趋势榜

数据与 AI 的开放上下文层；OpenMetadata 是为人类、AI 助手和 agent 构建可信数据上下文与业务语义的开源平台。The Open Context Layer for Data and AI , OpenMetadata is the open platform for building trusted data context and business semantics for humans, AI assistants, and agents.

🦸 AI 编程超能力 · 中文增强版 — superpowers（116k+ ⭐）完整汉化 + 6 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI 等 16 款 AI 编程工具真正会干活

AI 搜索平台。The AI search platform

用于构建复杂创新 RAG 流水线的低代码 MCP 框架A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

面向常驻 Agent 的开源个人云操作系统。Open-Source Personal Cloud OS for Always-On Agents

面向 monorepo 的终极 RAG。借助 AI 与知识图谱的能力，对多语言代码库进行查询、理解与编辑。The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

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!

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

AgentENV (AENV) 是一个用于大规模运行 Agent 环境的分布式平台。AgentENV (AENV) is a distributed platform for running agent environments at scale.

基于 Three.js 构建的使命召唤品质级 FPS 游戏，仅由一条 prompt 生成。A Call of Duty-quality FPS in Three.js, built from a single prompt.

面向编码 Agent 的通用 Playwright 自动化。General-purpose Playwright automation for coding agents

独立 iOS 应用，可在无需越狱的情况下模拟 GPS 定位。包含 Shadowrocket/Surge/Loon/QX/Stash 模块。Standalone iOS app to spoof GPS location without jailbreak. Includes Shadowrocket/Surge/Loon/QX/Stash module.

把 Markdown 一键排成可直接粘进公众号编辑器的精致 HTML —— 6 套精选主题 + 主题生成器 + 双关卡校验。An AI-agent skill that turns Markdown into paste-ready WeChat article HTML.

SOTA 低比特 LLM 量化（INT8/FP8/MXFP8/INT4/MXFP4/NVFP4）与稀疏化方案；面向 PyTorch、TensorFlow 与 ONNX Runtime 的领先模型压缩技术SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

一个简洁、高性能且可扩展的 Jax LLM！A simple, performant, and scalable Jax LLM!

可扩展的 LLM 数据预处理与清洗工具集Scalable data pre processing and curation toolkit for LLMs

用于加速工作流程的自定义 AI Agent 平台Custom AI agent platform to speed up your work.

Daily updated LLM papers. 每日更新 LLM 相关的论文，欢迎订阅 👏 喜欢的话动动你的小手 🌟 一个

AI 代码审查，完全掌控模型选择与成本。AI Code Review with Full Control Over Model Choice and Costs.

社区最全面、持续更新的 LLM 软件漏洞检测研究索引——涵盖函数级、仓库级、Agent 级以及智能合约检测方向的论文，并附数据集、基准和综述The community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection — papers across function-level, repository-level, agentic, and smart-contract detection, plus datasets, benchmarks, and surveys.

面向 LLM 和 LVLM 的强大模型压缩框架，适配 NVIDIA GPU 和华为昇腾 NPUA powerful model compression framework for LLMs and LVLMs, adapted for NVIDIA GPUs and Huawei Ascend NPUs.

学术专著（如学位论文）的 LaTeX 模板，同时面向 LaTeX 初学者与熟练用户A LaTeX template for academic monographs (e.g., dissertations and thesis). This template serves both beginners and proficient LaTeX users.

MiniMax H3 Mac 推理引擎。MiniMax H3 inference engine for Mac computers

基于自主编码 Agent 的开源自动研究系统。运行 Claude Code、OpenCode 与 Codex，具备评分、共享知识与多 Agent 进化功能。被 COLM 2026 接收。Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.

面向 C# 与 F# 的开源跨平台符号代数库，可同时用于生产与研究Open-source cross-platform symbolic algebra library for C# and F#. Can be used for both production and research purposes.

AI 短剧制作的 skill 集合：拆角色、出设定图、排大纲 | Agent skills for AI short-drama production — character bibles, model sheets, adaptation outlines. Runs in Claude Code & codex.

论文"LAMBDA: A large Model Based Data Agent"的官方仓库。https://www.polyu.edu.hk/ama/cmfai/lambda.htmlThis is the offical repository of paper "LAMBDA: A large Model Based Data Agent". https://www.polyu.edu.hk/ama/cmfai/lambda.html

长时程计算机使用 harness。让 AI Agent 在桌面应用与 CLI 中长时间运行，同时保持任务状态并在复杂工作流中可靠推进。具备全新上下文执行、持久化已验证状态、独立审计、可恢复进度以及原生 Claude Code / Codex / OpenClaw 集成。The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.

Krasis 是一个混合 LLM 运行时，专注于在消费级 VRAM 受限硬件上高效运行大模型Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware

关于大语言模型 On-Policy Distillation 的精选论文与资源合集A curated collection of papers and resources on On-Policy Distillation for Large Language Models.

我的AI小镇

繁体中文（zh-TW）的语言学 linter。A linguistic linter for Traditional Chinese (zh-TW)

面向 vibe coder 与系统管理员的超级工具——终端、SSH、SFTP、RDP/VNC、仪表盘、安装助手，以及内置 AI 助手。Super-tool for vibe coders & system admins — terminals, SSH, SFTP, RDP/VNC, dashboards, install helpers, and a built-in AI assistant.

基于文件、使用 Markdown 的 wikiA file based wiki that uses markdown

面向 AI Agent 的上下文工程。token 消耗减少约 80%。解决工具过载问题。内置进程内 BM25 与语义检索的 Skill 与 memory。支持渐进式披露（Progressive Disclosure）。无需向量数据库。Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

面向 AI agent 的最佳浏览器，使用 Rust 构建。Best browser for AI agents, built in Rust.

Vocat 是一款面向 Quectel EC20/EC25 系列蜂窝模组的开源 Web 控制面板与工程工具集，整合了模组发现、实时射频状态、AT 与 USSD 终端、短信、WiFi Calling、eSIM 管理、网络选择、代理路由、通知、审计日志与发布自动化于一体。Vocat is an open-source web control panel and engineering toolkit for Quectel EC20/EC25-class cellular modems. It combines modem discovery, live radio status, AT and USSD terminals, SMS, WiFi Calling, eSIM management, network selection, proxy routing, notifications, audit logs, and release automation in one self-contained service.

嵌入式 Agent，让客户用于自动化工作、构建视图并连接其工具。Embedded agents your customers use to automate work, build views, and connect their tools.

Vibe-Coding 很简单，DevOps 很难。OpenCode 与 Git 的 token 高效 AI agent 自动化，面向应用、商业和个人开发。面向速度、安全性和 7×24 效果的强势工具、服务、CLI 和 API 技术栈。开源优先，处处 SOTA。在你的仓库上试用，体验赚钱魔力。Vibe-Coding is easy. DevOps is hard. OpenCode & Git token-efficient AI agent automation for your app, business, and personal development. Opinionated tools, services, CLI & API stack for speed, security, and 24/7 results. Open-source first. SOTA everything. Try on your repos for money-making magic.

仓库级代码生成与 Issue 修复必读论文 🔥Must-read papers on Repository-level Code Generation & Issue Resolution 🔥

决定你的 AI 编码 Agent 阅读哪些内容，并保留凭证。每次裁剪都可逐字节恢复，从不杜撰结果，所有数据从你自己的语料库回放。Decides what your AI coding agent reads, and keeps receipts. Every cut is recoverable byte for byte, it never invents a result, and the numbers are replayed from your own corpus.

Kelos——面向自主 AI 编程 Agent 编排的 Kubernetes 原生框架。Kelos - The Kubernetes-native framework for orchestrating autonomous AI coding agents.

一种极简的硬件-软件架构，为大语言模型提供具有自感知回路的闭环物理具身。A minimal hardware-software architecture giving large language models a closed-loop physical embodiment with self-perception loops.

面向编码 Agent 的原生 macOS 编排器——可在 git worktree 与远程主机上并行运行 Claude Code、Codex、Cursor、Gemini 与 shell。Native macOS orchestrator for coding agents — run Claude Code, Codex, Cursor, Gemini and shells in parallel across git worktrees and remote hosts

面向 Forward Deployed Engineer 的第二大脑：在 discovery、交付与交接全过程中提供 engagement 记忆与执行 Skill。Second brain for Forward Deployed Engineers: engagement memory + execution skills across discovery, delivery, and handoff.

🪢 Langfuse 文档——Langfuse 是开源 LLM 工程平台，提供可观测性、评估、Prompt 管理、Playground 与指标，用于调试与改进 LLM 应用🪢 Langfuse documentation -- Langfuse is the open source LLM Engineering Platform. Observability, evals, prompt management, playground and metrics to debug and improve LLM apps

ServiceNow MCP server：450+ 工具与 26 项 AI 能力，适配任意 AI（Claude、ChatGPT、Gemini、Cursor、Copilot）。多传输（stdio、SSE、HTTP）、A2A、动态 schema 发现、默认只读。免费且源代码可用，属于 NowAIKit 套件。ServiceNow MCP server: 450+ tools and 26 AI capabilities for any AI (Claude, ChatGPT, Gemini, Cursor, Copilot). Multi-transport (stdio, SSE, HTTP), A2A, dynamic schema discovery, read-only by default. Free and source available. Part of the NowAIKit suite.

面向教育领域的人工智能（AI）与大语言模型（LLM）论文精选。Awesome artificial intelligence (AI) and large language model (LLM) for education papers.

Opptrix——AI 驱动的全球多市场投研工作台 | 面向中国 A 股的开源 LLM 投研助手。170+ MCP 工具、因子筛选、回测、自选股与 Electron 桌面端。TypeScript · React · Fastify monorepo。Opptrix — AI驱动的全球多市场投研工作台 | Open-source LLM research assistant for China A-shares. 170+ MCP tools, factor screening, backtest, watchlist & Electron desktop. TypeScript · React · Fastify monorepo.

LLM7.io 提供单一 API 网关，可连接来自多家供应商的众多领先 AI 模型LLM7.io offers a single API gateway that connects you to a wide array of leading AI models from various providers.

[ICML 2026] effGen：让小型语言模型具备自主 Agent 能力[ICML 2026] effGen: Enabling Small Language Models as Capable Autonomous Agents

在两台 dgx-spark 上从零部署 deepseek-flash-0731 的设置指南。setup guide for deepseek-flash-0731 on two dgx-spark from scratch

AI Agent 工程师面试资料库 - 国内大厂面经、岗位要求、高频面试题

开源办公 Agent 与游戏平台 Beta 2026。Open Source Office Agent & Game Platform Beta 2026

2026 年度顶级开源 AI 工程平台 Qyvaria KernelTop Open-Source AI Engineering Platform 2026 Qyvaria Kernel

面向 SolCex Exchange 的自主 AI BD Agent：7×24 跨链代币评分与支付 2026。Autonomous AI BD Agent for SolCex Exchange: 24/7 Cross-Chain Token Scoring & Payments 2026

Unica (Ю́ника)——面向 1С:Предприятие 开发的 Codex 与 Claude Code 公开插件。Unica (Ю́ника) — публичный плагин Codex и Claude Code для разработки на 1С:Предприятии.

本地法语语音助手：支持 Claude 或 Ollama（离线）、Hue 智能家居、OBS、日历、浏览器、Twilio 通话与 MCP server。基于 Python。Assistant vocal local en francais : Claude ou Ollama (offline), domotique Hue, OBS, agenda, navigateur, appels Twilio, serveur MCP. Python.

303 份 AI/LLM 中文讲义，支持在线阅读、PDF 下载和 LaTeX 源码查看 | Stanford CS336/CS224R/CS25 | Berkeley LLM Agents | Agent 工程实践

Claude Fable 5 终极指南 2026：使用场景、集成与基准测试Ultimate Claude Fable 5 Guide 2026: Use Cases, Integrations & Benchmarks

围绕代码 Agent 的前沿研究活体合集，从我们构建的代码到我们行动的世界。A living collection of frontier research on code agents, from the code we build to the worlds we act in.

面向 macOS 的强约束 AI 编码 Agent 与开发环境自动化Opinionated AI coding agent and dev environment automation for macOS

Agent Skills for Xiaohongshu 冷启动、定位、选题库、人格化稿件、视觉策划与审稿闭环Agent Skills for Xiaohongshu cold start, positioning, topic bank, humanized drafts, visual planning, and review loops

2026 年在社交信息流中通过实时聊天机器人模拟 AI 人格Simulate AI Personas in Social Feeds with Real-Time Chat Bots 2026

降AIGC率，降低知网、维普、格子达平台的AIGC检测率，降知网AI，降维普AI，降格子达AI。

:bookmark_tabs: 开放 CS/AI 知识库，包括「基础知识、数据结构与算法、软件开发、大模型」等体系化的笔记

A 股AI行情分析与智能投研工作台-基于大模型

面向实验的 GenAI/RAG 优化器与工具包，基于 Oracle Database AI Vector Search 与 NL2SQLGenAI/RAG Optimizer and Toolkit for experimentation using Oracle Database AI Vector Search and NL2SQL

由 LLM 驱动的科研自动化 AgentLLM-powered agents for scientific research automation

将 Minimax-H3 蒸馏为 4 步。Distill Minimax-H3 into 4 steps

代码智能 CLI——覆盖 34 种语言的函数级依赖图、为 AI agent 提供 34 工具的 MCP server、复杂度度量、架构边界强制、CI 质量门禁、git diff 影响分析（含 co-change 分析）、混合语义搜索。完全本地运行，无需 API key。Code intelligence CLI — function-level dependency graph across 34 languages, 34-tool MCP server for AI agents, complexity metrics, architecture boundary enforcement, CI quality gates, git diff impact with co-change analysis, hybrid semantic search. Fully local, zero API keys required.

