Governance runtime for Claude Code. Enforces workflow gates at tool time, delivers the engineering rules relevant to the work, and preserves decision provenance across sessions.

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

Reverse engineer anything with agents, from app behavior down to native binaries.

The open standard for omnipresent AI. Claude Code, OpenCode, Gemini CLI, Shell, Chrome, DeepSeek Harness. Model-agnostic

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-first methods, powered by TypeScript and Bun.

Open-source AI front-office factory for agencies serving local businesses: website, booking, intake, CRM, and agents in one workspace. Self-hostable.

Standalone engineering skills for Claude Code and Codex: review, audit, optimization, testing, product discovery, architecture, and safe publishing.

AI chat and agent tooling for Godot, with both MCP support and in-built native chat window.

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.

A comprehensive guide for setting up Claude Code CLI with PRD-driven workflows, extended thinking (ultrathink), and planning modes optimized for Swift/SwiftUI iOS development.

Agent-ready writing studio for Chinese WeChat articles, English essays, research writing, human voice editing, source-bound data storytelling, and statistical graphics.

Air traffic control discipline for agent output. Written for a reader with ADHD.

The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.

The Most Advanced MCP Server for Unity Editor with execute_code, prompts/resources, input simulation, screenshots, and play mode automation.

Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after compaction, plug-in code standards, optional TDD mode, and zero behavior changes for developers.

The design layer for agentic AI — design context, interface checks, and verification for coding agents.

On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.

🚀 UE5-UMG-MCP: A deep-focused MCP for Unreal Engine UMG layout. Designed to maximize AI efficiency within limited context windows by prioritizing precision in UI structure, animations, and blueprint integration.

A Claude Code skill that plays bouncer at the door of production: audits AI-built apps (Lovable, Bolt, v0, Cursor) across 5 domains and hands you a scored punch list with copy-paste fixes. MIT.

You say it. AutoCode ships it. 48 skills. Code to deployment in one session. I-Lang v5.0 judgment + secret-safe deploys. Free forever.

PyWry is a cross-platform app factory, rendering engine and UI toolkit for Python that produces native desktop, web, and notebook experiences from a single API.

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence