。repo-map generates LLM-enhanced summaries and analysis of software repositories, providing developers with valuable insights into project structures, file purposes, and potential considerations across various programming languages.

使用 GPT-3 辅助撰写基金申请书的实验Experiment to use GPT-3 to help write grant proposals.

Run the native 284B-A13B DeepSeek-V4-Flash-0731 LLM locally on one laptop CPU: pure C, 8 GB RAM minimum, no GPU, best TPOT 0.892 s/token, resident OpenAI-compatible API with function tools. | 在笔记本单颗 CPU 上本地运行原生 284B-A13B DeepSeek-V4-Flash-0731 大模型：纯 C，最低 8 GB 内存，无需 GPU，最优 TPOT 0.892 秒/token，支持模型常驻的 OpenAI 兼容接口与函数工具。

🦙 使用 Ollama CLI 配置 GitHub Actions。🦙 Set up GitHub Actions with Ollama CLI.

Memory OS CLI 和 npm 包Memory OS CLI and npm package

通用学术写作 Agent Skill：论文润色、中英互译、学位论文与基金申请、审稿回复与投稿材料，适用于各学科；不改数据、不编文献、不夸大结论。支持 Claude Code、Codex、Cursor、Grok Build、OpenCode，复制提示词即可安装。

并行运行 Claude Code、Codex 与 Gemini，并支持彼此交接任务。面向 AI CLI 的便携 Windows 终端。Run Claude Code, Codex and Gemini side by side — and let them hand work to each other. Portable Windows terminal for AI CLIs.

💻 在 macOS 上借助 Metal GPU 实现 Qwen3 Transformer 模型，获得加速且高效的性能，并支持关键架构特性💻 Implement Qwen3 transformer model on macOS using Metal GPU for accelerated, efficient performance with support for key architecture features.

开放兼容性测试网络：该库 API 是否能在你的版本、操作系统和运行时上真正运行？提供真实构建证据、已验证样本以及每个结果对应的运行环境。An open compatibility testing network: does this library API actually run on your version, OS and runtime? Real build evidence, verified samples, and the environment each result came from.

轻松优化面向 AI 系统的 prompt，借助直观工具与特性提升性能🚀 Optimize your prompts for AI systems easily and boost performance with intuitive tools and features designed for better results.

一个可复用的 Codex Skill，用于证据对齐、AI 与人工审稿人就绪的学术写作。A reusable Codex skill for evidence-aligned, AI- and human-reviewer-ready academic writing.

Codex + DeepSeek 的任务感知推理模式路由（spec/react/weak）Task-aware reasoning-mode router for Codex + DeepSeek | Codex+DeepSeek 思维模式路由（spec/react/weak）

构建 LongCat-Flash-Prover，利用 LongCat 模型进行快速定理证明与形式化推理。Build LongCat-Flash-Prover for fast theorem proving and formal reasoning with LongCat models

本代码库提供个人研究成果《Deep Learning Approach in Time Series Forecasting: Literature Review and Extension on Feature Extraction》的代码与报告存档。This repository provides code and report archive of individual research: Deep Learning Approach in Time Series Forecasting: Literature Review and Extension on Feature Extraction

The Convergence Gap 的代码与 artifact：指令微调模型何时收敛到下一 token 预测Code and artifacts for The Convergence Gap: when instruction-tuned models settle on next-token predictions.

prompt工具箱

生产级 LLM 网关：兼容 OpenAI 的 API，支持语义缓存，可在 Claude/OpenAI/Ollama 之间进行智能路由与成本分析。Production LLM gateway: OpenAI-compatible API, semantic caching, intelligent routing across Claude/OpenAI/Ollama, cost analytics.

使用 TurboQuant 和 MLX 在 Windows 上运行 Qwen3.5 语言模型，实现快速的本地推理。Run the Qwen3.5 language model on Windows using TurboQuant and MLX for fast local performance.

在双 RTX 3090 GPU 上以 262K 上下文长度并发流运行 Qwen3.6-27B，开发工作已迁移至 club-3090。Run Qwen3.6-27B at 262K context with concurrent streams on dual RTX 3090 GPUs. Development moved to club-3090.

本地优先、隐私至上的 AI 驱动学术写作人性化工具。AI-Powered Academic Writing Humanizer - Local-First, Privacy-Centric Solution

使用支持 macOS 和 Windows 平台的开源工具高效构建与定制机器学习模型Build and customize machine learning models efficiently with an open-source tool that supports macOS and Windows platforms.

通过单一严格的 YAML 清单统一管理本地 LLM 运行时——支持状态查看、健康检查、启动、停止，基于原生 systemd 与 Docker。Manage local LLM runtimes from one strict YAML manifest — status, doctor, start, stop over native systemd and Docker.

Codex skill，面向交通运输与低空出行领域的学术写作（知识蒸馏自 LT）。Codex skill for transportation and low-altitude mobility academic writing (Knowledge distillation from LT)

🚀 通过 autopack 简化 Hugging Face 模型的运行、分享与发布，自动完成量化与多格式导出🚀 Simplify running, sharing, and shipping Hugging Face models with autopack; it quantizes and exports to multiple formats effortlessly.

AI-Core 2026：面向 OpenAI、Anthropic、Gemini 与 Grok API 管理的集中化 WordPress AI Provider 中枢。AI-Core 2026: Centralized WordPress AI Provider Hub for OpenAI, Anthropic, Gemini & Grok API Management

Arcee AI —— 由 API Evangelist 提供的独立第三方公开 API 画像。Arcee AI 是一家美国开放智能研究实验室，构建并发布小型、高效的开源权重语言模型（Trinity 系列、AFM-4.5B 以及 Virtuoso/Maestro 衍生模型），并提供运行这些模型的开发者平台。Arcee AI — independent third-party profile of a public API surface, by API Evangelist. Arcee AI is an American open-intelligence research lab that builds and releases small, efficient open-weight language models (the Trinity family, AFM-4.5B, and Virtuoso/Maestro derivatives) along with a developer platform for running them.