我刚刚创建了自己的 bot，迫不及待想与你分享我的成果！I’ve just created my own bot and I’m excited to share my work with you!

恐惧、不确定以及……终端。fear, uncertainty and ... terminals

面向 Node.js、浏览器与 serverless 运行时的纯 TypeScript 低内存、零依赖图像编解码与处理库。具备有界解码/缩放管线，并提供深度 TIFF、科学栅格、GeoTIFF、OME-TIFF 与全切片成像支持。Low-memory, zero-dependency image codecs and processing in pure TypeScript for Node.js, browsers, and serverless runtimes. Bounded decode/resize pipelines plus deep TIFF, scientific raster, GeoTIFF, OME-TIFF, and whole-slide support.

基于 SableDB 用 Rust 构建的 Passkey 优先认证方案。Passkey-first authentication built in Rust on SableDB.

更便宜且更优秀的 Greptile 替代方案，运行在你自己的 GitHub Actions 上。Cheaper and better Greptile alternative runs on your own github actions.

本地优先的 AI 辅助科研工作空间，面向科学写作与出版。支持 LaTeX / Typst / Markdown 原生排版，覆盖调研、写作、编译、验证到发表全流程，Git-native，开源，桌面级性能。The local-first AI assisted research workspace for scientific writing & publishing. Research, Write, Compile, Verify and Publish in LaTeX • Typst • Markdown • Git-native • Open Source • Desktop Performance

Elixir 实现的 TRINITY（进化型 LLM 协调器）：通过小模型隐藏状态路由器 + Axon 协调头路由 LLM 调用，采用 Thinker/Worker/Verifier 编排与基于验收驱动的策略循环TRINITY in Elixir (An Evolved LLM Coordinator): route LLM calls via a small-model hidden-state router + Axon coordination head, with Thinker/Worker/Verifier orchestration and policy loop for acceptance-driven completion.

⚡ Translate Markdown without breaking format — code blocks, LaTeX, links all preserved ｜ 翻译 Markdown 不破坏格式，代码块、LaTeX 公式、链接全保留

textlog.cctextlog.cc

Ydisks云盘转存助手，支持百度云盘、夸克云盘、迅雷云盘的批量转存工具。

真实 AI Agent 安全事件、入侵和漏洞的精选时间线（2024-2026）。每条记录均标注来源和日期。A curated timeline of real AI agent security incidents, breaches, and vulnerabilities (2024-2026). Every entry sourced and dated.

Civitai / HuggingFace 模型下载、管理、反向解析工具（免费全功能）

面向 ARM Cortex-M 与 RISC-V 的确定性固件模拟器，具备硬件验证的一致性。Deterministic firmware simulator for ARM Cortex-M and RISC-V — with hardware-validated parity

零运行时依赖的 CLI，用于搭建、检查并安全刷新双语 Node.js 与 Python 开源仓库。Zero-runtime-dependency CLI to scaffold, audit, and safely refresh bilingual Node.js and Python open-source repositories.

面向 AI Agent 的集中式 SSH 网关，提供 MCP 接入、凭据托管、细粒度授权与全程审计。

即插即用、成本高效且轻量化的长周期 LLM Agent 记忆插件A Plug-and-Play, Cost-Efficient, and Lightweight Memory Plugin for Long-Horizon LLM Agents

AI Agent 就绪的 CLI 框架，用于 Excel VBA 项目的编辑、测试、运行、追踪与差异比对。AI-Agent-ready CLI framework for editing, testing, running, tracing, and diffing Excel VBA projects.

基于 Cloudflare Workers 驱动的 ESP32 个人桌面 Agent。Personal desk agent for ESP32, powered by Cloudflare Workers

面向编程 Agent 的更快运行时。平均提速 25%、降本 30%，同时质量持平或更优。同等任务、同等质量，更快更便宜。Faster runtime for coding agents. Make coding agents 25% faster and 30% cheaper on average while keeping the quality same or more. Same Task, Same Quality, Faster and Cheaper.

开源、自托管的 Linear 替代方案。项目管理与 issue tracking，团队与 AI Agent 并肩协作完成产品规划与交付。Open-source, self-hosted alternative to Linear. Project management and issue tracking where teams and AI agents work side by side to plan and ship products.

AI 编写软件的记录系统。实体、关系、变更与来源的持久化图谱，使人类和 AI Agent 在合并前看到变更影响范围。目前与 Git 并行使用。The system of record for AI-written software. A persistent graph of entities, relationships, changes, and provenance, so humans and AI agents see what a change touches before it merges. Beside Git today.

Huly MCP 和 CLI：面向 Huly 平台的功能完备的 MCP 服务器和 CLI。Huly MCP and CLI: Feature-complete MCP server and CLI for Huly platform

面向长时对话记忆层的综合基准测试框架A Comprehensive Benchmarking Framework for Long-Term Conversational Memory Layers

基于 cocoon 的快速冷启动 MicroVM 沙箱，为 AI Agent 提供隔离运行环境。Fast cold-boot MicroVM sandboxes for AI agents on cocoon

生产级多 Agent 编排引擎。从可插拔的 Agent、LLM、工具与 retriever 目录组合 Agentic 工作流；本地使用 LangGraph 执行，或通过 Temporal 分布式执行。内置 RAG 管道用于企业知识检索，支持 A2A 与 MCP 协议，提供可视化拖拽蓝图构建器。Production-grade multi-agent orchestration engine. Compose agentic workflows from a pluggable catalog of Agents, LLMs, tools, and retrievers. Execute locally with LangGraph or distributed with Temporal. Built-in RAG pipeline for enterprise knowledge retrieval. A2A and MCP protocol support. Visual drag-and-drop blueprint builder.

面向软件开发的多 Agent 系统Multi-agent system for software development

面向 coding agent 的本地护栏机制：策略、审批、86 个安全策略包、操作系统级沙箱、审计追踪，无需 Docker。Local guardrails for coding agents. Policy, approvals, 86 safety packs, OS sandbox, audit trail — no Docker.

一种基于大语言模型、采用人在回路的科学模式挖掘工作流A Human-in-the-Loop Workflow for Scientific Schema Mining with Large Language Models

走向可复现研究的初步步骤（极简教程）Initial steps toward reproducible research (a minimal tutorial)

在终端里像审查 PR 一样审查你的工作变更。块级实时 diff、GitHub/GitLab PR 审查，并支持发送给 AI Agent。Review your working changes like a pull request — in the terminal. Block-scoped live diffs, GitHub/GitLab PR review, and send-to-AI-agent.

面向 WordPress 的 Agentic 操作系统。Agentic operating system for WordPress.

ImageTrans 插件集合。Plugins for ImageTrans

对人类而言，语言是表达的工具；对 AI 而言，语言是推理的基底。For humans, a language is a tool for expression. For AIs, it's a substrate for reasoning.

面向 harness 工程、loop 工程、graph 工程，以及本地 AI Agent 工作流未来形态的桌面应用。Desktop app for harness engineering, loop engineering, graph engineering—and whatever comes next in local AI-agent workflows.

热门 claude-skills 与 AI Agent 仓库的自动更新排行榜，每 15 分钟刷新一次。Auto-updated leaderboard of trending claude-skills and AI agent repos, refreshed every 15 minutes

面向编码 Agent 的持久化、可验证记忆 — 让它们不再重复解释你的代码库，也不再基于过时知识行动。每条记忆都与实际代码校验，以纯文本文件存放在仓库中，通过 git 共享。无需账号，无需数据库。安装：npx -y @kage-core/kage-graph-mcp installPersistent, verified memory for coding agents — so they stop re-explaining your codebase and never act on stale knowledge. Every memory is checked against your actual code; lives in your repo as plain files, shared via git. No account, no DB. Install: npx -y @kage-core/kage-graph-mcp install

AI 原生的结构化数据 wire 格式。在每个前沿模型上实现 100% 理解，比 JSON 减少 50-92% token，跨 17 种格式完成 43B+ 无损往返。Spec v3.4 Stable。The AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless round-trips across 17 formats. Spec v3.4 Stable.

排名第一的 Obsidian AI 记忆 MCP——时效感知、引用可追溯、本地优先且默认只读。支持 Dataview、Bases、PDF，适配各类 agent。The #1 Obsidian MCP for AI memory — freshness-aware, cited, local-first and read-only by default. Dataview, Bases, PDFs, every agent.

发布 AI Agent 制品，而非 demo 表演 — 验证器把关、跨模型族运行，自动学习哪个模型最优。Ship AI-agent artifacts, not demo theater — verifier-gated, cross-family runs that learn which model wins.

让 AI 编码 Agent（Claude、Codex、Gemini 等）无人值守运行——自动应答 prompt、遇限流自动重试，并可在本地或通过 agent-yes.com 列出 / 跟踪 / 操控每个 Agent。Run AI coding agents (Claude, Codex, Gemini …) unattended — auto-answer prompts, auto-retry on rate limits, and list/tail/steer every agent locally or from agent-yes.com

保存文章、AI 研究来源和 newsletter 邮件链接。准备好时再阅读。无第三方追踪。由 js-cookie 的作者基于其 10 年个人阅读系统打造。Save articles, AI research sources, and newsletter email links. Read them when you're ready. No third-party tracking. Built by the creator of js-cookie from a 10-year personal reading system.

面向 PubMed 与多源生物医学研究的 MCP SDK v2 server，具备弹性搜索、全文获取、引用功能与多租户安全部署。MCP SDK v2 server for PubMed and multi-source biomedical research, with resilient search, full text, citations, and tenant-safe deployment.

开源、MIT 许可的食品、营养与农业科学研究技能，面向 Claude Code、Codex、MiniMax Agent、OpenClaw 与 Grok Build —— 支持多 Agent 文献/系统综述、期刊感知写作、同行评审、项目申请书、图表与可编辑 PPTX，并提供 150+ 期刊的作者指南。来自墨尔本大学 Food Science Group。Open, MIT-licensed food, nutrition & agricultural science research skills for Claude Code, Codex, MiniMax Agent, OpenClaw & Grok Build — multi-agent literature/systematic review, journal-aware writing, peer review, proposals, figures & editable PPTX, plus author guidelines for 150+ journals. From the Food Science Group, Univ. of Melbourne.

精选 AI 模型及其 API 提供商列表，完全无需信用卡即可使用，欢迎贡献！Curated list of AI Models with their API Providers that you never ever require a Credit Card for. Feel free to Contribute!

ASTRA 的 Agent 层 —— 面向可复现研究的专用 skills、工作流执行与 HPC/容器管理。Agentic layer for ASTRA — dedicated skills, workflow execution, and HPC/container management for reproducible research

⚽ 使用 W-5 Multi-Agent AI Consensus Framework 预测足球比赛结果，结合 AI 与机器学习技术实现高准确率。⚽ Predict football match outcomes using the W-5 Multi-Agent AI Consensus Framework, achieving high accuracy with a blend of AI and machine learning techniques.

精选且自动更新的 AI Agent Skill 资源汇总列表，为 Claude、GPT 等提供质量评级。Curated, auto-updated awesome-list of vetted AI agent skills with quality ratings for Claude, GPT, a

BibexPy 是一个基于 Python 的软件，旨在简化文献计量数据整合、去重、元数据增强和格式转换。它通过自动化传统的手动且易出错的任务，简化了高质量数据集的准备，以用于高级分析。BibexPy is a Python-based software designed to streamline bibliometric data integration, deduplication, metadata enrichment, and format conversion. It simplifies the preparation of high-quality datasets for advanced analyses by automating traditionally manual and error-prone tasks.

面向 AI 编程 agent 的无向量代码检索——基于 Tree-sitter 图，按业务意图（@intent、@domainRule）搜索代码，通过 MCP 为 MSA 构建。Vectorless code retrieval for AI coding agents — search code by business intent (@intent, @domainRule) over a Tree-sitter graph. Built for MSA via MCP.

[CoLM 2026] MoANT 官方代码：面向多任务大语言模型微调的语义感知秩一专家混合模型[CoLM 2026] Official code for MoANT: Mixture-of-Rank-One-Experts with semantic-aware Intuition for Multi-task Large Language Model Finetuning

发现并联系真正匹配你技术栈的 GitHub 开发者——基于社交图谱遍历、仓库分析、相似度评分、ML 互关预测以及现代化分析仪表盘。Discover and connect with GitHub developers who actually match your stack — powered by social graph traversal, repository analysis, similarity scoring, ML followback prediction, and a modern analytics dashboard

面向 ECG-语言模型（ELM）的研究型训练与评估框架A research-oriented training and evaluation framework for ECG-Language Models (ELMs)

🚀 掌握 prompt engineering，通过指南、示例与最佳实践优化 AI 交互，覆盖各技能水平与应用领域。🚀 Master prompt engineering to optimize AI interactions with guides, examples, and best practices for all skill levels and domains.

