agents

Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.

Skills for teaching agents how to build on Cloudflare.

oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.

A world-class collection of Claude Code utilities: autonomous skills, expert agents, slash commands, and prompts that supercharge your development workflow

全网最全的、持续更新的、最火爆的 100+ 人格 蒸馏skills 合集｜ 多agent系统 ｜名人/导演/天涯大神/古籍/二次元/职场/情感全品类

The World's Fastest Claude Code Launcher Make Claude Code launching simpler Click Dock to launch, or start from any folder instantly.

Huge AI models catalog. A curated list of AI tools, platforms, and resources across various domains.

Drop agents inside running marimo notebook sessions

Vibe-Coding is easy. DevOps is hard. OpenCode & Git token-efficient AI agent automation for your app, business, and personal development. Opinionated tools, services, CLI & API stack for speed, security, and 24/7 results. Open-source first. SOTA everything. Try on your repos for money-making magic.

A recursive coding agent inpired by RLMs

PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.

A Docker & dev container setup for securely running AI agents in `--dangerous` mode. All container traffic is routed through a transparent mitmproxy, enforcing network access rules and injecting secrets.

Stop your coding agent from stalling real work on self-invented bookkeeping - receipts, hashes, locks, certification rituals. Ship first, then verify. Skill for Claude Code, Codex, and other agents.

Minimal by design, explicitly multi-lang, production-ready and battle-tested collection of configs and plugins for your Claude Code agentic development workflows: mcp, configs, skills, agents and more.

A More Effective Agent Harness for Claude

Self-hosted app store and runtime for AI agents. Install third-party agents, run them on your infrastructure with your own model providers (Ollama, Bedrock, OpenAI, etc.). Container isolation, credential injection, default-deny egress.

A collection of structured AI agent skills that enable Claude Code, Cursor, GitHub Copilot, and other AI coding assistants to create, operate, debug, and govern Harness CI/CD workflows through natural language.

Supercharge Claude Code with Expert Knowledge A comprehensive framework for AI-assisted development. Install standardized rules, agents, and commands for your projects across multiple technology stacks.

Skill pack for Claude Code that helps you monitor and troubleshoot your K8s clusters superintelligently

Research capability for coding agents: multi-source corroboration, active discovery, logical-space thinking, structured output. Browser-first evidence.