仓库/Skill 库

Astrid：面向可组合软件的轻量级、能力安全（capability-secure）操作系统。Astrid is a portable, capability-secure operating system for composable software.

用于本地运行 AI 的生产就绪工具包。Production ready toolkit to run AI locally

构建、管理和部署 AI/ML 系统。Build, Manage and Deploy AI/ML Systems

LLM 实战指南资源的精选清单（LLMs Tree、示例、论文）A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

面向 AI 编码 Agent 的循环工程实用模式、starter 与 CLI 工具。设计 prompt 编排 Agent 的系统（灵感来自 Addy Osmani 与 Boris Cherny）。包含 loop-audit、loop-init、loop-cost。Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.

基于 Ray 的易用、可扩展、高性能 Agentic RL 框架（PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL）An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

面向本地部署的高速 LLM 服务High-speed Large Language Model Serving for Local Deployment

Cybersecurity AI (CAI)，面向 AI 安全的框架。Cybersecurity AI (CAI), the framework for AI Security

通过修改一行代码即可将 GPT 替换为任意 LLM。Xinference 让你在云端、本地或笔记本上运行开源、语音和多模态模型，全部通过统一的生产就绪推理 API。Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

你的工作超级 Agent：本地优先，分钟级学习你的工作上下文，永不遗忘。Open-source All in One AI agent workspace. Run any agent — Claude Code, Codex — across your tools (100+ integrations + MCP), apps, browser, and files, with shared memory. Built-in models or BYOK.

轻松微调、评估和部署 Gemma 4、Qwen3.5、Qwen3.6、gpt-oss、DeepSeek-R1 或任意开源 LLM / VLM。Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!

Deeplake 是面向 Agent 的 AI 数据运行时，提供无服务器 postgres 与多模态 datalake，支持可扩展的检索与训练Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

训练你自己的 LLM 的简洁方法，覆盖从数据下载到文本生成A straightforward method for training your LLM, from downloading data to generating text.

OpenAI Codex 与 Claude Code 的通用 provider 代理 —— 可在 Codex CLI、App、SDK 及 Claude Code 中使用任意 LLM（Claude、Gemini、Grok、DeepSeek、Ollama…）。Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

🧑‍🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

提供 AI 应用和模型服务的最简方式 —— 构建模型推理 API、任务队列、LLM 应用、多模型 pipeline 等。The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

🚀💪Maximize your efficiency and productivity. The ultimate hub to manage, customize, and share prompts. (English/中文/Español/العربية). 让生产力加倍的 AI 快捷指令。更高效地管理提示词，在分享社区中发现适用于不同场景的灵感。

LTX-2 音视频生成模型的官方 Python 推理与 LoRA 训练包。Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

使用 Model Context Protocol 和简洁的工作流模式构建高效的 Agent。Build effective agents using Model Context Protocol and simple workflow patterns

Omnigent 是一个开源 AI agent 框架与元 harness：编排 Claude Code、Codex、Cursor、Pi 及自定义 agent——无需重写即可替换 harness，强制执行策略与沙箱化，并支持任意设备实时协作。Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

Transformer 可视化解析：通过交互式可视化学习 LLM Transformer 模型的工作原理。Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

⚙️🦀 使用 Rust 构建模块化、可扩展的 LLM 应用。⚙️🦀 Build modular and scalable LLM Applications in Rust

使用 Python 构建自主 AI Agent。Build autonomous AI agents in Python.

Ev​​idently 是一个开源的 ML 和 LLM 可观测性框架，评估、测试和监控任何 AI 驱动的系统或数据 pipeline，覆盖从表格数据到 Gen AI 场景，提供 100+ 指标。Evidently is ​​an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.

FinRobot：基于 LLM 的开源金融分析 AI Agent 平台 🚀 🚀 🚀FinRobot: An Open-Source AI Agent Platform for Financial Applications using LLMs 🚀 🚀 🚀

22 种 prompt engineering 技术，附带 Jupyter Notebook 实战教程，覆盖从基础概念到利用 LLM 的高级策略。22 prompt engineering techniques with hands-on Jupyter Notebook tutorials, from fundamental concepts to advanced strategies for leveraging LLMs.

掌控你的 AI。面向 AI Agent 的原生 macOS Harness——任意模型、持久记忆、自主执行、加密身份。Swift 开发，完全离线，开源。Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

基于 OpenTelemetry，为你的 GenAI 或 LLM 应用提供开源可观测性。Open-source observability for your GenAI or LLM application, based on OpenTelemetry

🔥 官方 Firecrawl MCP Server —— 为 Cursor、Claude 以及其他任意 LLM 客户端增添强大的网页抓取与搜索能力。🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

最快的 enterprise AI gateway（比 LiteLLM 快 50 倍），具备自适应负载均衡、集群模式、guardrails，支持 1000+ 模型，在 5k RPS 下额外开销 <100 µs。Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

AI 搜索平台。The AI search platform

构建端到端可控的 agent harness。面向生产级 AI agent 的开源 SDK，支持 Python 与 TypeScript —— 兼容任意模型、任意云。Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

Plano 是面向 agentic 应用的 AI 原生代理与数据平面，内置编排、安全、可观测性和智能 LLM 路由，让你专注于 agent 核心逻辑。Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.

TalkToFigma：AI Agent（Cursor、Claude Code、Codex）与 Figma 之间的 MCP 集成，使 Agentic AI 能与 Figma 通信，读取设计并以编程方式修改它们。TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.

面向并利用基础模型的数据处理！🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