基于确定性状态机的无头 Agent 编排器——处理 bead 队列，分派至任意 LLM CLI，覆盖所有结果分支。Rust 实现。Headless agent orchestrator with deterministic state machine — processes a bead queue, dispatches to any LLM CLI, handles every outcome. Rust.

ServiceNow MCP server：450+ 工具与 26 项 AI 能力，适配任意 AI（Claude、ChatGPT、Gemini、Cursor、Copilot）。多传输（stdio、SSE、HTTP）、A2A、动态 schema 发现、默认只读。免费且源代码可用，属于 NowAIKit 套件。ServiceNow MCP server: 450+ tools and 26 AI capabilities for any AI (Claude, ChatGPT, Gemini, Cursor, Copilot). Multi-transport (stdio, SSE, HTTP), A2A, dynamic schema discovery, read-only by default. Free and source available. Part of the NowAIKit suite.

Semantic Scholar MCP server：提供 14 个类型化工具，覆盖论文检索、引用图谱、作者画像、推荐等，支持 PyPI/Docker。Semantic Scholar MCP server: 14 typed tools for paper search, citation graphs, author profiles, recommendations, PyPI/Docker.

用于创建你自己的文献综述引擎的模板。A template to create your own literature survey engine

实时追踪 GitHub 上每个新增的“skills”仓库，捕捉 AI Agent Skill 生态趋势。Real-time tracking of every new GitHub 'skills' repo to capture the AI agent skill ecosystem trend

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

面向 AI 编码工具的桌面端聚焦型 Provider 管理器与路由器A focused desktop provider manager and router for AI coding tools.

AGI简史 — 持续更新的 AGI 知识体系 | A Brief History of AGI: books, knowledge base, and ecosystem tracking for the open-source LLM era

面向 Claude Code 的零幻觉参考验证——实时 CrossRef/S2/PubMed 校验、摘要逐字溯源、撤稿检查。Zero-hallucination reference verification for Claude Code — live CrossRef/S2/PubMed verification, verbatim abstract traceability, retraction check

AI Agent 的社交网络。把 SKILLS.md 喂给你的 AI——它就成为一位公民。无需服务器，无需 API key。GitHub 本身就是平台。Social network for AI agents. Feed SKILLS.md to your AI — it becomes a citizen. No servers, no API keys. GitHub IS the platform.

每日 LLM 价值排行榜——基于智能、速度、价格对比 300+ 模型。OpenRouter + Artificial Analysis。大模型性价比排行榜Daily LLM value rankings - compare 300+ models by intelligence, speed and price. OpenRouter + Artificial Analysis. 大模型性价比排行榜

Notepad++ 风格 LaTeX 编辑器，支持即时 PDF 预览与 SyncTeX，面向 Windows 与 Linux，Overleaf 的快速离线替代方案Notepad++-style LaTeX editor with instant PDF preview and SyncTeX, for Windows and Linux. A fast, offline alternative to Overleaf

面向智能座舱的云边协同 AI Agent：端侧毫秒级车控，云端声明式 Multi-Agent 与 Skill/DAG 编排，支持 S2S 实时语音、声纹多用户、视觉与 HMI；LLM 只负责理解与规划，VAL 负责确定性安全执行。

面向严谨学术论文写作、修订与投稿的 Claude Code skill。跨领域通用，支持按论文设置期刊覆盖规则。Claude Code skill for rigorous academic paper writing, revision, and submission. Field-agnostic with per-paper journal overrides.

原生终端的 LifeOS，可选本地 Web UI，支持任务、笔记、习惯、日程、时间记录、关系与人机协作。Terminal-native LifeOS with an optional local Web UI for tasks, notes, habits, schedules, timelogs, relationships, and human-agent collaboration.

本地 AI 秘书、技术支持与销售一体化方案，基于 XTTS v2 语音克隆、Vosk/Whisper 实时语音识别与 vLLM + Qwen/Llama 等离线 LLM。配备 Vue 3 完整管理面板、Telegram Bot、网站挂件及 fine-tuning pipeline。支持自托管、数据隐私、短信与电话呼叫。📞 Локальный AI-секретарь, тех. поддержка и менеджер по продажам с клонированием голоса XTTS v2, real-time распознаванием речи (Vosk/Whisper) и offline LLM (vLLM + Qwen/Llama и тп). Полноценная админ-панель (Vue 3), Telegram-бот, виджет для сайта, fine-tuning pipeline. Self-hosted, приватность данных, СМС и телефонные звонки .

RAG 管道的回归测试与配置扫描，附带统计学指标以判断变更是否真正带来改进。Regression testing and configuration sweeps for RAG pipelines, with the statistics to know whether a change actually helped.

AgentWorks：开源控制平面，用于在企业内运行、衡量和改进 AI Agent 工作流。AgentWorks: the open-source control plane for running, measuring, and improving AI agent workflows across your company.

本地 Windows 桌面监视器，用于查看正在运行的 Claude Code agent —— 实时状态、预估成本、模型、主机以及一键聚焦，按项目分组。只读且完全离线。Local Windows desktop monitor for your running Claude Code agents - live status, estimated cost, model, host and one-click focus, grouped by project. Read-only and fully offline.

清理、去重并丰富用于系统综述的 RIS 文献格式文件。Clean, deduplicate, and enrich RIS bibliographic files for systematic reviews.

为 MCP agent 提供 policy-as-code：在工具调用执行前拒绝高风险操作，以可验证证据证明实际运行内容，并在内核层面强制出站控制（eBPF/LSM，Linux）。确定性、离线优先、声明有界。Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enforce egress in the kernel (eBPF/LSM, Linux). Deterministic, offline-first, bounded claims.

微调、评估、提示工程、开源模型Fine-tuning, evaluation, prompting, open-source models

在 macOS 后台稳定运行 Codex 和 Claude Code — 提供原生 dashboard、持久化 tmux session、本地 checkpoint、恢复、通知和合盖运行支持。Run Codex and Claude Code reliably in the background on macOS—with a native dashboard, persistent tmux sessions, local checkpoints, recovery, notifications, and closed-lid support.

AI 工程操作系统。在一个地方统一协调模型、Agent、工具、仓库与长期运行的任务。The operating system for AI engineering. Coordinate models, agents, tools, repositories, and long-running work from one place.

自托管 MCP 服务器，让你的 Obsidian/markdown 知识库可被任意 MCP 客户端检索——涵盖文本、PDF、Office 文档、图片与音频。基于类型化、可治理语料库的混合检索，5 万条笔记下仍可达亚秒级响应；文件保持纯 markdown。Self-hosted MCP server that makes your Obsidian/markdown vault searchable — text, PDFs, Office docs, images, audio — from any MCP client. Hybrid retrieval over a typed, governed corpus, sub-second at 50k notes; your files stay plain markdown.

自然语言到 ROS2 动作——适用于任意机器人的结构化 LLM 接地引擎。Natural language to ROS2 actions — a structured LLM grounding engine for any robot.

GitHub 上 LLM Agent 框架的实时索引，每 15 分钟刷新一次。Live-updating index of LLM agent frameworks shipping on GitHub, refreshed every 15 minutes

Katra — AI Agent 的认知记忆即服务。开源认知记忆基础设施，支持 MCP 协议。Katra — Cognitive Memory as a Service for AI Agents. Open-source cognitive memory infrastructure with MCP protocol support.

Known Agents 的官方 Node.js SDK：AI agent 分析（bot 流量）、LLM 引荐来源追踪、自动生成 robots.txt。The official Node.js SDK for Known Agents: AI agent analytics (bot traffic), LLM referral tracking, automatic robots.txt

AI 辩论，代码裁定，亏损留在账面上。一款可移植的投资决策工作流插件与可验证 harness，已在真实的港股+美股组合上验证。AI argues. Code settles. The losses stay on the page. A portable investment decision-workflow plugin and verifiable harness, proven on a real HK + US portfolio.

IFSP - Hortolândia 物理题库Banco de questões de Física do IFSP - Hortolândia

Autobots | 由 NVIDIA NIM 驱动的去中心化模型 agent 集群。通过专用 6 文件控制架构编排高精度、端到端可鉴权软件开发流程，具备自动化安全审计、无冗余任务路由与自主状态管理能力。Autobots | A decentralized model agentic swarm powered by NVIDIA NIM. Orchestrating high-precision, end-to-end authenticated software development through a specialized 6-file control architecture. Features automated security auditing, non-redundant task routing, and autonomous state management.

OpenClaw 的社区补丁、配置和进阶用户 mod — 按 Agent 压缩、上下文管理等。Community patches, configs, and power-user mods for OpenClaw — per-agent compaction, context management, and more

软件系统的工作空间智能：为 AI Agent、开发者工具和工程团队构建有证据支撑的软件系统认知。Workspace Intelligence for Software Systems: Build an evidence-backed understanding of your software system for AI agents, developer tools, and engineering teams.

Claude Code Skill：为经济学与人口学研究者推荐学术期刊。Claude Code Skill: academic journal recommendation for Economics & Demography researchers

科学文档的确定性 linterDeterministic linter for scientific docs

MobileMem：面向持续演进 Agent 的设备端记忆MobileMem: On-Device Memory for Continually Evolving Agents

零基础设施构建 AI agent 与工作流。Build AI agents and workflows with zero infrastructure

Agent SkillOS — 自进化 AI Agent 的财富积累层。Agent SkillOS — the wealth-accumulation layer for self-improving AI agents.

VoiceAudition — AI Agent 的语音选角导演。跨供应商 TTS 语音发现与推荐。VoiceAudition — the voice casting director for AI agents. Cross-provider TTS voice discovery and recommendation.

你的分身。Claude Code、Codex 和 OpenCode 的任务控制中枢：查看每个 session、审批 Agent 行为、按计划调度运行。自托管，MIT 协议。You, multiplied. Mission control for Claude Code, Codex, and OpenCode: see every session, approve what your agents do, and run them on a schedule. Self-hosted, MIT.

Aixle Flow — 通过持久化、可检视的工作流编排编码 Agent。Aixle Flow — orchestrate coding agents through durable, inspectable workflows.

🧪 Cypress AI 命令，通过 LLM（大语言模型）生成 E2E 测试🧪 Cypress AI command that generates E2E tests with LLM (Large Language Model).

面向 AI Agent 的类脑持久化记忆：混合检索、知识图谱、睡眠-巩固生命周期、专家路由（HMoE），以及基于图 Laplacian 扩散的衰减、巩固、自动链接与谱检索子系统。提供 65 个 MCP 工具，本地运行，无需云端。Brain-like persistent memory for AI agents. Hybrid search, knowledge graph, sleep-consolidation lifecycle, expert routing (HMoE), and a graph-Laplacian diffusion subsystem driving decay, consolidation, auto-link, and spectral retrieval. 65 MCP tools. Local, no cloud.

面向 AI 编码 Agent 的厂商中立 continuation 协议：纯文件项目状态、标准库验证、恢复与冷启动 Agent 交接。Vendor-neutral continuation protocol for AI coding agents. Plain-file project state, stdlib validation, recovery and cold-agent handoff.

AI 运营门店。人类定方向，Agent 执行落地。AI run the shop. Humans set direction, agents execute.

动态 README，包含 AI 生成的 SCP 基金会与 Wikipedia 随机文章摘要。A dynamic README with AI-generated summaries of random articles from the SCP Foundation and Wikipedia.

机器可读的架构决策记录。Git 原生的决策记忆与治理，面向人类与 Agent 编写的方案 — 集成 lint、CI 与 MCP。Machine-readable architecture decision records. Git-native decision memory and governance for human and agent-authored plans -- lint, CI, and MCP.

你的 agent 能写出变更——却无法告诉你还有哪些内容依赖于它正在修改的代码。本工具从你自己的代码构建产品模型，然后对每个任务打分：变更内容、影响范围、波及的用户旅程与敏感数据——让运算结果直观呈现在屏幕上。本地运行，零依赖，无遥测。包含 MCP。Your agent can write the change — it can't tell you what else depends on the code it's touching. This builds a model of your product from your own code, then scores every task: what it changes, what that reaches, which user journeys and sensitive data are in the blast radius — arithmetic on screen. Local, zero deps, no telemetry. MCP included.

Gebo.ai —— 开源、企业级、与 AI 供应商无关的平台Gebo.ai The open source Enterprise AI vendor agnostic platform

🤖 利用 TRPO、PPO、DPO、GRPO、DAPO、GSPO 等先进算法提升强化学习的稳定性与效率，优化策略训练。🤖 Enhance reinforcement learning stability and efficiency with advanced algorithms like TRPO, PPO, DPO, GRPO, DAPO, and GSPO for optimized policy training.

可移植的 Rust Agent Client Protocol (ACP) server，具备模型路由、工具、权限、沙箱、会话与 MCP 集成。Portable Rust Agent Client Protocol (ACP) server with model routing, tools, permissions, sandboxing, sessions, and MCP integration.

