仓库/Skill 库

为赫尔辛基大学师生打造的 LLM 聊天工具，用于教育与研究。LLM chat built for University of Helsinki staff and students, for education and research.

可审计的 MCP + 跨 Agent 框架，支持自主与人工引导的学术写作——从经验证的证据到已审校的 DOCX/PDF。Auditable MCP + cross-agent harness for autonomous and human-guided academic writing—from verified evidence to reviewed DOCX/PDF.

🤖 在易用平台中通过 AI 驱动工具轻松管理多个 Telegram 账户，支持群发、调度等🤖 Manage multiple Telegram accounts effortlessly with AI-driven tools for bulk messaging, scheduling, and more in one easy-to-use platform.

在研究全球干旱状况的同时实践可复现研究方法的项目A project to practice reproducible research practices while studying the state of drought around the world

一款插件，将 PayPal 的 API 与 MCP server 集成到多个 AI 编码 Agent（Claude Code、Cursor 等）的开发流程中。A plugin that integrates PayPal's APIs and MCP server across multiple AI coding agents (Claude Code, Cursor and more) into your development workflow.

官方开放数字产品工厂This is the official open digital product factory

面向律所的自托管、GDPR 合规 AI Agent。零云依赖、哈希链审计追溯（符合 AI Act 第 12 条）、自带模型、支持 9 种语言版本。willchen96/mike 的硬分叉，AGPL-3.0 许可。Self-hosted, GDPR-safe AI agent for law firms. Zero-cloud, hash-chained audit trail (AI Act art. 12), bring-your-own-model, 9 language editions. Hard fork of willchen96/mike, AGPL-3.0.

面向 Godot 与 Unity 的 Playwright 风格 UI 测试，通过 MCP 提供统一的语义自动化层，支撑测试、CI 与 AI 编程 Agent。Playwright-style UI testing for Godot & Unity. One semantic automation layer for tests, CI, and AI coding agents via MCP.

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.

基于 Claude Code 的 AI 辅助学术写作框架，覆盖从课程论文到学位论文。KI-gestütztes Framework für wissenschaftliche Arbeiten mit Claude Code. Seminararbeiten bis Dissertationen.

连接 Suunto 手表数据到 Claude 及其他 AI 助手的 MCP server。MCP server that connects your Suunto watch data to Claude and other AI assistants

面向 systematic review 和 evidence synthesis 的 AI 驱动全文筛选与数据提取。AI-Driven Full-Text Screening and Data Extraction for Systematic Reviews and Evidence Synthesis

一个强大且高效的浏览器 agent，可自动化完成网页上的任何任务。A powerful & efficient browser agent that automates any task on the web

面向业务的 Agent harnessThe business agent harness

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.

经过调优、功能完备的 MCP，以 LLM 优化的方式操作文件系统。Tuned and fully-featured MCP to work with the filesystem in LLM optimized way

面向 AI Agent 的 Markdown 优先的长期记忆基础设施。通过 MCP 在 markdown/代码文件上实现 BM25 + 语义混合检索。Markdown-first, long-term memory infrastructure for AI agents. Hybrid BM25 + semantic search across markdown/code files via MCP.

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.

AI4Scholar for DeepSeek Harness (dsh)：38 个原生学术工具——Semantic Scholar、PubMed、Google Scholar、arXiv、bioRxiv/medRxiv、DOI、full text、auto-cite、figures、unified search。由 ai4scholar.net 提供支持AI4Scholar for DeepSeek Harness (dsh): 38 native academic tools — Semantic Scholar, PubMed, Google Scholar, arXiv, bioRxiv/medRxiv, DOI, full text, auto-cite, figures, unified search. Powered by ai4scholar.net

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.

SharpAI 是基于 llama.cpp（通过 LlamaSharp）构建的可嵌入 Embedding、补全与模型管理平台，内置 Ollama 兼容的 Web 服务。SharpAI is an embeddable embeddings, completions, and model management platform using llama.cpp via LlamaSharp, with a built-in Ollama-compatible webserver.

JabRef 博客的代码仓库。Repository for JabRef's blog

运行 Ollama 本地 LLM 服务的 Docker 镜像。默认安全，所有 API 请求需 Bearer token（首次启动时自动生成）。OpenAI 兼容 API。支持首次启动模型预拉取、NVIDIA GPU (CUDA) 加速和持久化模型存储。多架构：amd64、arm64。Docker image to run an Ollama local LLM server. Secure by default, all API requests require a Bearer token (auto-generated on first start). OpenAI-compatible API. Supports first-start model pre-pull, NVIDIA GPU (CUDA) acceleration, and persistent model storage. Multi-arch: amd64, arm64.

定位并修复 MCP 2026-07-28 规范修订给你的 server 带来的破坏。21 条规则、5 个自动修复器与一张就绪度看板。Find and fix what the MCP 2026-07-28 spec revision breaks in your server. 21 rules, 5 autofixers, and a readiness board.

数据在本地自由探索 —— AI Agent 受控运行。具备治理化 Agent 访问能力的联邦化数据探索器。Your data, explored locally — and your AI agents kept on a leash. A federated data explorer with governed agentic access.

用于学术写作的 Agentic Claude Code skills：评审模拟、修改与润色。Agentic Claude Code skills for academic writing: review simulation, revision, and prose improvement.

自动化你的工作：local-first AI 任务中枢。Email、Teams、Slack 及报告 → 统一时间线 → AI 分类 → 你的编码 agent（Claude Code、Codex、Gemini）执行，你审批。Automate your job: local-first AI task hub. Email, Teams, Slack & reports -> one timeline -> AI triage -> your coding agents (Claude Code, Codex, Gemini) do the work, you approve.

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.

TransPraxis / 译践 —— AI 辅助的翻译实践、术语治理、交付与学术写作工作空间。TransPraxis / 译践 — AI-assisted translation practice, terminology governance, delivery, and academic writing workspace.

面向 Node.js 与 TypeScript 的 AI firewall。阻止 prompt injection、音频幻觉与 RAG 数据爬取。零依赖。MIT 许可。AI firewall for Node.js & TypeScript. Stop prompt injection, audio hallucinations, and RAG data scraping. Zero dependencies. MIT

面向 AI agent 的轻量、Git 备份的永久记忆。A lightweight, Git-backed permanent memory for AI agents.

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.

Promovolve 是一项试图找回杂志广告昔日魅力的尝试。Promovolve is an attempt to get back what magazine advertising had!

Claude Code Agent 的 Web 仪表盘与自动驾驶 —— 在浏览器中管理会话、任务与审批Web dashboard + autopilot for Claude Code agents — manage sessions, tasks, and approvals from your browser

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