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
A Claude Code skill providing the latest OWASP security best practices (2025-2026) for developers building secure applications.
**是一个 AI Skill——不是魔法棒，不是"一键生成好莱坞剧本"的营销噱头。它是一个经过精密设计的**，把成熟故事一步一步转化为标准影视剧本、分镜方案和数字资产清单。
compile lua2c (single binary with embedded scripts)
An easy-to-use web framework. Based on baize and pydantic.
· Next-Gen Transparent Agent Architecture
주요정보통신기반시설(CII) 취약점 분석평가, AI 보안 평가, 로봇 보안 점검, 우주 보안 점검, 시큐어코딩 가이드, 제로트러스트 보안 평가, SW 공급망 보안(SBOM)을 위한 Claude Code 스킬 플러그인입니다.
Local-first AI agent framework built for small models, with optional hybrid cloud support.
AI defaults to the mean. Models are trained on millions of average websites. If you don't constrain them, they will build an average website.
A skill that turns any goal into one short, paste-ready prompt. That prompt makes your agent pick a real quality bar, split the work into small pieces, run a builder and a separate harsh critic on...
This project is currently in the testing stage. Star it, try it, and feel very welcome to share suggestions and feedback.
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。