Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
Original-SVG-first architectural community design copilot framework with mandatory OpenCrab MCP workflow.
Free trending topics aggregator — 20 sources, zero auth. CLI + Python library + MCP Server.
This is an unofficial, community-built project. It is not affiliated with, endorsed by, or maintained by HackerOne. "HackerOne" is a trademark of HackerOne, Inc.
An experimental way to connect MCPs to Pi using Code
This project showcases how to use the MCP protocol with OpenAI, Azure OpenAI and GitHub Models. It provides a simple demo terminal application that interacts with a TODO list Agent.
Give Claude Code eyes for your frontend. No more blind debugging where Claude guesses about your UI, you take screenshots, and you go back and forth hoping it understands what's broken.
Illustrative estimates. The ~90% is Claude-side token reduction on analysis-heavy tasks — not total cost: Kimi's own subscription still applies.
The offline internet — searchable, browsable, and self-updating. A modern server for ZIM files with cross-source search, built-in library management, JSON API and MCP server.
Most AI coding tools give you a result but no record of how you got there - no trail of decisions for teammates to follow, no way to continue work across sessions, and no framework for managing large...
- 功能集大成：集成市面已有项目的大部分功能，还会继续维护根据issue添加功能 - 依赖极少：只需要一个最新的FastMCP2.0，不需要复杂的uv及特定版本的python - 兼容性强：支持所有MCP功能的大模型助手，无需科学上网配置复杂的依赖和环境，成功率极高 - 代码极简：市面项目大量采用嵌套代码生成工具，可读性极差。本项目浓缩到单文件，mcp.
小叶发布器：连接浏览器登录态与 MCP/AI 客户端，一键提取文章并保存到公众号、知乎、掘金、CSDN 等平台草稿箱，适合自媒体作者和开发者本地自动化发布。
ensp通过mcp接口连接到trae实现ai对ensp设备的全自动化规划和配置
Agent Skills
(刺し子, literally "little stabs") is a form of decorative reinforcement stitching from Japan. Originally used to reinforce points of wear or to repair worn places or tears with patches, here it...
Self-hosted team chat where humans and agents are first-class members — channels, DMs, threads, reactions, file uploads, and an agent runtime.
A Context Engineering Framework for AI-Assisted Multi Agent Applications Development
一个本地优先、可被 AI Agent 调用并持续维护的个人知识库，以及它的可视化 Workbench。
Type one sentence, approve once, walk away — Toh Framework installs an AI build department (14 commands, 8 agents, 23 skills) into your project and keeps building, testing and fixing until it is...
An foundation for shipping browser games with Vite 8 · React 19 · TypeScript · Three.js.
A collection of skills for agentic LLM tools
Turn scattered, duplicated AI-agent Skills into per-Agent Rosters—with evidence, receipts, and exact undo.
A human-governed AI coding workflow that distills ephemeral session context into persistent project memory—making work traceable, reviewable, and resumable.
Expert code review skill: SOLID, security, performance, error handling, boundary conditions
Proof SDK: open-source collaborative editor, provenance model, and agent HTTP bridge
A comprehensive, build-ready reference for constructing a high-performance personal knowledge system using Obsidian and Claude Code, grounded in Andrej Karpathy's "LLM Wiki" pattern (April 2026).