openyak — 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 openyak · Codex Skill · ★ 708

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

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

About openyak

OpenYak OpenYak is an open-source local AI agent that runs entirely on your desktop. It connects to 100+ models from 20+ providers, manages your files, and automates workflows — all without your data ever leaving your machine. ##

acpagentagent-client-protocolagentic-aiai-agentclaude-codecodexdesktop-applicationelectronlocal-first

Quick Facts

Stars708
Forks61
LanguageTypeScript
CategoryCodex Skill
LicenseApache-2.0
Quality Score62.7948066543742/100
Open Issues9
Last Updated2026-09-05
Created2026-03-20
Platformsclaude-code, cli, codex, node
Est. Tokens~15k

Compatible Skills

These tools work well together with openyak for enhanced workflows:

  • get-physics-done — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)
  • Agently-Daily-News-Collector — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)
  • skillkit — semantic(0.15)+complementary+same_lang+similar_pop+shared_platform (55%)
  • bondai — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (51%)
  • CQAsk — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (51%)

openyak alternative? Top 6 similar tools

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

  • opentag by amplifthq · ⭐ 1.4k

    Mention any ACP coding agent from Slack, GitHub, GitLab, Linear, or Lark. OpenTag runs Claude Code, Codex, Cur

  • claw-orchestrator by Enderfga · ⭐ 571

    Run Claude Code, Codex, Antigravity, Cursor Agent and OpenCode as one runtime — persistent sessions, multi-age

  • OpenACP by Open-ACP · ⭐ 378

    Self-hosted bridge that lets you interact with AI coding agents (Claude Code, Codex, etc.) from messaging plat

  • bitrouter by bitrouter · ⭐ 226

    The context-aware model router that learns & adapts to your long-horizon coding agent workflows. Lightweight &

  • codeg by xintaofei · ⭐ 3.4k

    Collaborative multi-agent AI coding workspace: aggregate sessions from Claude Code, Codex, OpenCode, Pi, Grok

  • skills-hub by qufei1993 · ⭐ 1.7k

    A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ gl

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is openyak?

openyak is One chat. Every agent. A universal interface for AI agents running on your computer.. It is categorized as a Codex Skill with 708 GitHub stars.

What programming language is openyak written in?

openyak is primarily written in TypeScript. It covers topics such as acp, agent, agent-client-protocol.

How do I install or use openyak?

You can find installation instructions and usage details in the openyak GitHub repository at github.com/openyak/openyak. The project has 708 stars and 61 forks, indicating an active community.

What license does openyak use?

openyak is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to openyak?

The top alternatives to openyak on Agent Skills Hub include opentag, claw-orchestrator, OpenACP. 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