Cursor 安装指南
常与开发类 MCP Server 搭配使用的 AI 代码编辑器。
MCP Servers
A Model Context Protocol (MCP) server running on ESP32 (and Nordic nRF52840 in sensor-only mode), exposing real-world sensor data and bus protocols to AI assistants and automation tooling over...
Python implementation for building AI Agent with MCP (Model Context Protocol) tools and MCP server/client architecture.
is a local-first skill management platform that turns operational knowledge into structured, searchable, reusable artifacts.
This project demonstrates an Agent Development Kit (ADK) agent that interacts with a local SQLite database.
In the rapidly evolving world of web development, the integration of AI assistants with UI component libraries has become increasingly important.
The fastest BM25 scoring engine: 2,300x faster than BM25S. 28K QPS on 8.8M docs. 5 BM25 variants (Robertson, Lucene, ATIRE, BM25L, BM25+). Memory-mapped persistence, BMW pruning, streaming indexing.
Self-hosted WHOIS/RDAP API and MCP server for domains, IPv4/IPv6, CIDRs and ASNs.
This extension integrates Context7 as a Model Context Protocol (MCP) server for Zed's Assistant, providing up-to-date documentation for any prompt.
The Weaviate Model Context Protocol (MCP) server is now built into Weaviate itself — there is nothing to install or run separately.
A proof-of-concept implementation of a Model Context Protocol (MCP) server that runs in WebAssembly (WASM) within a web browser.
This server implements an MCP (Model Context Protocol) server with WebSocket enhancements for real-time data updates.
A practical, community-driven checklist for . This guide covers local and remote MCP server risks, traffic analysis, tool-call behaviors, context boundaries, authorization flows, and unsafe code...
Agent Skills
An open agentic prompt-expansion harness for image and video generation. Turn everyday intent into validated, model-ready prompts through a bounded AI-agent workflow.
把 Taiji / TAAC 训练与评估平台变成任何人和任何 agent 都能读取、比较、归档、提交训练、发布模型和收集线上评估证据的实验命令行工具。
A ready-to-use Obsidian vault for running an AI agent (Claude, Codex, etc.) as a personal OS: skills, grounding notes, and a self-improving feedback loop. Clone and open as a vault.
规格驱动 + 工程纪律的完整开发工作流 Skill，协调 OpenSpec（规格管理）和 Superpowers（TDD + 子代理审查），从需求到实现到归档一条流程走完。
Turn a web page into records your agent can use, from one 3 MB binary.
A small helper that tries to keep Engineers in step with the pace of Vibe Coding.
This is the branch tracking v7 work. If you are looking for the published latest on npm check out v6 branch.
*Write projections easily with generation*.
Describe your workflow in one sentence, and get a complete workflow definition file ready to import into Coze, Dify, or ComfyUI — including node configuration, edges, layout, and all...
Battle-tested execution playbooks that give any AI agent the exact commands, APIs, and patterns it needs — cutting token usage by and making local models as capable as GPT-4.
Skills, plugins & sub-agents Claude Managed Agents multi-agent + custom Skills + the pre-built docx skill 60 minutes A coordinator agent that fans work out to 3-5 specialist sub-agents, each with its...
This repository is a reference implementation of the stack on Trac Network for an .