Language

Shell agents

1,795 Shell AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.

1,795 agents · ranked by popularity · refine in the directory →

Shell agents — page 5 of 18

Spec-Kit-Antigravity-Skills63

An Agentic Skill System for Antigravity, transforming Spec-Driven Development into autonomous AI capabilities for the entire SDLC.

aegis62

Multi-agent codebase audit for Claude Code — 12 specialized personas with epistemic discourse and bias removal for high-fidelity findings

cc-skills62

Claude Code Skills Marketplace: plugins, skills for ADR-driven development, DevOps automation, ClickHouse management, semantic versioning, and productivity workflows

PocketClaw62

🦞 PocketClaw(口袋龙虾)— 装在 U 盘里的随身 AI 助手

hermes-self-evolution62

A self-evolving harness framework for Hermes Agent. Evolution + Critic + Verifier + Gardener cooperate to make your Hermes instance measurably more useful over time. Generic, MIT-licensed, ships empty.

zsh-llm-suggestions61

Get ChatGPT/GitHub Copilot suggestions in your zsh prompt

bash-ai61

An advanced Bash shell script functioning as an AI-powered terminal assistant, equipped with plugin support for all your terminal tasks and questions

luxor-claude-marketplace61

Professional Claude Code marketplace with 140 development tools: 67 skills, 28 commands, 30 agents, 15 workflows

claude-war-room61

Orquestrador de 5 agentes IA especializados para analise 360 de features com Claude Code. 1 comando, 5 perspectivas, 1 relatorio executivo.

reminder-watch61

Uses Apple Reminders as a bridge between Claude on your phone and Claude Code on your Mac, dispatching agents from new reminders.

claude-warden60

Security hooks and monitoring for Claude Code — quiet overrides, SSRF protection, MCP compression, OTEL tracing

git-context-controller60

Structured context management framework for LLM agents. Implements Git-like operations (COMMIT, BRANCH, MERGE) to manage long-horizon agent memory.

skills60

Agent skill library for PixVerse CLI — helps AI agents (Claude Code, Cursor, Codex, etc.) generate videos and images through structured, composable workflows.

skill_tree60

为 AI coding agent(Claude Code / Codex CLI 等)打造的 Skill 分层路由树生成器。把臃肿的单体 Skill 拆分/聚合成 ROOT → ROUTER → SKILL 的树形结构,让 agent 根据用户意图按需加载子能力,避免一次性塞满上下文。支持单 Skill 拆树、多 Skill 聚合(含歧义消解)、增量扩展三种模式,兼容 .claude/skills 与 .agent/skills 双路径约定,纯 Markdown + Bash,零依赖。

copaw-docker59

QwenPaw(原 CoPaw 项目)的 Docker 部署方案,支持一键构建和运行,相比官方镜像更小。

hermesclaw59

Hermes Agent (NousResearch) sandboxed by NVIDIA OpenShell — hardware-enforced network/filesystem/syscall policy, full memory + gateway stack

learnship59

Learn as you build. Build with intent. Ship real products. Agentic engineering done right.

claude-code-profiles59

Manage multiple Claude Code configuration profiles. Switch between work, personal, and other accounts without logging in and out.

HolyCode59

AI coding workstation: OpenCode + Claude subscription support + 30+ tools + headless browser + multi-agent orchestration

ai-science-toolkit59

Skills & reviewer agents for AI-first climate science — built and used by a PhD atmospheric scientist

claudebox58

Full Claude agent, completely contained, one command.

claude-code-setup57

Persistent memory system for Claude Code via Markdown. Setup with /init-project, resume with /catchup, wrap with /wrapup. Includes coding standards, MCP servers, and modular skills. Solves context loss after /clear.

cc-copilot-bridge57

Multi-provider routing for Claude Code CLI. Use your Copilot subscription, Ollama offline, or Anthropic Direct.

iSparto57

Open-source cross-provider AI dev team for solopreneurs, built on Claude Code + Codex CLI. Claude plans and reviews what GPT builds; a zero-context GPT pass blind-reviews the plan. One command, full army.

MyAgents_skills57

Curated open-source skills for AI agents (Claude Code compatible)

SkillTree57

为 AI coding agent(Claude Code / Codex CLI 等)打造的 Skill 分层路由树生成器。把臃肿的单体 Skill 拆分/聚合成 ROOT → ROUTER → SKILL 的树形结构,让 agent 根据用户意图按需加载子能力,避免一次性塞满上下文。支持单 Skill 拆树、多 Skill 聚合(含歧义消解)、增量扩展三种模式,兼容 .claude/skills 与 .agent/skills 双路径约定,纯 Markdown + Bash,零依赖。

lightning-agent-tools57

AI agent toolkit (skills+MCP server) for Lightning Network payments. Run nodes, pay for APIs (L402), host paid endpoints, and manage credentials.

