Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP 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.
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。
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.
Prerequisite: first, make sure you have the Readwise MCP server or CLI installed (whichever you prefer!)
Unlike cat videos, most data are trapped in the physical world. Bagel unlocks them and —just like you do with ChatGPT. For example:
A working pattern for SSE-based MCP clients and servers
Living Memory Architecture for Autonomous AI Agents — MCP server with typed connections, beliefs, decay, reconsolidation
An MCP server for Basecamp 3. It lets MCP-capable clients such as Codex, Cursor, and Claude Desktop read and manage Basecamp projects through OAuth-authenticated Basecamp API calls.
Self-hosted audit trail for AI agents — one command or one dashboard click from any step back to root cause.
A canvas design tool your agent can edit. Arrange structured UI nodes on the canvas; connect Claude, Codex, Cursor, or opencode over MCP and it works on the same document.
This is an example of an application that's exclusively accessible via Model Context Protocol (MCP).
Agent Skills
⚠️ 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。
AI penetration testing agent in your terminal. Multi-agent architecture • Engagement state tracking • 20+ LLM providers
LightClaw: The Real Lightweight AI Assistant
生成AIを用いて大量生産された、低品質で中身を伴わないコンテンツを指す俗語です。
is an AI Agent development scaffold Meta-Skill that establishes four layers of enhancement for any project in one command: knowledge management, architecture constraints, feedback loops, and entropy...
本项目是微信小程序 AI demo，演示**： 用户在小微对话中与小程序 AI 交互，平台返回**， 用户点击卡片后 **进入小程序的开发者业务页（接力页），在小程序内完成选品、下单、支付。
Browser automation agents forget everything between runs. Same site, same page structure to figure out, every single time. Wasted time, wasted tokens.
This repository is a generated compatibility mirror. The editable source, Issues, and contributions live in zjp1997720/zhijian-skills.
Master algorithms through intelligent guidance, not just solutions.
Claude Code artifacts graded by Skill Crossroads — click the badge for the evidence-cited scorecard.
A Claude Code skill that turns "make me a chart" into a Tufte-compliant chart. Distilled from the three foundational books by Edward R. Tufte.
Agentic browser automation and ui testing system — built with composable skills, subagent, command, and justfile layered architecture for repeatable, deployable browser use.