launchdock — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

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 nghyane · Codex Skill · ★ 330

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

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

About launchdock

launchdock Use Claude and GPT across AI coding tools through one local gateway, with both OpenAI-compatible and Claude-native API surfaces. gives you one local endpoint for tools like OpenCode, Codex, Claude Code, Droid, and Pi. Why people use it: use OpenCode or Codex with the accounts you already have use Claude through either OpenAI-compatible chat clients or the native Claude Messages API avoid managing separate credentials and configs everywhere log in once and reuse managed auth across multiple tools push managed auth to a personal server when needed Install Optional: Quickstart bash launchdock auth login claude launchdock auth login openai launchdock auth list launchdock start laun

ai-toolsanthropicclaudecodexgptlocal-gatewayopenai-compatibleproxy

Quick Facts

Stars330
Forks93
LanguageGo
CategoryCodex Skill
LicenseMIT
Quality Score69.5864181543589/100
Open Issues9
Last Updated2026-05-01
Created2025-12-09
Platformsclaude-code, codex, go
Est. Tokens~4674k

Compatible Skills

These tools work well together with launchdock for enhanced workflows:

  • ccNexus — semantic(0.17)+complementary+shared_fw(openai)+same_lang+similar_pop+shared_platform (59%)
  • llmapibenchmark — semantic(0.17)+complementary+shared_fw(openai)+same_lang+similar_pop+shared_platform (59%)
  • skillboss-skills — semantic(0.23)+complementary+shared_fw(openai)+similar_pop+shared_platform (56%)
  • NadirClaw — semantic(0.21)+complementary+shared_fw(openai)+similar_pop+shared_platform (55%)
  • bifrost — semantic(0.18)+complementary+shared_fw(openai)+same_lang+shared_platform (54%)

launchdock alternative? Top 6 similar tools

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

  • ocp by dtzp555-max · ⭐ 121

    Turn your Claude Pro/Max subscription into an OpenAI-compatible API for your IDEs and devices — LAN auth, per-

  • claude-delegator by jarrodwatts · ⭐ 1.0k

    Delegate tasks to Codex and Gemini directly from within Claude Code.

  • UnrealClaude by Natfii · ⭐ 880

    Claude Code CLI integration for Unreal Engine 5.7 - Get AI coding assistance with built-in UE5.7 documentation

  • mcp-nixos by utensils · ⭐ 823

    MCP-NixOS - Model Context Protocol Server for NixOS resources

  • tokentap by jmuncor · ⭐ 814

    Intercept LLM API traffic and visualize token usage in a real-time terminal dashboard. Track costs, debu

  • Overture by SixHq · ⭐ 641

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

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Go Agent Tools

Frequently Asked Questions

What is launchdock?

launchdock is Use Claude and GPT through one local gateway with OpenAI-compatible and Claude-native APIs.. It is categorized as a Codex Skill with 330 GitHub stars.

What programming language is launchdock written in?

launchdock is primarily written in Go. It covers topics such as ai-tools, anthropic, claude.

How do I install or use launchdock?

You can find installation instructions and usage details in the launchdock GitHub repository at github.com/nghyane/launchdock. The project has 330 stars and 93 forks, indicating an active community.

What license does launchdock use?

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

What are the best alternatives to launchdock?

The top alternatives to launchdock on Agent Skills Hub include ocp, claude-delegator, UnrealClaude. 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