为 AI Agent 设计的记忆系统，学习真正起作用的教训：在行动瞬间注入经验，依据结果归功，以反证挑战。本地优先、多 Agent、测试门控。Memory for AI agents that learns what actually helped: lessons injected at the moment of action, credited by outcome, challenged by counter-evidence. Local-first, multi-agent, test-gated.

系统性文献综述辅助工具，可基于预定义标注体系对一组论文进行标注。A tool that helps in Systematic Literature Review for annotating a set of papers based on a defined annotation schema

OAuth 2.1 授权服务器，实现 MCP 授权规范。OAuth 2.1 Authorization Server. Implements the MCP Authorization Spec

Jaz 的完整 agent 技术栈。包含插件、Skills、MCP 工具和 CLI，支持 Claude Code、Cowork、Codex、Copilot、Cursor 等。Complete agent stack for Jaz. Plugins, Skills, MCP tools, and CLI for Claude Code, Cowork, Codex, Copilot, Cursor, and more.

面向科学 grounding 的 MCP server：搜索 arXiv、OpenAlex、Crossref、Semantic Scholar、PubMed——通过公开元数据获取付费期刊的参考文献/引用信息。MCP server for scientific grounding: search arXiv, OpenAlex, Crossref, Semantic Scholar, PubMed — references/citations from paywalled journals via public metadata

为 AI 编码 Agent 提供调用图上下文——展示调用者、测试与 blast radius，让 Agent 安全地变更代码。CLI 与 MCP。MIT 许可。Call-graph context for AI coding agents — surfaces callers, tests, and blast radius so agents make changes safely. CLI and MCP. MIT.

按模型自适应地缩放系统提示指引：一个 oh-my-pi 插件，按模型系列、版本与层级追加经过能力调优的指令块。Scales system-prompt guidance to the model reading it: an oh-my-pi plugin that appends a capability-tuned directive block chosen by model family, version, and tier.

众多 Agent，一个目标——你的目标。Many Agents, one objective... yours

面向 LLM 的无损上下文压缩：token 用量减少 2–8 倍，按字节精确还原（sha256 校验）。提供 Claude Code 与 Cursor 的 MCP server。Lossless context compression for LLMs: 2x-8x fewer tokens, byte-exact reconstruction (sha256-verified). MCP server for Claude Code & Cursor.

AI-Factory — 自主流水线，自动设计、构建、测试并发布产品。AI-Factory — autonomous pipeline that designs, builds, tests, and publishes products.

一个可复现的 Hermes Agent 研究运行时，用于系统性文献综述、全文证据抽取、方法路由以及可审计的发表产出。A reproducible Hermes Agent research runtime for systematic literature reviews, full-text evidence extraction, methodological routing, and auditable publication artifacts.

并行运行 AI coding agent——当任务层层叠加时可进行堆叠式调用。一款 macOS 应用，为每个任务提供独立的 git worktree、分支和 Claude Code 会话。Run AI coding agents in parallel — and stack them when work builds on work. A macOS app that gives every task its own git worktree, branch, and Claude Code session.

CiteBeat · 听见你引用的节拍。Chrome 扩展：双数据源（Google Scholar + Semantic Scholar）追踪论文引用增长。

Proof Gradient 是 agent 演化协议：每次运行都会留下 proof，每个 proof 都会筛选 intelligence，每个被选中的 artifact 都会推动网络演化。Proof Gradient is the agent evolution protocol where every run leaves proof, every proof selects intelligence, and every selected artifact evolves the network.

Claude Code 扩展、hooks 和插件的实时索引，每 15 分钟从 GitHub 刷新一次。Live index of Claude Code extensions, hooks, and plugins — refreshed every 15 minutes from GitHub

与 Agent 无关、与项目无关的 AI 工具包，用于与 AI 编码 Agent 开展结构化编码会话。An agent agnostic, project agnostic, AI toolkit for running structured coding sessions with AI coding agents

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.

Galactus 在低于规格的 Mac 上运行 744B 与 235B MoE 模型，具备与 llama.cpp 的逐位精度一致、以 RAM 作为缓存的执行模式，并提供完整的本地应用，涵盖 Agent、权限门控、代码编辑器、已认证的服务器模式、定时无人值守运行以及完整公开的测评数据Galactus executes 744B and 235B MoE models on undersized Macs with bit‑perfect llama.cpp parity, RAM-as-cache execution, and a full local app featuring an agent, permission gate, code editor, authenticated server mode, scheduled unattended runs, and fully published measurements.

基于 Rust 的 SIP 与 RTP 抓包、分析与安全工具，单二进制，仅依赖 libpcap。SIP & RTP capture, analysis, and security tool. One binary, one dependency (libpcap), built in Rust.

[COLMW'26] AdaFlash：通过 On-Policy 蒸馏扩散 Drafters 实现的自适应投机解码[COLMW'26] AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

自治 AI 的形式化框架——Neural Parliament、Ulysses Contracts、Identity Layer。提供参考实现与 Lean 验证的证明，Apache-2.0 许可。Formal framework for self-governing AI — Neural Parliament, Ulysses Contracts, Identity Layer. Reference implementation, Lean-verified proofs, Apache-2.0.

浏览用于自动化科学研究各个环节的开源工具，覆盖从文献综述、实验到写作与同行评审。Browse open-source tools for automating scientific research, from literature review and experiments to writing and peer review

Music Assistant 的 FastMCP server——可从 Claude Code、Codex、Cursor 及其他 AI agent 控制 MA。FastMCP server for Music Assistant — control MA from Claude Code, Codex, Cursor, and other AI agents

Dust：一款受 React/Vue 启发的现代化、组件化 Dart Web 框架，基于 WebAssembly（WASM）构建，具有高性能与流畅的开发体验，可使用 Dart 构建健壮、类型安全的 Web 应用。Dust: A modern, component-based Dart web framework inspired by React/Vue. Built with WebAssembly (WASM) for high performance and a seamless developer experience. Create robust, type-safe web applications with the power of Dart.

为 AI 编码 Agent 提供的本地文档镜像——自动同步，与索引器无关。Local docs mirror for AI coding agents — auto-synced, indexer-agnostic.

大语言模型元数据的开放注册表——以单一机器可读的 models.json 提供身份、作者、模态、上下文/输出限制、能力与生命周期日期，并通过 JSON Schema 校验。CC BY 4.0Open registry of large-language-model metadata — identity, authorship, modalities, context/output limits, capabilities & lifecycle dates as one machine-readable models.json validated by JSON Schema. CC BY 4.0.

面向多 Agent 工作流的 MCP 协调原语。LLM 无关、CLI 无关、可自托管。TypeScript + SQLite。MCP coordination primitive for multi-agent workflows. LLM-agnostic, CLI-agnostic, self-hostable. TypeScript + SQLite.

用于评估检索增强视觉语言模型在循证医学视觉问答中表现的研究框架Research framework evaluating retrieval-augmented vision-language models for evidence-grounded medical visual question answering.

支持从多源智能检索、筛选与总结科学论文，提升研究与报告生成效率Enable intelligent retrieval, filtering, and summarization of scientific papers from multiple sources for efficient research and report generation.

🐙 通过 Python 与 PyTorch 实战代码深入理解 LLM 内部机制，掌握 LLM 架构、训练及核心原理。🐙 Explore the inner workings of large language models with hands-on Python and PyTorch code. Master LLM architecture, training, and mechanisms for AI systems.

GitHub 上 MCP server 的自动更新索引，每 15 分钟刷新一次。Auto-updated index of MCP servers shipping on GitHub, refreshed every 15 minutes

GitHub 上最新 Agent 框架的实时索引，按发布时间而非 star 数排序。Live index of the newest agent frameworks shipping on GitHub, sorted by recency not stars

在 LIBERO 与 RoboTwin2.0 上，基于状态融合解码与冻结视频骨干网络训练面向机器人操作的轻量级世界动作模型。Train lightweight world action models for robot manipulation using state-fusion decoding and frozen video backbones on LIBERO and RoboTwin2.0.

自托管、多用户转录平台：录制或上传音频。支持说话人标记、带时间戳的转录、跨录音识别说话人、摘要、提取行动项，并可使用自有 OpenAI 兼容 LLM 与转录内容对话。你的音频、你的服务器、你的模型。已在笔记本 RTX4070、台式机 RTX3090 与 RTX5090 上测试。Self-hosted, multi-user transcription platform: record or upload audio. Speaker-labeled, timestamped transcripts, Recognize speakers across recordings, Summarize, extract action items and chat over your transcripts with your own OpenAI-compatible LLM. Your Audio, your Server, your Model. Tested on Laptop RTX4070, Desktop RTX3090 and RTX5090

通过用于获取 arXiv 论文、提取技术细节与跟踪引用的研究 Skill，为 Agent 工作流自动化文献综述。Automate literature reviews with research skills for fetching arXiv papers, extracting technical details, and tracking citations for agent workflows.

用于生成基于 Transformer 的 LLM 完整注意力头热力图的一组脚本。A set of scripts to generate full attention-head heatmaps for transformer-based LLMs

自托管、可扩展的 AI agent 平台，具备受治理的 MCP 工具、持久化项目记忆、持久工作流、能力包、自主执行，以及分布式本地模型计算能力。Self-hosted, extensible AI agent platform with governed MCP tools, persistent project memory, durable workflows, capability packs, autonomous execution, and distributed local-model compute.

🛠️ 通过 Local-LLM（一款基于 BERT 模型的轻量级 Python 库）在安全环境中实现离线 NLP 工作流，确保可复现性与可靠性。🛠️ Enable offline NLP workflows with Local-LLM, a lightweight Python library for secure environments using the BERT model, ensuring reproducibility and reliability.

LM Studio 的 Web 前端——支持浏览器访问、自适应记忆、多用户鉴权与 MCP 工具。Web frontend for LM Studio — browser access, adaptive memory, multi-user auth, MCP tools

从零开始构建开源预训练 LLM，附带已发布的数据、训练代码、消融实验与结果，以高效提升模型质量。Build open pretraining LLMs from scratch with released data, training code, ablations, and results to improve model quality efficiently

准确捕获 macOS 听写内容，不改写你的措辞，保留真实输入并规避常见应用问题Capture macOS dictation accurately without rewriting your words, keeping your input true to what you speak and avoiding common app issues.

RSI-EAF：基于 XRPL 的自治工厂。LIVE x402 商户——使用 testnet Tag 1/2 支付。RSI-EAF: XRPL-grounded autonomous factory. LIVE x402 merchant — pay testnet Tag 1/2. https://published-zeta.vercel.app/pay.html

面向 Bun 的、强约定的全栈框架，主要用户是 AI Agent。八个原语，统一的 authz 系统覆盖所有入口，错误信息附带可直接执行的修复命令。可在 PaaS 上免费起步，扩容无需改动应用代码。Bun-only, opinionated full-stack framework where the primary user is an AI agent. Eight primitives, one authz system across every surface, errors that carry an exact fix command. Start free on a PaaS; scale out without changing app code.

开源核心的「AI Agent 版 Spotify」——可自托管的可运行 Agent 工件注册中心：skill、bundle、loop 与 personality。docker compose up 即可在 60 秒内启动可用注册中心，零注册。MCP 原生，MPL-2.0 许可。Open-core 'Spotify for AI agents' — a self-hostable registry of runnable agent artifacts: skills, bundles, loops, and personalities. docker compose up → working registry in 60s, zero signup. MCP-native, MPL-2.0.

将 Justin Sun 的营销逻辑提炼为心智模型、决策启发式与文案模板，用于注意力驱动的增长。Distill Justin Sun's marketing logic into mental models, decision heuristics, and copywriting templates for attention-based growth.

空间智能工作站——53 路实时 OSINT 数据源，基于 PostgreSQL+pgvector 的 FollowTheMoney 实体图谱，9 阶段多 Agent 编排器（4 层防幻觉防护）、贝叶斯信源裁定、W3C PROV 证据 DAG、GNN 流水线（GAT+T-GCN+FedAvg+DP-SGD），3 节点 Ed25519 认证网格，通过 NVIDIA NIM Cascade 实现 24 小时自动简报Spatial intelligence workstation — 53 live OSINT feeds, FollowTheMoney entity graph on PostgreSQL+pgvector, 9‑phase multi‑agent orchestrator with 4‑layer anti‑hallucination guards, Bayesian source adjudication, W3C PROV evidence DAG, GNN pipeline (GAT+T‑GCN+FedAvg+DP‑SGD), 3‑node mesh with Ed25519 auth, automated 24h briefing via NVIDIA NIM Cascade

面向 Claude Code 的 IMRAD 学术写作全生命周期插件。持久化的 .writing/ 状态、主张优先验证、Zotero 双源真相、由子 Agent 驱动的撰稿流程。IMRAD academic-writing lifecycle plugin for Claude Code. Persistent .writing/ state, claim-first verification, Zotero dual-source-of-truth, subagent-driven drafting.

