kooky — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by iAmCorey · Agent Tool · ★ 639

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is kooky safe to install? View the security audit →

About kooky

kooky A minimal modern terminal for AI coding. 🇬🇧 English · 🇨🇳 中文 · 🇯🇵 日本語 A minimal modern terminal built for AI coding. Sidebar workspaces; horizontal / vertical split panes; one-click agent launch; per-agent activity readout; live workspace state with one-click Node and branch switching. Open-source, MIT-licensed. No accounts, no telemetry; app state stays local. GPU rendering via libghostty. Download latest · Changelog Features Vertical tabs, split panes & windows. Sidebar workspaces with three-state collapse (). Each pane owns its own tab strip and active tab; split it right or down from the two buttons on its tab bar, or wit

agentai-agentsai-codingclaudeclaude-codecoding-agentdeveloper-toolslibghosttyllmmacos

Quick Facts

Stars639
Forks36
LanguageSwift
CategoryAgent Tool
LicenseMIT
Quality Score66.8050080628616/100
Open Issues5
Last Updated2026-09-05
Created2026-05-08
Platformsclaude-code, cli
Est. Tokens~17k

Compatible Skills

These tools work well together with kooky for enhanced workflows:

  • workflow-audit — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
  • Hopet — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (52%)
  • octo-terminal-releases — semantic(0.34)+complementary+rare_topics+similar_pop+shared_platform (51%)
  • skills-manager — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (51%)
  • codmate — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (51%)

kooky alternative? Top 6 similar tools

Looking for a kooky alternative? If you're comparing kooky with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • termio by termio-sh · ⭐ 434

    A terminal-first agentic development environment for agentic coding. Build for CLI/TUI agent. Runtime for Codi

  • parallel-code by johannesjo · ⭐ 1.0k

    Run Claude Code, Codex, and Gemini side by side — each in its own git worktree

  • claude-code-apple-skills by rshankras · ⭐ 606

    Claude Code skills for Apple platform development (iOS, macOS, iPadOS) — product validation, code generation,

  • smart-ralph by tzachbon · ⭐ 536

    Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured

  • hcom by aannoo · ⭐ 431

    Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs

  • ouijit by ouijit · ⭐ 167

    Git worktree-based task manager with integrated terminals for CLI coding agents

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Swift Agent Tools

Frequently Asked Questions

What is kooky?

kooky is A minimal modern terminal for AI coding experience — Sidebar workspaces; horizontal / vertical split panes; one-click agent launch; per-agent activity readout; live workspace state with one-click Node. It is categorized as a Agent Tool with 639 GitHub stars.

What programming language is kooky written in?

kooky is primarily written in Swift. It covers topics such as agent, ai-agents, ai-coding.

How do I install or use kooky?

You can find installation instructions and usage details in the kooky GitHub repository at github.com/iAmCorey/kooky. The project has 639 stars and 36 forks, indicating an active community.

What license does kooky use?

kooky is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to kooky?

The top alternatives to kooky on Agent Skills Hub include termio, parallel-code, claude-code-apple-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools