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

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses,...

A database-backed Model Context Protocol (MCP) server for managing structured project context, designed to be used by AI assistants and developer tools within IDEs and other interfaces.

MCP server for long term agent memory with Mem0. Also useful as a template to get you started building your own MCP server with Python!

A simple MCP server for Obsidian

MCP server that integrates the LINE Messaging API to connect an AI Agent to the LINE Official Account.

结合 Vue 3 前端 + FastAPI 后端 + LitServe GPU负载均衡

The local runtime, CLI bridge, SDK, drop-in adapters, and wallet/auth/signing layer are MIT and readable here, so you can verify what runs on your machine rather than trust a black box.

⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero now; Obsidian, Apple Notes & local docs on the road).

⚡ Blitz Strike — a universal MCP penetration-testing toolbelt. Structured methodology: reconnaissance & attack-surface mapping, source-to-sink analysis, and live validation.

Agent-native knowledge engine — search, deep-read, and build knowledge bases from Markdown, PDF, DOCX, and PPTX.

Model Context Protocol (MCP) to enable AI LLMs to trade using MetaTrader platform

We don't make AI smarter. We make it experienced. AI coding memory — the local-first memory + judgment layer for AI coding agents. Save up to 50%+ of AI tokens. Stop repeating yesterday's bug.
Agent Skills

Turn AI output into game design decisions you can verify. Local-first · Evidence-linked · Human-gated

PersianTools provides Jalali (Shamsi) dates and datetimes that work just like Python's datetime — plus handy tools for Persian text: digit conversion between Persian, Arabic, and English, character...

Read the skill docs » · Install · Example report · 繁體中文

fizzy is a command-line interface for Fizzy. Manage boards, cards, comments, and more from your terminal or through AI agents.

MotionEyes is an agent-first SwiftUI motion observability system.

把授权照片、主页截图、简介或已有角色档案,转成一套可长期复用的极简手绘图解角色;再把文章、课程、观点或脚本拆成适合传播的长文配图、知识卡、方法拆解图、手机海报或整页 PPT 演讲页面。

My agent skills that I use every day to do real engineering - not vibe coding.

Perforated is a data-efficiency layer for machine learning that adds artificial to your neural network.

An agent that directs Seedance 2.0 like a filmmaker — reading each scene before it writes the prompt.

The skills here are built from this source into a portable Agent Plugin and installable client-specific plugins for Claude Code, Cursor, Codex, and Grok — install one of those, not this repo.

Portable for writing ML/AI academic papers — from topic to compiled PDF, with verified BibTeX citations, gated workflows, and multi-agent collaboration.

Readable RTL → clear behavior → reviewable delivery Give AI the design intent, review the behavior preview, and receive artifacts you can inspect and verify.