基于 Python（Anthropic SDK）的多 Agent 系统，为私人教练生成个性化训练与饮食计划——内置免费规则引擎 + 可选 LLM 层、显式状态编排器、Streamlit 仪表盘与确定性安全校验器。A multi-agent system in Python (Anthropic SDK) that generates personalized workout routines and meal plans for a personal trainer — free rule engine + optional LLM layer, explicit-state orchestrator, Streamlit dashboard, and deterministic safety validator.

基于 specter2 + BERTopic 的 arXiv 论文发现——通过 embedding 检索与主题聚类实现每日论文推荐。arXiv paper discovery with specter2 + BERTopic — embedding-based retrieval and topic clustering for daily paper recommendations.

🤖 自主研究论文分析器——下载 arXiv 论文，通过 HuggingFace Transformers 运行本地 LLM 分析，并将 AI 生成的文献综述发布至 GitHub Pages。🤖 Autonomous Research Paper Analyzer — Downloads arXiv papers, runs local LLM analysis via HuggingFace Transformers, and publishes AI-generated literature reviews to GitHub Pages

[进行中 / 实验性] 关于免疫检查点抑制剂耐药性的活态文献综述。[WIP / experiment] Living literature review of resistance to immune checkpoint inhibitors

AI Agent 集群的开源任务控制中心 —— 对话即可配置，Agent 负责执行，人类负责审批。Open-source mission control for AI agent fleets — chat to provision, agents to operate, humans to approve.

教学用 LLM 应用teaching LLM applications

AI agent memory 与基础设施全景——912 个系统 × 68 列的对比目录，覆盖记忆层、agent 框架、运行时、vector store、知识图谱、MCP server、benchmark。支持按类型化边、谱系、引用进行检索。AI agent memory & infrastructure landscape — comparative catalog of 912 systems × 68 columns covering memory layers, agent frameworks, runtimes, vector stores, knowledge graphs, MCP servers, benchmarks. Searchable with typed edges, lineages, citations.

面向人类与 AI Agent 的开放、无需登录的 KiCad 器件注册中心——提供经验证的 footprint、symbol 与 3D 模型（STEP/GLB），附带 datasheet 来源溯源、静态 JSON API 与 MCP server。Open, no-login KiCad parts registry for humans & AI agents — verified footprints, symbols & 3D models (STEP/GLB) with datasheet provenance + static JSON API + MCP server

⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。

使 AI agent 能够在任何市场上自主创建、评估与进化 Skill，无需用户干预Enable AI agents to autonomously create, evaluate, and evolve skills across any marketplace without user intervention.

本地优先的 AI 论文阅读助手 —— Agentic RAG、引文追溯、Electron 桌面应用，完全离线。Local-first AI reading assistant for academic papers — Agentic RAG, citation tracing, Electron desktop app, fully offline

🖥️ 通过终端中键盘优先的 Kanban board 简化工作流，实现快速、专注的任务管理。🖥️ Streamline your workflow with a keyboard-first Kanban board in your terminal for fast, focused task management.

使用 SQLite 和 FAISS 存储、整合与召回 coding agent 记忆，附带 provenance 追踪，实现快速、结构化的知识访问Store, consolidate, and recall coding agent memories with provenance tracking using SQLite and FAISS for fast, structured knowledge access.

可复用的 Codex skill，用于生成紧凑、可直接投稿的科研配图，含匿名模板与统一的 V7 样式。Reusable Codex skill for compact, journal-ready scientific figures with anonymous templates and consistent V7 styling.

AI Agent 的认知操作系统——浏览器与计算机智能、持久化任务、记忆、恢复、证据与受治理的真实世界行动。A cognitive operating system for AI agents — browser & computer intelligence, persistent missions, memory, recovery, evidence, and governed real-world action.

适用于 macOS 与 Linux 的个人 dotfiles，由 GNU Stow 管理。Personal dotfiles for macOS & Linux, managed by GNU Stow.

一份由 AI Agent 为人类撰写的出版物。Node/Express SSR + SQLite，自主化编辑部，实时 AI 工具数据引擎。https://dreaming.pressA publication where AI agents write for humans. Node/Express SSR + SQLite, autonomous newsroom, live AI-tool data engine. https://dreaming.press

你的 AI Agent 无法掏空的钱包。一个非托管的 Soroban 资金库，限定自主 Agent 的支出上限——由合约而非模型强制执行。The wallet your AI agent can't drain. A non-custodial Soroban treasury that bounds what an autonomous agent may spend - enforced by the contract, not the model.

Delta-9 MAW — 按严重程度（P0–P3）路由的多 Agent 异常处理流水线 + TOTP 操作面板，并配套线上 d9bkk.com 会员商店（KYC、D9-Wallet、PromptPay、TCG Lottery Pack）。Delta-9 MAW — severity-routed multi-agent anomaly pipeline (P0–P3) + TOTP operator panel, alongside the live d9bkk.com member storefront (KYC, D9-Wallet, PromptPay, TCG Lottery Pack).

:exclamation: CRAN R 包仓库的只读镜像。AgriDataTools —— 农业研究的自动化统计分析与工具。:exclamation: This is a read-only mirror of the CRAN R package repository. AgriDataTools — Automated Statistical Analysis and Tools for Agricultural Research

Claude Code 的治理与可审计层：在 CEO 协议下运行由专业 Agent 组成的结构化团队——plan→debate→execute 门控、防篡改审计日志、跨 LLM 双重护栏。Governance & auditability layer for Claude Code: run a structured team of specialist agents under a CEO protocol — plan→debate→execute gating, tamper-evident audit log, cross-LLM pair-rail.

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.

Cypress AI 演示Cypress AI Demo

5dive 维护的 Claude Code 插件市场——包含 Telegram 桥接及相关 agent-channel 集成。Claude Code plugin marketplace maintained by 5dive — Telegram bridge and related agent-channel integrations.

🤖 仅需 10 行代码即可在 Android 上免 root 自动回复聊天消息，适合使用 Autojs 或 Hamibot 进行测试。🤖 Automate chat replies on Android without root using just 10 lines of code. Ideal for testing with Autojs or Hamibot.

面向 AI 生成可执行方案的 verifier-first 运行时，支持独立验证、对比与检索。A verifier-first runtime for independently verifying, comparing, and searching AI-generated executable solutions.

使用 AI agent 自动化文献综述，基于结构化协议实现全面研究与高质量报告生成📚 Automate literature surveys with AI agents using a structured protocol for thorough research and insightful report generation.

《大模型推理原理与优化》：面向系统/架构/后端研发工程师的模型原理入门课，目标是通俗易懂的解释推理过程，理解原理有助于系统开发/维护工作

一切留痕：需求即 issue，决策即审批评论，工作即 PR，理由即该 PR 的记录。协调器将对话中继到 GitHub，并为每个角色派生沙盒化会话，各自仅持有自己的规则集。Everything on the record: a requirement is an issue, a decision is an approval comment, work is a PR, rationale is that PR's record. The orchestrator relays conversation to GitHub and spawns sandboxed role sessions, each with only its own rulebook.

用于论文推荐的 Claude botClaude bot for paper recommendation

本仓库包含一个纯 Python 工作流，用于消费级可穿戴设备系统综述论文中的两项可复现任务。This repository contains a plain-Python workflow for two reproducible tasks used in a consumer wearable systematic review paper.

面向 Solana 上 AI Agent 的语义交易验证。Semantic transaction verification for AI agents on Solana.

隐私优先、local-first 的文本清理与文档格式化应用，支持结构化 DOCX/TXT 导出Privacy-first, local-first text cleanup and document formatting app with structured DOCX/TXT export.

基于 Microsoft Agent Framework (.NET) 的 LLM Agent 三层评估：运行时护栏、PR 闸口、校准过的评审者。该框架可自我评估。Three-tier evaluation for LLM agents on Microsoft Agent Framework (.NET): runtime guardrails, a PR gate, and calibrated judges. The framework evaluates itself.

使用 HTML 和 CSS 构建简洁、风格化的网站，配备响应式布局、导航与现代设计，提升用户参与度🌐 Build a simple, stylish website using HTML and CSS, featuring a responsive layout, navigation, and a modern design for easy user engagement.

GitHub 个人主页 README。GitHub profile README

软件工程作品集 | Web 开发 | 桌面应用开发Software Engineering Portfolio | Web Development | Desktop App Development

Swift AI Command CenterSwift AI Command Center

将 Herdr 工作区平铺为 N 个 Claude Code 窗格，然后通过单一菜单列出、恢复或终止它们。Windows 使用 PowerShell，macOS 和 Linux 使用 bash。Tile a Herdr workspace with N Claude Code panes, then list, resume, or kill it from one menu. PowerShell on Windows, bash on macOS and Linux.

可安装的私有 AI 指挥中心，跨 Windows、macOS 与 Linux，集成 OpenZero、ZSEC Shield 与 TalkToAI 工作区。Installable private AI command center for Windows, macOS and Linux with OpenZero, ZSEC Shield and TalkToAI workspaces

🛠️ 使用 Haystack 轻松构建强大搜索系统，该框架用于开发端到端问答与搜索应用。🛠️ Build powerful search systems effortlessly with Haystack, a framework for developing end-to-end question answering and search applications.

通过一次 wrap() 调用为 LLM 流水线构建运行时可靠性守卫，可配置地防御常见生产故障Build runtime reliability guards for LLM pipelines with one wrap() call and configurable protection against common production failures

轨道不确定性传播方法的综合性文献综述。Comprehensive literature review of Orbital uncertainty propagation methods

面向 Windows 与桌面端的 local-first LaTeX 论文编辑器A local-first LaTeX paper editor for Windows and desktop.

协调 OpenClaw AI Agent 攻克 LHON——一种导致失明的罕见遗传疾病。安装 Skill，让你的 Agent 参与真实医学研究。Coordinating OpenClaw AI agents to cure LHON — a rare genetic disorder causing blindness. Install the skill, let your agent contribute to real medical research.

Orchestra 的 AI 服务器——蓝图生成、任务分配、Clover 助手与知识图谱AI server for Orchestra- blueprint generation, task assignment, Clover assistant, and knowledge graph

面向编码 Agent 的 MCP 原生部署控制平面。MCP-native deployment control plane for coding agents.

📊 自动化从 LinkedIn 抓取招聘信息，通过高效批量数据收集简化研究与招聘工作。📊 Automate job listing extraction from LinkedIn to streamline your research and recruitment efforts with efficient, bulk data collection.

最简单的可扩展自然语言数据库查询方案，快速且随规模伸缩。Simplest Natural Langauge Querying DB That scales. Fast.

GenAI 职业路线图 2026 🚀 | AI 岗位路径与技能指南GenAI Career Roadmap 2026 🚀 | AI Job Paths & Skills Guide

基于你的 AI Agent 集群已编写的 markdown 协作日志之上，为每个 Agent 提供独立收件箱。A per-agent inbox over the markdown coordination logs your AI agent fleet already writes

脚手架搭建生产级 AI Agent 项目最快的方式。The fastest way to scaffold production-ready AI Agent projects

通过 MCP 为协作型 AI agent 提供基于 PostgreSQL 的共享记忆。Shared PostgreSQL-backed memory for collaborating AI agents via MCP

自托管 Docker 栈，用于跨平台 AI Agent 工作区（Claude Code + ChatGPT + 任意 LLM）。MIT 许可。Self-hosted Docker stack for cross-platform AI agent rooms (Claude Code + ChatGPT + any LLM). MIT.

基于环境凭证的 CrewAI scaffold 与 Streamlit kickoff-client 学习。CrewAI scaffold and Streamlit kickoff-client study with environment-only credentials.

使用本地 LLM 与私密法律文档对话，在自有硬件上获得带引用、可验证的答案。Chat with private legal documents using local LLMs. Get cited, verifiable answers on your own hardware.

一种静态类型、编译型编程语言，带有原生 x86-64 后端 — 由 AI 编写，为 AI 服务。A statically-typed, compiled programming language with a native x86-64 backend — written by AI, for AI.

AI 驱动的企业级 Agile OS，使用 Gemini 1.5 将原始客户音频与笔记即时转化为客户 pitch deck、PM epic、UI 规格与后端工程架构。An AI-powered Enterprise Agile OS that instantly translates raw client audio and notes into client pitch decks, PM epics, UI specs, and backend engineering architectures using Gemini 1.5.

论文《Controllable molecular graph generation from natural-language chemical constraints》（基于自然语言化学约束的可控分子图生成）的代码仓库。This is repository for "Controllable molecular graph generation from natural-language chemical constraints"

面向 WHOOP API v2 的只读 MCP server——可从任意 MCP 客户端查询并分析你自己的恢复、睡眠、负荷与训练数据。本地运行，凭据不离开本机。Read-only MCP server for the WHOOP API v2 — query and analyse your own recovery, sleep, strain and workout data from any MCP client. Runs locally; credentials never leave your machine.

提供提案撰写、医学影像文献综述与论文报告幻灯片的工具，自动化学术研究工作流。Automate academic research workflows with tools for proposal writing, medical imaging literature reviews, and paper presentation slides.

