clay — 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 chadbyte · Codex Skill · ★ 399

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

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

About clay

Multiplayer Claude Code and Codex. Drop into a teammate's session live. Or pair with AI mates that remember and push back. Self-hosted, one toggle between vendors. The browser tab your whole team lives in. Humans, AI agents, projects, sessions, decisions. Afraid of locking your personal or team knowledge into one vendor? With Clay, your conventions, sessions, and decisions live on your disk. Switch when you want. A team-shared, self-hosted GUI for Claude Code and Codex CLIs. What's Clay? A browser-based workspace for Claude Code and Codex. Open it on any device, alone or with your whole team. A place where your

ai-agentai-agentsai-teamautomationclaudeclaude-agent-sdkclaude-codecodexcollaborationdev-tools

Quick Facts

Stars399
Forks55
LanguageJavaScript
CategoryCodex Skill
LicenseAGPL-3.0
Quality Score66.7840062361572/100
Open Issues2
Last Updated2026-09-22
Created2026-02-09
Platformsbrowser, claude-code, codex, node
Est. Tokens~16k

Compatible Skills

These tools work well together with clay for enhanced workflows:

  • cui — semantic(0.56)+complementary+rare_topics+similar_pop+shared_platform (59%)
  • everything-claude-code-zh — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (52%)
  • agent-infra — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (51%)

clay alternative? Top 6 similar tools

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

  • Overture by SixHq · ⭐ 641

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • garcon by cfal · ⭐ 86

    Self-hosted browser workspace to run coding agents in parallel, steer work as it runs, review diffs, and ship.

  • claude-elixir-phoenix by oliver-kriska · ⭐ 556

    Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP

  • smart-ralph by tzachbon · ⭐ 544

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

  • sandboxed.sh by Th0rgal · ⭐ 513

    Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

  • better-agent-terminal by tony1223 · ⭐ 513

    Multi-workspace terminal aggregator with Claude Code AI integration

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is clay?

clay is A self-hosted workspace where people and coding agents work together across projects, sessions, and providers.. It is categorized as a Codex Skill with 399 GitHub stars.

What programming language is clay written in?

clay is primarily written in JavaScript. It covers topics such as ai-agent, ai-agents, ai-team.

How do I install or use clay?

You can find installation instructions and usage details in the clay GitHub repository at github.com/chadbyte/clay. The project has 399 stars and 55 forks, indicating an active community.

What license does clay use?

clay 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 clay?

The top alternatives to clay on Agent Skills Hub include Overture, garcon, claude-elixir-phoenix. 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