Coding & Development

Context management framework for Claude Code — Multi-agent isolates context by capability, module topology tree isolates context by business domain

AI-curated multi-vendor certification practice exam platform — Next.js 15, Prisma, PayPal, Claude Agent SDK, Coolify-ready.

A Model Context Protocol (MCP) server for GoHighLevel API v2 — giving any AI agent full access to your GHL location.

Provide a clear, practical security checklist for teams building and deploying Model Context Protocol servers and AI agent infrastructure.

Shared AI coding agent infrastructure — define MCP servers once, deploy to every agent

Reusable AI Agent skill for building subject timeline HTML from listings, protocol files, and PD trackers.

Ably's official collection of agent skills

Startup failure diagnosis agent skill distilled from 1100+ failed startup case studies

Vibe-coded tower-defense game built by an AI agent pipeline (planner → coder → smoke-tester → reviewer) running across Claude Code, Cursor, and VS Code Copilot.

Local-first BYOK AI workspace for reusable assistants, prompts, tools, skills, model choices, and private local history across multiple LLM providers.

On-call intelligence for DevOps and platform teams. Local-first AI agent over your tools — HITL-gated, MCP-native, AGPL-3.0.

Native SwiftUI macOS client for Paseo daemon (Claude Code remote agents)

Browser-based control panel for managing and monitoring Claude Code multi-agent pipelines

Codex AI Coding Agent for Android - Native app with deep system integration

DreamCoder - Claude Code 骨架下的中文原生 AI 编程桌面工作台 | dreamfield非官方指定coding agent |DreamSeed 种梦计划参赛作品

面向 Claude Code 与 Codex CLI 的 AI 小说写作工程框架 | Inspired by InkOS | AGPL-3.0

SkillSpec is a DSL that adds types, contracts, composition, and tests around agent skills, then compiles back down to the same SKILL.md that existing runtimes already understand. Once a skill works and you want to make it production-ready, you codify it into a .agent file and get versioning, structural diffs, type checking, and a path to CI/CD.

It lets you scan local agent skill folders, bundle multiple skills into a reproducible skill pack, publish that pack to GitHub Releases, install other people's packs, and keep editable workspaces synced across machines.

Agent Your Agent (AYA) — multi-agent orchestration framework built on Claude Code CLI. Routes tasks to the best model (Claude/Deepseek/GPT), coordinates parallel workers via file-system protocol.

29 .mdc architecture rules that prevent AI coding assistants from hallucinating insecure auth, deprecated imports, and broken Next.js 15 patterns. Built for Cursor Agent and Claude Code.

An MCP-first AI Agent for DeepSeek powering digital work.

Personal collection of Claude Code skills

Agent Skill for academic journal recommendation, journal selection, manuscript submission, CAS/JCR ranking, Aims & Scope matching, and publication-risk checks.

💻 Control AI agents to automate tasks on computers, enabling true autonomy with browser, terminal, and desktop interaction. Perfect for developers.