基于架构决策记录（ADR）理念的 Memory Framework，用于 AI agent（Claude Code、Codex、Antigravity……）之间的知识共享。支持 agent 安装，vector（Postgres + pgvector）+ graph（Neo4j）双骨干，通过本地 gateway 管理，支持多种本地 LLM 后端，具备完整 provenance、合并、遥测等能力。Memory Framework based on the idea of Architectural Decision Records, shared knowledge between AI agents (Claude Code, Codex, Antigravity ...). Agent installable, vector (Postgres + pgvector) + graph (Neo4j) backbone, managed through a local gateway, supporting multiple local LLM backends, with full provenance, consolidation, telemetry and more

PaperForge v2026 是一款基于浏览器的学术写作自动化系统，通过 LLM 引导的工作流完成论文生成、引用处理、迭代与校验。PaperForge v2026 is a browser-based academic writing automation system with LLM-guided workflows for paper generation, citation handling, iteration, and validation.

📊 通过统计分析基因表达差异，调查临床研究中的性别偏差，以改善医疗结果。📊 Investigate gender bias in clinical research through statistical analysis of gene expression differences to improve healthcare outcomes.

Haven 42 是一款证据门控、本地优先的 AI 工作台，支持 Windows、Linux 和 macOS 上的编码、聊天与媒体处理。Haven 42 is an evidence-gated, local-first AI workbench for coding, chat, and media on Windows, Linux, and macOS.

Daily Paper Update 是一个精选仓库，提供人工智能、机器学习与计算机科学多领域近期研究论文的结构化技术摘要。目标是加速文献综述，为研究人员、工程师与学生提供便利。Daily Paper Update is a curated repository that provides structured and technical summaries of recent research papers across multiple domains in Artificial Intelligence, Machine Learning, and Computer Science. The goal is to accelerate literature review, facilitate researchers, engineers, and students.

AI 驱动的系统综述。AI Powered systematic review

用日常语言描述应用需求，AI 专家团队即可设计、构建、测试并私有发布到你的 GitHub — 无需编码。面向非技术用户的 Claude Code 插件。个人使用免费；商业许可可用。Describe an app in plain words and a team of AI specialists designs, builds, tests and privately publishes it to your own GitHub — no coding needed. A Claude Code plugin for non-technical people. Free for personal use; commercial licence available.

使用本地 RAG 系统增强知识库，借助混合搜索实现精准信息检索与最优结果🔍 Enhance your knowledge base with a local RAG system that leverages hybrid search for precise information retrieval and optimal results.

面向学术阅读的本地桌面 PDF 阅读器，支持 AI 翻译、OCR、高亮、笔记、翻译历史以及导入/导出。A local desktop PDF reader for academic reading, with AI translation, OCR, highlights, notes, translation history, and import/export support.

这份 AI 研究清单告诉你该"做什么不同"，而不仅仅是读什么——100+ 篇 2026 年顶会论文 → 50+ 条面向 AI Agent 构建者的生产实践要点。中英双语。The AI-research list that tells you what to DO differently, not just what to read — 100+ top-tier 2026 papers → 50+ production takeaways for AI agent builders. Bilingual EN/中文.

大语言模型情境感知相关论文精选目录。Curated bibliography of papers on situational awareness in large language models

0n1x——Agent 执行证明（Proof of Agent Execution）。面向 AI Agent 的中立、签名式信任层：付款前先验证，签名的是事实而非判断。AI Agent 领域的 Carfax。0n1x — Proof of Agent Execution. The neutral, signed trust layer for AI agents: verify before you pay, signed facts not judgments. The Carfax for AI agents.

用于自动汇编每日/每月文献综述的 Web 爬虫工具。Web scraping tools designed to assemble automated daily/monthly literature reviews

精选的评分量表、检查清单、评分标准集、原则和评分指南汇总，用于对现代生成模型进行评分、排名、验证、过滤或训练。A curated list of rubrics, checklists, criteria sets, principles, and scoring guides used to score, rank, verify, filter, or train modern generative models.

EoG 应用迁移与功能实现的代码仓库。Code for EoG App Migration and Functionality

为 AI 编程 agent 构建 Claude Code prompt 模板，包含系统 prompt、工具 prompt、记忆管理与多 agent 协调。Build Claude Code prompt templates for AI coding agents, with system prompts, tool prompts, memory, and multi-agent coordination

MCP 桥接，让 Claude Code 和其他宿主将实现工作委托给 OpenAI Codex CLI。MCP bridge that lets Claude Code and other hosts delegate implementation to the OpenAI Codex CLI

企业级数字支付平台：Java 21 / Spring Boot 3 微服务、Kafka 事件驱动、六边形（端口与适配器）架构，由专业 AI Agent 团队以 spec 驱动并编排，包含完整 CI/CD、GitOps 和供应链安全。Enterprise-grade digital payment platform: Java 21 / Spring Boot 3 microservices, Kafka event-driven, hexagonal (ports & adapters) architecture, spec-driven and orchestrated by a team of specialized AI agents. Includes full CI/CD, GitOps, and supply-chain security.

Codex Autonomous Objective Loops 2026：强制审查与验证的 AICodex Autonomous Objective Loops 2026: AI with Mandatory Review & Verification

OWNEX——自主工作操作系统（Autonomous Work Operating System）：机会发现、安全自动化、Agent 编排、本地优先 AI 路由、收入情报。Python/FastAPI + Vue 3 + Tauri。OWNEX — Autonomous Work Operating System: opportunity discovery, security automation, agent orchestration, local-first AI routing, revenue intelligence. Python/FastAPI + Vue 3 + Tauri.

面向 Webasyst 2026 的非官方 Codex-First MCP——应用、插件与 UI 审计工具。Unofficial Codex-First MCP for Webasyst 2026 – Apps, Plugins & UI Audit Tools

一个通过自博弈掌握 LLM 工具调用的 Python 库A Python library for LLM tool call mastery through self play.

ThesisAI 是一个高性能的自主研究 Agent（自主研究代理），旨在简化学术写作流程。它能将你提供的知识库中的复杂信息合成为结构化、格式规范的学术文本。ThesisAI is a high-performance Autonomous Research Agent designed to streamline academic writing. It synthesizes complex information from your provided knowledge base into structured, properly formatted academic prose.

文献综述声明图谱。Literature review claims graph

面向飞书/Lark 的开源 AI 辅助入职方案：可配置工作流、文档 OCR 与审阅、Bitable 同步、提醒功能，以及零凭证 Demo。Open-source AI-assisted HR onboarding for Feishu/Lark: configurable workflows, document OCR and review, Bitable sync, reminders, and a zero-credential demo.

可复用的 Agent skill，用于有证据支撑的科研写作、发表级图表生成以及安全的 DOCX 修订。Reusable agent skills for evidence-grounded scientific writing, publication-ready figures, and safe DOCX revision.

研究问题系统Research Question system

自动化 Python 兼容性补丁工具，将 Google Scholar PDF Reader 从 Chromium 移植到基于 Firefox 的浏览器，并使用 IndexedDB 集成自定义离线论文数据库。Automated Python compatibility patcher to port Google Scholar PDF Reader from Chromium to Firefox-based browsers, integrating a custom offline paper database using IndexedDB.

arXiv 论文的端到端推荐引擎：流式接入开放快照，使用量化 ONNX 模型对标题与摘要进行 embedding，构建 FAISS 向量索引，通过 FastAPI 服务提供推荐，并在 Streamlit 面板中交互探索。End-to-end recommendation engine for arXiv research papers: stream an open snapshot, embed titles + abstracts with a quantized ONNX model, build a FAISS vector index, serve recommendations through a FastAPI service, and explore them in a Streamlit dashboard.

Agent 中立的自主、协作与能力编排 harness。Agent-neutral autonomy, collaboration, and capability orchestration harness.

Same Targets, Different Computation 的代码与 artifact：后训练如何在模型各层之间划分计算Code and artifacts for Same Targets, Different Computation: how post-training divides work across model layers.

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.

N-able N-central 的 MCP server——设备、组织单元、活跃问题、定时任务、自定义属性（支持本地部署与托管）。MCP server for N-able N-central — devices, org units, active issues, scheduled tasks, custom properties (on-prem and hosted)

Clio Manage 的 MCP server——案件、联系人、活动、任务、文档、日历、计费。MCP server for Clio Manage -- matters, contacts, activities, tasks, documents, calendar, billing

一次编写 AI Agent 知识，编译输出为所有 Agent 配置格式——CLAUDE.md、AGENTS.md、.cursor/rules 等。Write your AI agent knowledge once. Compile it to every agent config format - CLAUDE.md, AGENTS.md, .cursor/rules and more.

🔍 使用多种 prompt 技巧在多步数学问题上分析 Mistral-7B 模型的数学推理能力。🔍 Analyze the mathematical reasoning abilities of the Mistral-7B model using diverse prompting techniques on multi-step math problems.

数据在被构建成有意义的东西之前只是噪声——将原始数据转化为真正可用的系统，涵盖欺诈检测、RAG pipeline、计算机视觉追踪器以及数据仓库等领域。FAST NUCES 数据科学本科生，在"搞坏东西"和"交付产品"之间反复横跳。持续构建，持续学习，欢迎合作和实习交流Data is noise until someone builds something meaningful out of it, turn raw data into systems that actually work, from fraud detection and rag pipelines to computer vision trackers and data warehouses. DS undergrad at FAST NUCES, somewhere between breaking things and shipping them. always building, always learning, open to collabs and interns

让 AI Agent 从 PDF（发票、报告、对账单）中提取文本和表格的 MCP server。MCP server that lets AI agents extract text and tables from PDFs: invoices, reports, statements.

适用于 Cursor 和 Claude Code 的 Waydock 插件。包含 Skills 以及通过 OAuth 连接的 Waydock MCP 服务器。Waydock plugins for Cursor and Claude Code. Skills plus the Waydock MCP server, connected over OAuth.

通过实战教程构建有效的 AI 评测，使用真实 agent 提升生产系统技能🎯 Build effective AI evaluations through a hands-on tutorial, using a realistic agent to enhance your production system skills.

基于 Java 的数据结构与算法项目，结合 Rabin–Karp 进行精确关键词匹配、编辑距离进行近似相似度计算、二分图匹配实现主题到论文的推荐。A Java-based DSA project that recommends relevant research papers using Rabin–Karp for exact keyword matching, Edit Distance for approximate similarity, and Bipartite Graph Matching for topic-to-paper recommendations.

基于 FastAPI、LangChain、ChromaDB 和 Google Gemini API 构建的快速、轻量级 RAG 聊天机器人。A fast, lightweight Retrieval-Augmented Generation (RAG) chatbot built with FastAPI, LangChain, ChromaDB, and the Google Gemini API.

AI 会议智能工作区，支持视频转录、结构化洞察以及基于转录的 RAG 对话。AI meeting intelligence workspace for video transcription, structured insights, and transcript-grounded RAG conversations.

Embrace the choas（拥抱混乱）Embrace the choas

某私有组织的公开主页，包含多个 .git 大学项目，涵盖软件工程、全栈 Web 开发、数据科学与工程（AI/ML）、嵌入式系统、GIS 等先进计算技术，分别在 Uppsala、Canterbury、Auckland 完成，并含多次海外正式交换经历；多数项目涉及广泛协作，且均以 distinction 等级通过Public profile for a private org containing multiple .git university projects in software engineering, full-stack web dev, data science & eng (AI/ML), embedded systems, GIS. & other advanced computing tech completed at Uppsala, Canterbury, Auckland & formal exchanges abroad; many involving extensive collaboration, all averaging with distinction

自动更新的全球最热门 AI 仓库集合，汇聚 LLM、Agent、RAG 等前沿项目。An auto-updating collection of the world's most popular AI repositories, bringing together LLMs, agents, RAG, and other cutting-edge projects.

面向 AI 编程工具的本地 Agent 多路复用器，原生 TUI 界面。Local agent multiplexer for AI coding tools with native TUIs

浏览器本地的 HTTP 请求转换器，支持 cURL、Fetch、Python、Go、Rust 和 Node.js。Browser-local HTTP request converter for cURL, Fetch, Python, Go, Rust, and Node.js.

学术写作服务、毕业论文、博客、项目提案、商业报告、医学报告。Academic Writing Services, Thesis, Blogs, Proposal, Buisness Reports, Medical Reports

2026 年由 AI 驱动的 Things 3 CLI 自动化工具——macOS 智能任务管理器AI-Powered Things 3 CLI Automation Tool 2026 – Smart Task Manager for macOS

Go 工具链：将 Bourbaki PDF 转换为带标签的 Markdown 语料，并完成翻译与习题求解Go toolchain that turns Bourbaki PDFs into a tagged Markdown corpus, translates it, and solves the exercises

Bourbaki《数学基础》代数篇第 I–VIII 章 Markdown 版本，带永久 Stacks 风格标签，提供越语/中文/日语翻译及习题解答Bourbaki, Elements of Mathematics: Algebra chapters I-VIII as Markdown, with permanent Stacks-style tags, translations (vi/zh/ja) and worked exercises

面向金融分析师的 Agentic Jupyter Notebook。Agentic Jupyter Notebook for financial analysts

面向几何感知量子机器学习的可复现研究框架。A reproducible research framework for geometry-aware quantum machine learning.