Claude-Code-to-Deep-Agents-Skills-Converter56

Convert Claude Code skills to Deep Agents format (English & Portuguese)

chief56

A portable framework that reduces the cognitive load of working with AI coding agents — plan, build, verify, milestone by milestone.

Satori56

A Claude skill blending psychology, philosophy, and wisdom traditions into a conversation partner with actual depth. Free, open-source, not a therapist.

flutter-flame-harness56

Idea-to-store harness for Flutter/Flame games

devin-handoff56

Hand off tasks to Devin — a plugin/skill for Claude Code, Codex, Cursor, and any coding agent

openclaw-installer55

One-click OpenClaw installer in pure Bash for Ubuntu/Debian with management mode, Docker sandbox, and multi-channel support.

MultipleCursor55

Allows you to run as many cursor windows as you want on 1 codebase, allowing for agentic coding sessions.

rg_history55

Agent Skill. The only memory Claude Code needs exists in the file system.

AI_PM55

AI PM 실전 가이드 — Claude Code로 PM 워크플로우를 재설계하는 8파트 커리큘럼

longgraph-skill55

Long-horizon agent skill for Claude Code / Cursor / Codex / Grok Build — multi-task ledger loop, host-portable, clean-context supervisor, verified gates. Markdown library (loop-graph), not a framework.

gpt3-cli54

A lightweight command-line interface to OpenAI's GPT-3. Temperature, presence, and frequency up to 2. Streaming support

claude-imessage54

iMessage integration for Claude Code - autonomous agent via iMessage

post_compact_reminder54

Claude Code hook that detects context compaction and injects a reminder to re-read AGENTS.md, preventing post-compaction rule amnesia in long sessions

auto-ollama53

run ollama & gguf easily with a single command

moltron53

Self-evolving Agents. MOLTRON upgrades agents to learn and evolve skills autonomously. Welcome to the Singularity.

gtm-engineer-playbook53

10 installable Claude Code skills that turn your terminal into a GTM command center. ICP building, signal scanning, lead scoring, outreach sequences, battlecards. Built by Earleads.

codex-account53

A simple utility to switch Codex accounts

superpowers-antigravity53

An agentic skills framework & software development methodology that works. Built natively for Antigravity 2.0, CLI & IDE

enterprise-ai-agents-spec52

An open-source, detailed blueprint for implementing highly scalable swarms of specialized AI Agents in enterprise product development, emphasizing parallelization, robust governance, compliance, and minimal human oversight

ralph52

Autonomous agent loop for implementing features

offgrid-tools52

Self-contained offline environment providing local AI chat, offline Wikipedia/content archives, IRC communication, audio streaming, file server, and development tools. Designed for zero internet dependency - download once, run anywhere. Perfect for remote areas, emergency scenarios, or escaping surveillance capitalism.

AgentLint52

The linter for your agent harness. Works with Claude Code, Codex, and Cursor.

device-takeover51

OpenClaw skill: AI agent takes over Android/Linux devices via ADB+SSH — see screen, send inputs, post content, play games autonomously

plugin51

Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.

tagore51

Make AI-generated prose sound human. 29-pattern catalog + 8-rule operating system + 8-dimension scoring rubric. Works with Claude Code, OpenCode, Copilot CLI, Codex, Gemini, Goose and Hermes.

agent-resources51

Battle-tested agent skills and Cursor rules from real projects. Works with Cursor, Claude Code, and any agent.

agentic_learning50
copilot-ralph50

Copilot ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.

gptme-agent-template50

Agent workspace template for gptme - create persistent autonomous agents that build, learn, socialize, and assist you with whatever you need.

lavra50

A plugin with compound engineering workflows and memory for AI coding agents

skills50

A collection of Agent Skills for building AI-powered apps with Replicate

claude-code-sdlc50

Turn Claude Code into a full dev team — 13 AI agents, documentation-first pipeline, TDD enforcement

git-native-issue50

Distributed issue tracking embedded in Git — track issues locally, sync anywhere, no server required

NestOS50

NestOS is a full-stack GUI automation agent. It's not just "chat-driven". Think of it as a digital teammate with a real screen.

codex-intel50

Run OpenAI Codex Desktop on Intel (x86_64) macOS — repackages the official app bundle into a runnable x64 Electron build. Superseded by OpenAI's official Intel support.

gentle-agent-state50

See which AI coding agent needs you — right in your tmux tab bar. A colored dot per window (working/blocked/idle) with off-screen sound alerts. Works with opencode, pi, Claude Code & Codex.

obsidian-agent-memory-skills50

Agent skill package that gives your agent persistent memory via an [Obsidian](https://obsidian.md) knowledge vault. Your agent automatically orients itself at session start, navigates project architecture through graph traversal, writes discoveries back to the vault.

