CliRelay — security grade SAFE, quality 60/100

Security audit verdict: SAFE · quality 60/100

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 kittors · Codex Skill · ★ 1.0k

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

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

About CliRelay

🔀 CliRelay A unified proxy server for AI CLI tools — use your existing subscriptions with any OpenAI / Gemini / Claude / Codex compatible client. Multi-tenant web panel · request logs & quotas · routing groups & failover · self-hosted English | 中文 📖 Docs · 🖥️ Management Panel · 🐛 Report Bug · ✨ Request Feature ⚡ What is CliRelay? ✨ Heavily enhanced fork of the CLIProxyAPI project — rebuilt with a production-grade management layer, web control pa

ai-gatewayanthropicapi-gatewayclaude-codegemini-cligollmllm-proxymulti-tenantopenai

Quick Facts

Stars1,021
Forks122
LanguageGo
CategoryCodex Skill
LicenseMIT
Quality Score59.5699057193444/100
Open Issues16
Last Updated2026-09-19
Created2026-02-27
Platformsbrowser, claude-code, cli, codex, gemini, go
Est. Tokens~23k

Compatible Skills

These tools work well together with CliRelay for enhanced workflows:

  • keirouter — semantic(0.31)+complementary+shared_fw(openai)+same_lang+similar_pop+shared_platform (69%)
  • JoyCodeProxy — semantic(0.29)+complementary+shared_fw(openai)+same_lang+similar_pop+shared_platform (68%)
  • JoyCode2Api — semantic(0.29)+complementary+shared_fw(openai)+same_lang+similar_pop+shared_platform (68%)
  • bifrost — semantic(0.28)+complementary+shared_fw(openai)+same_lang+similar_pop+shared_platform (68%)
  • ccNexus — semantic(0.26)+complementary+shared_fw(openai)+same_lang+similar_pop+shared_platform (67%)

CliRelay alternative? Top 6 similar tools

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

  • ccproxy by starbaser · ⭐ 350

    Build mods for Claude Code: Hook any request, modify any response, /model "with-your-custom-model", intelligen

  • octopus by bestruirui · ⭐ 2.6k

    One Hub All LLMs For You | 为个人打造的 LLM API 聚合网关

  • llmgateway by theopenco · ⭐ 1.6k

    Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

  • coderunner by instavm · ⭐ 882

    A local sandbox for your AI agents

  • NadirClaw by NadirRouter · ⭐ 655

    Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premi

  • dario by askalf · ⭐ 541

    Use your Claude and ChatGPT subscriptions in Cursor, Cline, Aider, Claude Code and the Agent SDK — at subscrip

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Go Agent Tools

Frequently Asked Questions

What is CliRelay?

CliRelay is Self-hosted AI gateway for coding CLIs — one OpenAI/Claude/Gemini/Codex-compatible endpoint, with a multi-tenant web console, request logs, and spend quotas.. It is categorized as a Codex Skill with 1.0k GitHub stars.

What programming language is CliRelay written in?

CliRelay is primarily written in Go. It covers topics such as ai-gateway, anthropic, api-gateway.

How do I install or use CliRelay?

You can find installation instructions and usage details in the CliRelay GitHub repository at github.com/kittors/CliRelay. The project has 1.0k stars and 122 forks, indicating an active community.

What license does CliRelay use?

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

What are the best alternatives to CliRelay?

The top alternatives to CliRelay on Agent Skills Hub include ccproxy, octopus, llmgateway. 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