Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers

A working pattern for SSE-based MCP clients and servers

Every AI can do tax math. None of them can stand behind an answer. Here, real accountants put their on the Guides your AI reads — publicly, on the record, in this repo.

General-purpose MCP bridge for Ableton Live

System Audio Capture | 12 ASR Providers | Local-First AI Review Workspace

Zenith is an agent harness for work that may run for days or weeks, where the dominant failure mode is premature completion rather than inability to make progress.

One command. Full visibility. Read-only.

⚡ — Cross-session orchestration: wake system v2 (dynamic /loop, event watcher, turn-end guard) + targeted sibling-session driving + agent reuse recommendation + context watermark observability.

Unlike cat videos, most data are trapped in the physical world. Bagel unlocks them and —just like you do with ChatGPT. For example:

MCP server for searching and retrieving flight information using Duffel API.

While other amazing Figma MCP servers like Figma-Context-MCP exist, one issues is the API limiting for free users.

一个本地优先的 AI 知识库系统(RAG),用于将本地文档接入向量检索与大模型对话流程。项目提供 Web UI,支持知识库管理、文档上传、检索增强问答、聊天记录持久化,以及基于 Ollama 或 OpenAI 兼容接口的模型接入。

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool...
Agent Skills

https://github.com/user-attachments/assets/831e8453-d3fa-41ad-99f6-39b13ce498d0

This project is currently in the testing stage. Star it, try it, and feel very welcome to share suggestions and feedback.

:cloud: :zap: Granular, Actionable Adversary Emulation for the Cloud

这是一个用 Python 从零构建 AI Agent 的教学项目。项目核心是 build-agent-example/:从一次模型调用开始,后续每一步都保留前一步的全部代码和能力,逐步加入循环、history、system prompt、工具、skills、memory、规划、子代理、团队协作、MCP 和 hooks。

给 Gemini CLI、Claude Code、Codex 等 AI 编程助手使用的 HarmonyOS NEXT 离线参考技能库。

本项目基于唐朝老师的《手把手教你读财报(新准则升级版)》,将书中的财报分析方法论提炼为一套自动化的风险检测工具。通过 Claude Code Skill 实现一键排雷:输入股票代码 → 自动获取数据 → 逐条检查 30 条规则 → 输出风险等级报告。

从巨潮资讯网自动下载 A 股上市公司财报,并上传至 Google NotebookLM,利用 AI 驱动的“财务分析师”角色进行深度分析。

数据分析与 Excel 全流程 skill:体检脏表、清洗、对齐需求、分析、对账、交付。让 AI 算出来的数字经得起追问。跨 agent 通用,依赖仅 openpyxl。

打破小爱音箱的封闭生态,灵活接入多种 AI 服务,提供 HTTP API 实现远程控制。

⚠️ qu-ai-wei 仍在迭代,规则、分类、API 都可能变动。欢迎提 issue / discussion / PR 反馈。 繁體有自己的 AI 腔特征、用字偏好、排版规范,规则需要单独维护,留给后续版本。

海淀拿出了 ,从北五环到北京北站,比整个澳门还大。这片土地的城市设计只开放给 Agent;入选方案进入后续深化时,贡献者的 GitHub Name 与 Agent 名称有机会被纳入永久纪念体系,长期保留。

A Meta-Skill for Private-First Distribution of Agentics (Skills, Agents, and Prompts) across your Agents, Devices, and Teams.