antigravity-2-fedora-installer50

Native Fedora installer scripts and local RPM packaging for Antigravity 2.0 Agent & IDE

whatsapp-agentkit49

Build custom WhatsApp AI agents with Claude Code in under 30 minutes, no coding needed.

hermes-ha-addon49

Hermes Agent Home Assistant Add-on

Building-AI-Agent-from-Scratch-LLM-based-Application-Development-Practice49

从零构建 AI Agent:LLM 大模型应用开发实践

claudecode-codex-subagents49

A Claude Code plugin for orchestrating complex tasks by delegating to multiple parallel Codex agents, then merging and reviewing results.

harness-init49

OpenAI harness engineering repo initialization scaffold for agent-first development. Works with Claude Code, Codex, Cursor.

zen-agentic-engineer-config49

zen-agentic-engineer-config

evey-setup49

Get a hermes-agent stack running in minutes. Free models, 29 plugins, zero cost.

remote-gpu-trainer49

An Agent Skill for the DL experiment lifecycle: RUN (a GPU you own or rent) → VERIFY the number is real → DELIVER reproducible, single-source figures and tables.

joompulse-skills49

Public Claude agent skills that turn JoomPulse data into Mercado Livre seller workflows: market research, competitor tracking, product discovery. Requires JoomPulse MCP.

beszel-agent-openwrt49

📊 Pre-built Beszel Agent packages for OpenWrt

linkly-ai-skills49

Agent Skills for Linkly AI — search, browse, and read your local documents from any AI coding agent.

tmux-pane-tree49

┣nteractive tmux pane tree with live agent badges and Vim-style navigation.

context7-skill49

Context7 documentation lookup skill for AI coding agents. Lightweight REST API wrapper with no MCP context overhead.

clawdboss-upgrade48

🦞 Non-destructive upgrade tool for existing OpenClaw installations. Merges Clawdboss improvements without destroying your customizations.

claw-hy2-agent48

这是一个用于claw.cloud部署 Hysteria2 + Nezha Agent 的轻量级 Docker 镜像。

ask48

ask is an AI-powered CLI tool for developers who live in the terminal. It brings multi-provider LLM support, agent capabilities, and shell-native intelligence to your fingertips.

skills48

Skills for AI agents.

brin48

credit score for context

pomasa48

Patterns of Multi-Agent System Architecture

huntkit48

Investigation toolkit for Claude Code: case management, OSINT, structured analytic techniques, chain-of-custody evidence capture, and bundled threat-intel MCP servers.

clawpilot48

🐾 ClawPilot — your OpenClaw copilot. Security-first agent skill for AI coding assistants. Supports 14+ chat platforms.

ai-ceo-framework48

Run your entire company with Claude Code. 15 AI Agents + 5 Skills + Approval Pipeline. Battle-tested in production for 1+ year.

claude-memory-skill48

A minimal, low-friction memory system for Claude Code

wechat-use48

macOS pure-background WeChat send CLI — no UI flash. Agent skill via npx skills.

quantum-free-router48

Zero-cost LLM routing across free-tier model APIs with Bifrost, certification scripts, and agent-ready fallback chains

cybergym-e2e48

CyberGym-E2E is a large-scale benchmark built from real-world vulnerabilities in widely used open-source projects to evaluate AI agents' end-to-end cybersecurity capabilities, from discovering vulnerabilities to generating proof-of-concept to writing patches.

agent-install-scripts48

Setup scripts for Agent DVR

awesome-gemini-cli-subagents48

A curated collection of 81 production-ready subagents for Gemini CLI. Drop them into .gemini/agents/ and let Gemini delegate the right specialist.

agentguard47

Universal security guardrails and workflow policies for AI coding agents.

Multi-Agent-Template-App47

A radically simple, reliable, and high performance template to enable you to quickly get set up building multi-agent applications

ispyagentdvr-docker47

Multi Aarch image of iSpy's Agent DVR, standalone free-to-use NVR software for IP Camera management

claude-boris47

The Ultimate Claude Code Workflow - Memory Bank, 14 Agents, 18 Commands, 10 Critical Gap Solutions

pm-workspace47

Sistema de gestión de proyectos, impulsado por OpenCode y ClaudeCode como asistentes de CEOs, CTOs, PMs, Scrum Masters, aquitectos, desarrolladores/as, QAs... con capacidad de delegar implementación técnica a agentes de IA.

minions47

Open-source multi-agent PM-ops team — associate PM, GTM, QA, data-analyst subagents and more, orchestrating product work end to end.

codex-bridge47

A Claude Code skill that bridges Claude Code to the Codex CLI: externalizes plan, files, conversation and conventions into an on-disk bundle, runs codex exec, validates the JSON response with jq.

Browse other language pages