hive — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 tt-a1i · Codex Skill · ★ 552

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

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

About hive

Hive Hive 是浏览器里的 Agent 协作工作台——一群 Agent 在你本机各自开工,一个当 Orchestrator 派活、归总进展,其余各司其职。 Orchestrator 本身就是一个真实的 / / / / / / 进程——不是你、也不是脚本——它派单的 Worker 同样是真 CLI agent。所有 agent 都是本机真实的 PTY 进程,通过 Hive 注入到 shell 里的小型 协议互相通信,共享 这份 markdown 任务图。 写代码、做调研、起草文档、做翻译——凡是能拆给一群人协作的脑力活,都可以让一群 Agent 合伙干。 -lightgrey.svg) 🌐 官网:hivehq.dev(English) English · 简体中文 Hive 是本机优先的工具,只监听 ,面向已经在用 CLI Agent 的人。最新稳定版本见 npm,上面的 badge 会指向它。 本仓库是 Hive 的公开源码基线。面

agent-orchestrationai-agentsclaude-codeclicodexcoding-agentdeveloper-toolslocal-firstmulti-agentnodejs

Quick Facts

Stars552
Forks68
LanguageTypeScript
CategoryCodex Skill
Quality Score62.6912117651446/100
Open Issues32
Last Updated2026-09-28
Created2026-04-19
Platformsbrowser, claude-code, cli, codex, gemini, node
Est. Tokens~16k

Compatible Skills

These tools work well together with hive for enhanced workflows:

  • codex-collab — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (58%)
  • Cliclaw — semantic(0.30)+complementary+same_lang+similar_pop+shared_platform (56%)

hive alternative? Top 6 similar tools

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

  • happier by happier-dev · ⭐ 1.8k

    Web, Desktop & Mobile client and orchestrator for Codex, Claude Code, OpenCode, Pi, Cursor, Grok, Antigravity,

  • SWE-AF by Agent-Field · ⭐ 1.0k

    Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a

  • maestro by ReinaMacCredy · ⭐ 232

    Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f

  • takt by nrslib · ⭐ 1.4k

    TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets reco

  • golembot by 0xranx · ⭐ 322

    Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Disco

  • orchestkit by yonatangross · ⭐ 286

    The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is hive?

hive is Browser-native hive-mind for CLI coding agents — Claude Code, Codex, Gemini, and OpenCode collaborate as real PTY processes via a team protocol.. It is categorized as a Codex Skill with 552 GitHub stars.

What programming language is hive written in?

hive is primarily written in TypeScript. It covers topics such as agent-orchestration, ai-agents, claude-code.

How do I install or use hive?

You can find installation instructions and usage details in the hive GitHub repository at github.com/tt-a1i/hive. The project has 552 stars and 68 forks, indicating an active community.

What are the best alternatives to hive?

The top alternatives to hive on Agent Skills Hub include happier, SWE-AF, maestro. 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 Codex Skill tools