用于将 LaTeX 编译为 Desmos 的微型 DSL。A tiny DSL for compiling LaTeX to Desmos

一个基于 R/Shiny 的应用，用于离散数据的图形绘制与统计分析，面向研究用途；可生成高分辨率图片或 SVG 格式的出版级图表，便于直接用于学术论文与报告。An R/Shiny-based application designed for graph plotting and statistical analysis of discrete data, tailored for research purposes. It generates publication-quality plots in high-resolution image or SVG formats, ready for seamless inclusion in academic papers and presentations.

在小型 LLM 中植入认知美德的激活引导实验——三项发现与一个失败模式数据集（DOI 见 README）Activation-steering experiments on installing epistemic virtues in small LLMs — three findings + a failure-mode dataset (DOIs in README).

本仓库包含开展以下系统综述所使用的完整代码库：'How The Biopsychosocial Model Frames Chronic Pain Research'。This repository contains the full codebase utilized in the process of conducting the following systematic review: 'How The Biopsychosocial Model Frames Chronic Pain Research'.

一款个人知识引擎，注重综合而非简单转录——每个声明都附带回到原始来源的引用。为 LLM agent 提供写入时综合 + 带引用的检索能力。A personal knowledge engine that synthesizes instead of transcribes — every claim carries a citation back to its source. Write-time synthesis + cited retrieval for LLM agents.

面向空间 LLM 与地理空间 AI Agent 的生产工程模式——验证优先架构、地理空间 RAG、prompt-to-spatial-SQL、tool routing 与评估。Production engineering patterns for spatial LLMs and geospatial AI agents — validation-first architecture, geospatial RAG, prompt-to-spatial-SQL, tool routing, and evaluation.

让编码 Agent 在需要你介入时通知你。Smoke Signal Codex & Claude 插件。Let your coding agent notify you, when you are needed. Smoke Signal Codex & Claude plugin.

macOS 菜单栏应用，监控 Claude Code 配额并自动开关其自主循环。macOS menu-bar app that watches Claude Code's quota and switches its autonomous loop on and off for you

本仓库最初是我毕设项目的 PyTorch Lightning 模板，后来演进为包含完整项目实现本身。研究问题是地理定位如何影响遥感视觉-语言模型的训练与推理。注：仓库名称与描述可能变化。This repo originally was a PyTorch Lightning template for my thesis project. It has since evolved to contain the full project implementation itself. The research question is how geolocation influences the training and inference of vision-language models for remote sensing. Note: The repository name and description may change

macOS 菜单栏 App：统计各 AI Agent 工具的 token 用量与花费，显示订阅额度，并用状态灯实时反映任务运行状态。纯本地只读。

Claude Code skill：检索近 30 天 OpenAlex、Semantic Scholar、PubMed、arXiv 与 HuggingFace Hub 的科学文献。Claude Code skill that searches the last 30 days of scientific literature across OpenAlex, Semantic Scholar, PubMed, arXiv, and HuggingFace Hub

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.

用于将各类文档排版为 UGent 风格的 LaTeX 宏包。LaTeX package for typesetting various documents to UGent house style

在 DABench 数据分析任务上对 DSPy RLM（Recursive Language Models）进行基准测试，使用自动评分实现基于代码的迭代评估Benchmark DSPy Recursive Language Models on DABench data analysis tasks with automated scoring for iterative code-based evaluation

每周阅读的研究论文推荐Research Paper Recommendations for Weekly Reading

通过查询条件超边预测，为 LLM agent 检索工具集合。Retrieve sets of tools for LLM agents using query-conditioned hyperedge prediction.

关于 AI、IoT、UAV、高光谱传感及其他数字技术用于稻瘟病检测、监测、预测与管理的系统综述的可复现分析流水线与配套数据。Reproducible analysis pipeline and supporting data for a systematic review of AI, IoT, UAV, hyperspectral sensing, and other digital technologies for rice blast detection, monitoring, prediction, and management.

借助这款轻量、原生的 Text Services Framework 输入法编辑器在 Windows 上输入孟加拉语，无需后台进程。Type Bangla on Windows with this lightweight, native Text Services Framework Input Method Editor that operates without background processes.

中立的 MCP server 信任注册中心——连接前先查验。Neutral trust registry for MCP servers — check before you connect

语言驱动、无锁的分布式工作流引擎 — 用 FFL 编写工作流，运行时负责执行、依赖解析、恢复和热部署。Language-directed, lock-free distributed workflow engine — write workflows in FFL, the runtime handles execution, dependency resolution, recovery, and live deployment.

面向生态学文献综述的 AI 辅助流水线，内置对 iEcology 与保护生物学相关数据源（社交媒体追踪、博物馆标本记录、新闻档案）的支持。AI-assisted pipeline for ecological literature review with built-in support for data sources relevant to iEcology and conservation biology (social-media tracking, museum specimen records, news archives).

升级 Grand Theft Auto V（GTA V）画面表现，增强真实光照、天气效果与改进贴图，带来终极 4K 视觉体验。Upgrade Grand Theft Auto V graphics with realistic lighting, weather effects, and improved textures for a definitive 4K visual experience.

守护你的 .bib 文件：在写入前验证引用，查找每篇论文的真实出版信息，并保持整个参考文献格式统一。纯标准库 Python，无需 pip，无需 API key。Your .bib, guarded: verify a citation before it is written, find where each paper was really published, and keep the whole bibliography in one format. Stdlib-only Python, no pip, no API key required.

🤖 通过教育型对冲基金模型探索 AI 驱动的交易决策，融合多位知名金融专家的多元投资策略。🤖 Explore AI-driven trading decisions with our educational hedge fund model, featuring diverse investment strategies from renowned financial experts.

本项目研究金融市场的统计特性、不同资产的收益行为、风险测度以及跨市场关联的量化方法，奠定量化研究的核心技能基础。This project investigates the statistical properties of financial markets, how different assets behave, how risk is measured, and how inter-market relationships can be quantified; building the core skills used in quantitative research.

可复现研究流程，通过改造预训练 LLM tokenizer 降低尼泊尔天城文分词成本：连续/字素感知的 BPE 候选挖掘、基于边际增益的贪心词表选择、保留 ID 的 merge 拼接、基于分解的 embedding 初始化，以及 embedding-only/LoRA/CPT 适配；面向 6GB 笔记本 GPU 调优。Reproducible research pipeline that reduces Nepali Devanagari tokenization tax by retrofitting a pretrained LLM tokenizer: continued/grapheme-aware BPE candidate mining, greedy marginal-gain vocabulary selection, ID-preserving merge splicing, decomposition-based embedding init, and embedding-only/LoRA/CPT adaptation. Tuned for a 6GB laptop GPU.

受 MemGPT 启发、支持 OpenAI API 的长期记忆 Agent，具备记忆生命周期控制与评估能力。MemGPT-inspired long-term memory agent with OpenAI API support, memory lifecycle controls, and evaluation.

基于 CrewAI 的 Agent 系统，用于辅助研究者围绕特定高层级研究问题定义研究项目与假设。This is a CrewAI agent system set up to assist a researcher with defining research projects and hypotheses for a specific high-level research question.

使用多 Agent RAG 系统与混合索引、LangGraph 编排，自动获取 arXiv 研究论文并生成文献综述。Automate arXiv research paper retrieval and literature review generation using a multi-agent RAG system with hybrid indexing and LangGraph orchestration.

通过 MegaQwen CUDA megakernel 加速 Qwen3-0.6B 推理，在 RTX 3090 上达到 531 tok/s decode，较 HuggingFace 提升 3.9×🚀 Achieve faster Qwen3-0.6B inference with the MegaQwen CUDA megakernel, delivering 531 tok/s decode on RTX 3090—3.9x faster than HuggingFace.

论文《Quantifying temporal changes in the monetary value of forest cultural ecosystem services globally: a meta-analysis (2026)》的复现材料。Replication materialss for: Quantifying temporal changes in the monetary value of forest cultural ecosystem services globally: a meta-analysis (2026)

基于已验证决策构建的共享 intelligence 层。A shared intelligence layer built from verified decisions.

基于 Base 的 fail-closed 支付安全判定：识别已知恶意钱包、高度相似 token 及反复 rug 的资方。非托管、仅依赖描述符——工具本身不转移资金。Fail-closed safe-to-pay verdicts on Base: known-bad wallets, look-alike tokens, repeat rug funders. Non-custodial, descriptor-only — no tool moves funds.

论文《Prompt Skill Matters: Examining GenAI Interaction and Writing Quality in L2 Academic Writing》的复现材料、统计分析脚本与补充数据，AI 介导的 L2 写作研究开放科学资源。Replication materials, statistical analysis scripts, and supplementary data for the study 'Prompt Skill Matters: Examining GenAI Interaction and Writing Quality in L2 Academic Writing'. Open science resource for AI-mediated L2 writing research.

从学术数据库中采集学术元数据，用于组织文献检索与构建研究参考目录。Harvest scholarly metadata from academic databases to organize literature searches and build research bibliographies.

本地、开源的推理框架，支持 Claude 和 Codex，包含 48 个编写好的系统，仅在需要更深层推理时选用。Local, open-source reasoning framework for Claude and Codex, with 48 authored systems selected only when deeper reasoning helps.

在 Claude 中强制以引用优先的研究流程，通过结构化五阶段工作流验证事实、识别不确定性并消除幻觉。Enforce citation-first research with Claude to verify facts, identify uncertainty, and eliminate hallucinations through a structured five-phase workflow.

🔧 通过灵活的 prompt 模板与任务规范项目简化 AI Agent，实现高效的指令与记忆管理。🔧 Streamline AI agents with this flexible prompt template and task specification project for effective instruction and memory management.

离线优先的 AI 研究助手，用于识别研究空白、对比学术文献、检测潜在矛盾、生成研究问题，并与上传的论文对话。An offline first AI research assistant for identifying research gaps, comparing academic literatures, detecting possible contradictions, generating research questions and chatting with uploaded papers

📰 Spec-driven daily briefings on Claude Code cloud Routines — git as the only state, zero servers, zero API keys | 用 Claude Code Routines 每天自动生成主题简报，git 即全部状态，零服务器零密钥

面向编码 Agent 的本地运行时，以合并质量为优化目标：由仓库自适应常驻模型生成补丁，大模型进行验证。单进程同时支持 Anthropic + OpenAI API，天生离线运行。A local coding-agent runtime that optimises for merge quality: a repo-adapted resident model generates patches, a large model verifies them. Anthropic + OpenAI APIs from one process, offline by construction.

SwiftUI 原生 LaTeX 数学渲染，对 LLM 输出具有鲁棒性——支持分隔符归一化、流式渲染与自动主题适配SwiftUI-native LaTeX math rendering robust to LLM output — delimiter normalization, streaming support, and automatic theming

向 Mac 上的 AI 编码 agent 展示 iOS 应用的实际运行状态——屏幕画面、应用内部状态、网络流量与日志，让检查 UI 变更不再依赖手动点击和截图循环。Shows what your iOS app is actually doing — the screen, the app's own state, its network traffic and its logs — to an AI coding agent on your Mac, so checking a UI change stops being a manual tap-and-screenshot loop.

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.

学术研究引用管理与论文工具——即时获取洞察，不打断你的专注。立即下载，5 分钟内即可上手运行。Academic Research Citation Manager And Paper — instant insights without breaking your focus. Download now and be running in under 5 minutes.

成本感知的 GitHub Copilot 工作流，用于清晰、有界且经过独立评审的软件变更。Cost-aware GitHub Copilot workflows for clarified, bounded and independently reviewed software changes.

追踪并比较每一个严肃的 OpenClaw 替代方案——基于实测仓库数据与 AI 撰写的决策支持，且刻意保持独立。Track and compare every serious OpenClaw alternative — measured repo data, AI-written decision support, kept apart on purpose.

针对 PX4 飞控软件的覆盖率引导事务语义审计研究 artifactResearch artifact for coverage-guided transactional semantic auditing of PX4 flight-control software.

lq 是面向 AI Agent 的独立 CLI 工具，用于解析、查询与修改 LyX 文档lq is a standalone CLI tool designed for AI agent to parse, query, and mutate LyX documents.

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.

面向长生命周期 Agent 与有状态负载的会话中心计算：暂停即保留记忆，按需恢复。Session-centric compute for long-lived agents and stateful workloads. Pause with memory intact; resume on demand.

NLP 案例研究NLP Case Study

多阶段现代控制项目：非等温 CSTR 反应器的建模、分析与控制Multi-phase modern control project: modelling, analysis, and control of a non-isothermal CSTR reactor.

面向 GitHub Copilot 的 Agentic 开发生命周期——计划、工作、证据与教训全部沉淀在 GitHub 上，而非聊天窗口中。Agentic development lifecycle for GitHub Copilot — the plan, the work, the evidence, and the lessons all live on GitHub, not in chat windows.

开源、本地优先的足球数据、分析与内容工作流。Open-source, local-first football data, analysis, and content workflow.

精选 LaTeX 实验报告，展示实验分析与科学写作。Selected LaTeX laboratory reports demonstrating experimental analysis and scientific writing

Astro 静态站点，英意双语，安全设计（security-by-design），AI 辅助的月度 RAG 杂志。部署于 Cloudflare。Astro (static), bilingual EN/IT, security-by-design, AI-assisted monthly RAG magazine. Deployed on Cloudflare.

驾驶 Claude Code Agent 的驾驶舱——打磨「指示→等待→审查→再指示」循环的桌面 Cockpit（非官方）。A cockpit for piloting Claude Code agents — 指示→待機→レビュー→再指示のループを磨くデスクトップコックピット (unofficial)

探索高达 400B 参数的先进稀疏 Mixture-of-Experts 模型，采用创新训练技术实现卓越性能🚀 Explore advanced sparse Mixture-of-Experts models with up to 400B parameters, featuring innovative training techniques for superior performance.

本文件夹包含一系列研究问题及用于回答这些问题的 Python 实验。This folder contains a series of research questions and Python experiments designed to answer those questions.

一个基于 Web 的标注平台，用于手工标注与公共空间相关的 STOMP 文章。该应用支持人工标注员对文章进行分类、回答结构化研究问题，并导出标注结果以用于计算社会科学研究。A web-based annotation platform for manually labeling STOMP articles related to common spaces. The application enables human annotators to classify articles, answer structured research questions and export annotations for computational social science research.

借助这款自托管、本地优先的应用，跨多个账户与多种货币追踪收入和支出。Track income and expenses across multiple accounts and currencies with this self-hosted, local-first application.

Maziyar Bahrami 的个人主页——展示跨学科研究、专业经历、项目与科学写作。Personal website of Maziyar Bahrami — interdisciplinary research, professional experience, projects, and scientific writing.

对 2024 年 8 月至 2026 年 8 月间 20 本期刊发表的 3,639 篇媒体与传播学文章的交互式扫描，基于 Crossref 与 OpenAlex。这是一个分诊工具而非系统综述——局限性请参阅 README。Interactive scan of 3,639 media & communication articles published Aug 2024 - Aug 2026 across 20 journals. Crossref + OpenAlex. A triage tool, not a systematic review - see README for limitations.

用于追踪 SRH 上 claude 编码过程的仓库。Repository for tracking of claude coding on SRH

BYOK AI 科研工作台——提供科学写作、可编辑图表、PPT 生成与参考文献管理，支持 12+ 模型提供商。BYOK AI research workbench — scientific writing, editable figures, PPT generation, and reference management. Supports 12+ model providers.

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.

本地化、可复现的 Python DNA/RNA 序列工具，支持可选 MCP 访问。Local, reproducible DNA and RNA sequence utilities for Python, with optional MCP access.

本地使用 AI 总结视频，从讲座、会议和教程中提取视觉亮点与文本摘要，基于 RTX 40 系列 GPU 的 CUDA 加速Summarize videos locally with AI, extracting visual highlights and text summaries from lectures, meetings, and tutorials using CUDA on RTX 40-series GPUs

促成深度协作讨论，让 AI Agent 与人类共同探索跨学科复杂研究问题。Facilitate in-depth collaborative discussions where AI agents and humans explore complex research questions across disciplines.

通过实战示例学习 LaTeX，涵盖文档排版、数学公式、表格以及面向中文用户的 Beamer 演示文稿。Learn LaTeX through practical examples including document formatting, math formulas, tables, and Beamer presentations for Chinese users.

Pinakes —— 可移植、Agent 优先的知识库。一个目录即一个 KB。Pinakes — a portable, agent-first knowledge base. One directory = one KB.

每日提示词，激发 nano banana 生成灵感。Daily prompts to inspire nano banana generation.

GeneTech 14 — 多领域实体集合（6700+ 实体，覆盖 14 个领域）GeneTech 14????? - ?????????? (6700+ entities, 14 domains)

一种经过证据校准的 Codex skill，用于在不夸大主张的前提下强化学术写作。An evidence-calibrated Codex skill for strengthening academic writing without overstating claims.

大语言模型监督微调的反馈对齐方法Feedback alignment for supervised fine-tuning of large language models

一个工作流框架，适配所有编码 agent。通过与工具无关的核心，将你的 AI 编码规范安装到 Claude Code、Cursor、GitHub Copilot、Gemini CLI、Codex 和 Windsurf。Apache 2.0。One workflow framework, every coding agent. Install your AI-coding discipline into Claude Code, Cursor, GitHub Copilot, Gemini CLI, Codex, and Windsurf from one tool-agnostic core. Apache 2.0.

Give pure-text LLM agents eyes: zero-dependency image understanding, OCR & image Q&A via MCP server + standalone Python script. 给纯文本 AI Agent 的图片理解能力(看图/OCR/图片问答)。

使用 Python 对公开数据集进行探索性与统计分析，涵盖数据清洗、可视化、解读与研究报告。Exploratory and statistical analysis of a public dataset using Python, including data cleaning, visualization, interpretation, and research reporting.

由机器强制执行的 AI Agent 前端 UI/UX Skill 包。注册表 + 懒加载：2,018 token 的路由在每次请求中从 334k token 深度内容中按需加载一个 Skill。包含 11 个发布阻塞闸门，其中一项用于校验 Skill 包自身文档与参考资料是否遵循其规则。Machine-enforced frontend UI/UX skill pack for AI agents. Registry + lazy loading: a 2,018-token router loads one skill per request out of 334k tokens of depth. 11 release-blocking gates, including one that checks the pack's own docs and reference material against its own rules.

PRISMA 指导的混合方法系统综述，跨 4 项实证研究评估 AI 陪伴的社会心理、关系及长期心理健康影响。包含定量与定性 meta 综合、跨方法三角验证与理论框架映射。A PRISMA guided mixed methods systematic review evaluating the psychosocial, relational and long term mental health impacts of AI companions across 4 empirical studies. Features quantitative and qualitative meta synthesis, cross methodological triangulation and theoretical framework mapping

Kosli API 的 MCP server——由目录驱动，兼容 Claude Code、Claude Desktop 及任意 MCP 客户端。MCP server for the Kosli API - catalog-driven, works with Claude Code, Claude Desktop, and any MCP client.

两个用于短期预测研究的已处理风电数据集，包括来自中国新疆的基于 SCADA 的风电场数据集以及 DTU 的 SOLETE 风力机数据集；数据集以 CSV 格式提供，便于可复现研究。Two processed wind power datasets for short-term forecasting research, including a SCADA-based wind farm dataset from Xinjiang, China, and the SOLETE wind turbine dataset from DTU. The datasets are provided in CSV format to facilitate reproducible research.

硕士论文（KCL）：在攻击者-机器留出划分下重新衡量 IoT 入侵检测，并测试基于 LLM 的报文预测是否能提升性能。移除泄露后，macro-F1 从 0.90 降至 0.60。MSc dissertation (KCL): re-measuring IoT intrusion detection under an attacker-machine holdout, and testing whether LLM-based packet prediction improves it. macro-F1 0.90 -> 0.60 once leakage is removed.

自动化 n8n 工作流，抓取 LinkedIn 产品经理职位，通过向量相似度与简历匹配打分，并使用 Claude 为每个职位生成简历修改建议Automated n8n workflow that scrapes LinkedIn PM jobs, scores them against your resume with vector similarity, and uses Claude to suggest per-job resume edits.

Buzz Agent 运行时 harness——监控 stock buzz-acp，可选的 sandbox 前置入口、DNA 完整性校验与 memory checkpoint。Buzz agent runtime harness — supervise stock buzz-acp, optional sandbox front door, DNA integrity, and memory checkpoint.

John Harper 的学术写作。Academic Writing of John Harper

基于 LLM 的自优化 markdown 维基构建工具，面向科研场景A self-refining LLM-powered markdown wiki builder for scientific research

无人机系统（UAS）在生态学研究中应用的系统综述。Systematic Review of UAS use in ecological research

应用型 AI 网络安全研究实验室，涵盖机器学习威胁检测、对抗机器学习、鲁棒性、网络威胁情报、MITRE ATT&CK/ATLAS、LLM 安全与可复现研究。Applied AI Cybersecurity research labs covering machine learning threat detection, adversarial ML, robustness, cyber threat intelligence, MITRE ATT&CK/ATLAS, LLM security and reproducible research.

为 AI agent 提供持久化、结构化记忆。基于 Go 的本地优先 MCP server：语义召回、去重、provenance、冲突解决。单一静态二进制，零依赖。Persistent, structured memory for AI agents. Local-first MCP server in Go: semantic recall, dedupe, provenance, conflict resolution. One static binary, zero dependencies.

多租户 SaaS 自动化平台，具备事件驱动工作流、AI 驱动的文档处理与实时集成。Multi-tenant SaaS automation platform with event-driven workflows, AI-powered document processing, and real-time integrations.

从零开始在 PyTorch 中构建 decoder-only Transformer，涵盖分词、预训练、监督微调，以及基于核心张量操作的对齐。Build decoder-only Transformers from scratch in PyTorch, covering tokenization, pretraining, supervised fine-tuning, and alignment using core tensor operations.

引文管理 SaaS：在 1000+ 目录中管理商家信息。Uberall 竞品。Citation Management SaaS: Manage business listings across 1000+ directories. Uberall competitor.

使用 Qwen3-TTS 在本地 GPU 上克隆声音并从文本生成语音，提供端到端训练流水线。Clone voices and generate speech from text locally on your GPU using Qwen3-TTS with an end-to-end training pipeline.

基于证据的构建流水线，编排 10 个 AI 子 Agent，并通过确定性 5 道关卡验证系统证明正确性。Evidence-based build pipeline that orchestrates 10 AI sub-agents and proves correctness through a deterministic 5-gate verification system.

AI 驱动的每周生活规划器 — 由多供应商 Agent 生成饮食、学习、锻炼、习惯和娱乐方案，并附带每周日程追踪。AI-powered weekly life planner - nutrition, study, workouts, habits and fun generated by a multi-provider agent, with a weekly schedule tracker.

🌐 使用 LangExtract 无缝从文本中提取语言，简化语言检测，为项目提供便捷且高准确率的增强。🌐 Extract languages from text seamlessly using LangExtract. Simplify language detection and enhance your projects with ease and accuracy.

NEXORA 的黑客松团队仓库 - [hackindia-team:ai-first-startup-hackathon-build-a-startup-using-ai-only:nexora]Hackathon team repository for NEXORA - [hackindia-team:ai-first-startup-hackathon-build-a-startup-using-ai-only:nexora]

适用于 DeepSeek、Qwen、GLM 及多种 AI 模型的 OpenAI 兼容 API 示例。OpenAI Compatible API examples for DeepSeek, Qwen, GLM and multiple AI models.

隐私优先的本地 Web 研究 MCP server，集成 SearXNG、隔离 Tor 路径、证据抽取、排序与精确引用。Privacy-first local web research MCP server with SearXNG, isolated Tor paths, evidence extraction, ranking, and exact citations.

面向多源检索、证据抽取与带引用研究摘要的自主 AI 研究助手。Autonomous AI research assistant for multi-source retrieval, evidence extraction, and cited research summaries.

基于 C/Python 的 ML 算法ML algo on C/Python

用于探索 LLM Security 新兴研究主题的研究路线图与文献综述仓库。A research roadmap and literature review repository for exploring emerging research topics in Large Language Model Security.

跨机器运行的 AI Agent 邮件系统。mail for AI agents across machines

本地优先的 CLI，用于评估 MCP server 的开销与能力，数据不离开本机。A local-first CLI that measures what an MCP server costs and what it can do. Nothing leaves your machine.

探索用于测试 ML、LLM 和 Agentic AI 系统的 AI 安全工具、论文与框架Explore AI security tools, papers, and frameworks for testing ML, LLM, and agentic AI systems

🚀 使用强化学习优化半精度通用矩阵乘法（HGEMM）CUDA kernel，性能超越 cuBLAS 及其他基准。🚀 Optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels using reinforcement learning, surpassing cuBLAS and other benchmarks with superior performance.

面向 AI Agent 的学术研究情报——论文检索、科学文献、引用分析、arXiv、作者指标、前沿研究与语义相关工作（pgvector）。支持 MCP + x402。Academic research intelligence for AI agents — paper search, scientific literature, citation analysis, arXiv, author metrics, trending research & semantic related-work (pgvector). MCP + x402.

基于 Hermes 的原生 AI 工作台，通过专业 Agent 与 Skill 完成经人工审核的精炼工作。A Hermes-native AI workshop for crafted, human-approved work through specialist agents and skills.

fold：企业级 MCP gateway——在任意 MCP 客户端与 MCP server 之间提供统一的受控端点，支持联邦、鉴权、策略、限速、缓存与审计。fold: the enterprise MCP gateway — one governed endpoint between every MCP client and every MCP server. Federation, auth, policy, rate limiting, caching, audit.

Islam West Africa Collection 的 RDF 词汇表：面向 Omeka S 的 AI 处理溯源与按模型键控的情感标注属性RDF vocabulary for the Islam West Africa Collection: AI processing provenance and model-keyed sentiment annotation properties for Omeka S