仓库/Skill 库

精选的 LLM、AI 绘画等领域的教程和资源。Curated tutorials and resources for Large Language Models, AI Painting, and more.

构建 Agent 的开源框架The Open Framework for Building Agents

面向 AI 编码 agent 的首选本地优先网页工具——基于 MCP 提供搜索、抓取、爬取与研究能力。无需 API key，无需云端，$0/query。现已开放公开测试。The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.

面向 Claude Code、Codex 和其他 AI 工具的 SwiftUI Agent Skill。SwiftUI agent skill for Claude Code, Codex, and other AI tools.

RLHF 精选资源列表（持续更新）。A curated list of reinforcement learning with human feedback resources (continually updated)

高质量且极速的预训练深度学习模型与 demo。Pre-trained Deep Learning models and demos (high quality and extremely fast)

TypeDB：为系统而生，而非为记录而生。TypeDB: Built for systems, not records

终端中的 Agent，配备本地工具：编写代码、使用终端、浏览网页。在其之上构建你自己的持久化自主 Agent。Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!

免费学习如何使用 LLMOps 最佳实践构建端到端生产级 LLM & RAG 系统：源码 + 12 个实操课程。🤖 𝗟𝗲𝗮𝗿𝗻 for 𝗳𝗿𝗲𝗲 how to 𝗯𝘂𝗶𝗹𝗱 an end-to-end 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗟𝗟𝗠 & 𝗥𝗔𝗚 𝘀𝘆𝘀𝘁𝗲𝗺 using 𝗟𝗟𝗠𝗢𝗽𝘀 best practices: ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 12 𝘩𝘢𝘯𝘥𝘴-𝘰𝘯 𝘭𝘦𝘴𝘴𝘰𝘯𝘴

面向 AI Agent 的开发者控制平面Developer Control Plane for your AI Agents

Zotero 插件，用于管理附件：自动重命名、移动并附加 PDF（或其他文件）到 Zotero 条目；将 Zotero 库中的 PDF 同步到（移动端）PDF 阅读器（如 iPad、安卓平板等）；并提取 PDF 批注。Zotero plugin to manage your attachments: automatically rename, move, and attach PDFs (or other files) to Zotero items, sync PDFs from your Zotero library to your (mobile) PDF reader (e.g. an iPad, Android tablet, etc.), and extract PDF annotations.

一个覆盖文本、图像、视频与音频任务的统一多模态评估工具包。One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

GPT Image 2 的 prompt gallery、image prompt library、agentic skill 以及用于 OpenAI 图像生成/编辑的 CLI。GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing

大型多模态模型 LMM 的开源评估工具包，支持 220+ LMM 与 80+ 基准测试。Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

非官方的、极好的 Home Assistant MCP Server。The Unofficial and Awesome Home Assistant MCP Server

思维导图、知识管理、项目管理应用。以最高效的方式构建、组织与传达你的想法和知识。Application for Mind Mapping, Knowledge Management, Project Management. Develop, organize and communicate your ideas and knowledge in the most effective way.

【三年面试五年模拟】AIGC/LLM/AI Agent算法工程师面试秘籍。涵盖AIGC、LLM大模型、AI Agent、具身智能、传统深度学习、自动驾驶、机器学习、计算机视觉、自然语言处理、强化学习、大数据挖掘、世界模型、元宇宙、AGI等AI行业面试笔试干货经验与核心知识。

开源 LLMOps 平台：集成 prompt playground、prompt 管理、LLM 评估和 LLM 可观测性。The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.

一款 AI Gateway、registry 与 proxy，置于任意 MCP、A2A 或 REST/gRPC API 之前，提供统一端点，具备集中化发现、guardrails 与管理能力。优化 Agent 与工具调用，并支持插件。An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.

使用 Zig 和 Web UI 构建桌面与移动应用Build desktop + mobile apps with Zig and web UI

Agent Skill。Agent Skills

为 LLM 优化推理代理Optimizing inference proxy for LLMs

收录公开漏洞利用 PoC 与漏洞研究技术报告的单一归档库。本人在发布时这些内容尚未被披露，欢迎自行上报并领取 CVE 编号（若获分配，权当一乐）。请勿滥用。我做这件事是为了吸引更多人进入这一领域，并且一直认为这是最高效的方式。A single archive of public exploit PoCs and vulnerability research writeups. At the time I post these, none have been reported. Feel free to report them yourself and take credit for the CVE if handed out lulz. Please do not abuse these. I do this so to allure people into the field, and I've always found this is the most efficient way.

CSGHub 是 OpenCSG 团队开发的全新开源 LLM 管理平台，提供开源与本地化/SaaS 解决方案，功能对标 Hugging Face。兼容 Hugging Face Python SDK，全面掌控 LLM、数据集和 agent 的全生命周期。CSGHub is a brand-new open-source platform for managing LLMs, developed by the OpenCSG team. It offers both open-source and on-premise/SaaS solutions, with features comparable to Hugging Face. Gain full control over the lifecycle of LLMs, datasets, and agents, with Python SDK compatibility with Hugging Face. Join us! ⭐️

将参考图像中的对象重建为纯代码、程序化、带质量门控、可动画化的 Three.js 模型。token 高效的图像到三维转换。Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

:orange_book: 面向 Offensive Security OSCP、OSWE、OSCE、OSEE、OSWP 考试报告的 Markdown 模板:orange_book: Markdown Templates for Offensive Security OSCP, OSWE, OSCE, OSEE, OSWP exam report

Python 终端多功能工具——OSINT、Discord、Web 与网络工具集。Rich TUI，13 种主题，支持远程更新。仅供学习使用。Python terminal multitool — OSINT, Discord, web & network utilities. Rich TUI, 13 themes, remote updates. Educational use only.

面向编码 Agent 的程序化视频方案——在本地将 HTML 转视频。把 HTML、CSS 与数据渲染为真实 MP4，支持可插拔渲染引擎、21 套模板与 AI 配乐。Apache-2.0，无按次计费。Open Design 团队的官方项目。Programmatic video for coding agents — HTML to video on your laptop. Turn HTML, CSS & data into real MP4s with pluggable render engines, 21 templates, AI soundtrack. Apache-2.0, no per-render fees. An official project by the Open Design team.

针对加速基础设施和微服务架构优化的生成式 AI 参考工作流。Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

一款可自动从 sci-hub 下载 Zotero 条目对应 PDF 的插件。A plugin that will automatically download PDFs of zotero items from sci-hub

使用 R Markdown 撰写书籍与技术文档Authoring Books and Technical Documents with R Markdown

PaperSpine 是以动机驱动的 Skill，用于研读高质量学术论文、构建论文核心论点，并通过证据感知蓝图、修订矩阵与 LaTeX 安全审计来重写稿件。PaperSpine is a motivation-driven skill for learning from strong academic papers, building a paper’s central argument, and rewriting manuscripts through evidence-aware blueprints, revision matrices, and LaTeX-safe audits.

在 Kubernetes 上借助现代加速器实现 SOTA 推理性能。Achieve state of the art inference performance with modern accelerators on Kubernetes

ChatGPT、Claude 等 LLM 的所有前端 GUI 客户端汇总。Every front-end GUI client for ChatGPT, Claude, and other LLMs

任意模型，任意硬件，零妥协。基于 @ziglang / @openxla / MLIR / @bazelbuild 构建。Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild