AI Systems & Skills Security Vetted

Shell

Top open-source Shell AI systems, agents, and MCP tools.

1-Click CLI Quickstartv0.1.10
$aistorehub pull @community/codex5-6-coldbrew

Discover and install verified Shell AI systems, autonomous agent skills, and Model Context Protocol servers on AIStoreHub. Reusable, security-scanned, and ready for 1-click execution in Cursor, Claude Code, and terminal workflows.

17Systems Indexed
49568Community Stars & Forks
17Verified Creators

Available AI Systems & Skills (17)

Open in Advanced Filter
agentCommunity Indexed
Source·Free

codex5.6破甲 冷咖啡|ENI ColdBrew v3.1.0|17领域 181节点|QQ群:1057540028 / 1077074552

agentCommunity Indexed
Source·Free

Run Linux-style commands on Windows via deterministic bash→PowerShell translation. No VM, no WSL. MCP server + CLI built for AI agents (Claude Code, Codex, OpenCode...). GNU-style output, bash-style errors, UTF-8/GBK handled.

ToolCommunity Indexed
Source·Free

Like the shell history command but for your Claude Code sessions.

MCP ServerCommunity Indexed
MCP·Free

Execute commands interactively on remote Windows machines using the WinRM protocol (just faster)

agentCommunity Indexed
Source·Free

Native Windows Bash for AI coding agents. Run Claude Code, Codex, opencode & Gemini CLI without Git Bash, MSYS2 or WSL. Built in Rust, with MCP support.

agentCommunity Indexed
Source·Free

The terminal that outlives its window. Shells survive quitting the app, agents can drive other agents, and remote machines work the same way. Pure Rust, GPU-rendered.

agentCommunity Indexed
Source·Free

QuietHarness:Claude Code、Codex、Cursor 共用的轻量 AI 工作系统

agentCommunity Indexed
Source·Free

Terminal-native AI coding assistant for real repositories. Inspect code, edit files, run tests, and verify changes from the CLI.

agentCommunity Indexed
Source·Free

单文件智能体,Single-file zero-dependency AI agent for Linux/Windows ops

agentCommunity Indexed
Source·Free

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.

ToolCommunity Indexed
Source·Free

Custom status line for Claude Code showing model, tokens, rate limits, and git info in real-time

agentCommunity Indexed
Source·Free

the extensible, customizable, self-documenting, real-time multi-agent computing environment

agentCommunity Indexed
Source·Free

The World's First Virtual Terminal for AI Agents

ToolCommunity Indexed
Source·Free

Run multiple Claude Code accounts on one machine — per-project switching, live usage limits, and session handoff when you hit a rate limit

agentCommunity Indexed
Source·Free

Shell and coding agent on mcp clients

agentCommunity Indexed
Source·Free

Empower the Shell to think. Evolve Operations.

agentCommunity Indexed
Source·Free

Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

Build & Monetize for Shell

Have you created an autonomous agent, MCP server, or Claude Code skill for Shell? Publish it to AIStoreHub with dual-currency checkout (USD $ + INR ₹) and earn 85–90% net revenue.