Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
MCP servers for Yandex APIs — search, keyword research, webmaster tools, and web analytics for the Russian market.
An MCP server that connects Claude Code to xAI's Grok, unlocking real-time web search and X (Twitter) search capabilities.
Production-ready starter for with Playwright, TypeScript, Page Object Model, and AI-powered Claude Code agents via MCP.
Long-term memory for Claude Code. Indexes every session as SQLite+FTS5, exposes recall via MCP, and ships PreCompact/PostCompact hooks so nothing is ever lost.
A currency conversion MCP server
PlatformIO MCP is the open-source, agent-first hardware execution layer for embedded development.
An MCP server that delivers cryptocurrency sentiment analysis to AI agents, leveraging Santiment's aggregated social media and news data to track market mood and detect emerging trends.
Interactive terminal coding agent in Rust — runs the DeepSeek V4 Flash model locally on macOS (Metal), with a Ratatui TUI, a full tool suite, MCP, and persistent sessions.
AI-powered X.com automation using Claude Agent SDK and Chrome DevTools MCP
Offensive security you run yourself — a local MCP workflow for authorized testing, in CI or against staging.
AgentMail has one MCP tool implementation, hosted at:
一套建構在 之上的美股投資研究與組合管理工作區。把日報、組合檢視、個股深度分析、選擇權策略、交易日誌等流程，全部封裝成可重複執行的 slash command，並用一套**（可驗證 thesis → 證偽條件 → 機率分布 + EV）約束每一個投資結論，避免淪為 narrative。
Agent Skills
A high-performance, enterprise-grade Next.js 16 application for mission-focused non-profit organizations. Built for high impact teams.
Open-source repository of finance and investing skills built around the SKILL.md format.
Skills that translate your coding agent's output into plain language: honest reports, straight verdicts, steps you can follow. MIT.
265 Rust rules your AI coding agent can use to write better code. Current for Rust 1.96 (2024 edition).
你現在是 lo2cin4bt 的專案經理（Project Manager，PM）。請檢查本機環境、初始化內建策略示範，並幫我執行 QQQ 日線簡單移動平均線（Simple Moving Average，SMA）穿越回測。整個流程只做本機研究，不要實盤交易或下單。
A systematic methodology for refactoring AI-generated code (Vibe Coding). Helps you discover duplicate implementations, unused resources, and inconsistent patterns.
— this project is in early development. Expect rough edges, breaking changes, and the occasional FreeCAD crash from LLM-generated code. Use with caution and save your work frequently.
FileScopeMCP watches your code, ranks every file by importance, maps all dependencies, and keeps AI-generated summaries fresh in the background. When your LLM asks "what does this file do?
⚠️ senpi is an opinionated, in-flight fork of badlogic/pi-mono. It powers Dori under the hood and reflects what one specific AI assistant needs from a coding-agent runtime.
(maintained by the authors): - https://github.com/minicoohei/ai-agent-camp Running AI agents from this repo grants them shell, file-write, and external-API permissions on your machine.
基于 Hermes 改造的轻量级 AI 助手框架，可以快速打造商用 SaaS 平台，支持多租户隔离部署、多平台渠道接入、工具调用、定时任务和 Web 实时通信。
让 AI 编码助手可靠地写嵌入式固件的开箱即用工程框架。 AI 写嵌入式三宗罪：乱猜引脚、上下文断档、空口宣称修好。auto-embedded 一条命令装进你的固件工程——强制五阶段流程、冻结的硬件资源表、落盘的任务记忆、编译/烧录/调试工具技能、80+ 篇离线嵌入式知识库——一次接线，7 个 AI 平台同时生效。