kanvibe — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by rookedsysc · Agent Tool · ★ 142

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

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

About kanvibe

KanVibe Keyboard-first Kanban workspace for AI coding agents KanVibe keeps AI coding work out of scattered terminal tabs. Track branch-based tasks on a real-time Kanban board, open each task's tmux/zellij session in the browser or desktop app, and let Claude Code, Gemini CLI, Codex CLI, and OpenCode hooks move tasks through the workflow automatically. Use shortcuts for project filters, task search, notifications, task detail panels, and common task actions without losing terminal focus. Buying me a coffee is nice, but honestly? A contribution would make my day even more. :) KO | ZH Main Kanban board Task detail workspace AI usage — remaini

ai-agentclaude-codedeveloper-toolsgit-worktreekanbanself-hostedtask-managementterminalterminal-multiplexertmux

Quick Facts

Stars142
Forks17
LanguageTypeScript
CategoryAgent Tool
LicenseAGPL-3.0
Quality Score67.46716835297/100
Open Issues2
Last Updated2026-09-20
Created2026-02-10
Platformsclaude-code, node
Est. Tokens~19k

Compatible Skills

These tools work well together with kanvibe for enhanced workflows:

  • agent-kanban — semantic(0.25)+complementary+rare_topics+same_lang+similar_pop+shared_platform (68%)
  • Claude-Code-Kanban-Automator — semantic(0.30)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)

kanvibe alternative? Top 6 similar tools

Looking for a kanvibe alternative? If you're comparing kanvibe 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.

  • termcanvas by blueberrycongee · ⭐ 379

    An infinite canvas desktop app for visually managing terminals

  • honeymux by honeymux · ⭐ 83

    All of your agents, shells, and TUIs in one durable terminal workspace

  • purplemux by subicura · ⭐ 58

    A web-native terminal multiplexer for Claude Code & Codex — monitor and manage multiple sessions from any brow

  • wmux by openwong2kim · ⭐ 396

    Run Claude Code, Codex & Gemini in parallel on Windows & macOS — git worktree fan-out with atomic hunk adoptio

  • seance by no1msd · ⭐ 133

    A scrolling terminal multiplexer that tracks your AI coding agents.

  • tortie by gregce · ⭐ 85

    A calm agent multiplexer with familiar IDE features, for macOS.

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is kanvibe?

kanvibe is Keyboard-first desktop Kanban workspace for AI coding agents with embedded terminals, git worktrees, and hook-driven task tracking.. It is categorized as a Agent Tool with 142 GitHub stars.

What programming language is kanvibe written in?

kanvibe is primarily written in TypeScript. It covers topics such as ai-agent, claude-code, developer-tools.

How do I install or use kanvibe?

You can find installation instructions and usage details in the kanvibe GitHub repository at github.com/rookedsysc/kanvibe. The project has 142 stars and 17 forks, indicating an active community.

What license does kanvibe use?

kanvibe is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to kanvibe?

The top alternatives to kanvibe on Agent Skills Hub include termcanvas, honeymux, purplemux. 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