agent-cli-to-api — 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 leeguooooo · Codex Skill · ★ 70

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

🔒 Is agent-cli-to-api safe to install? View the security audit →

About agent-cli-to-api

agent-cli-to-api Expose popular agent CLIs as a small OpenAI-compatible HTTP API (). Works great as a local gateway (localhost) or behind a reverse proxy. Think of it as LiteLLM for agent CLIs: you point existing OpenAI SDKs/tools at , and choose a backend by . Supported backends: OpenAI Codex - defaults to backend for vision and image generation (DALL-E / -class output); falls back to Cursor Agent - via CLI Claude Code - via CLI or direct API (auto-detects config) Gemini - via CLI or CloudCode direct (set ) Why this exists: Many tools/SDKs only speak the OpenAI API () - this lets you plug agent CLIs into that ecosystem. One gateway, multiple CLIs: pick a backend by (with optional prefixes like / / ). Expose your ChatGPT Plus / Pro subscription's image generation as an HTTP API. No required — the gateway reuses the OAuth token from , lets you call via plain chat completions, and returns the PNG inline (data URI). See Image generation (ChatGPT subscription). Table of Contents Requirements Install Run (No Needed) Core Configuration API [Im

agentchat-completionsclaude-codeclicodexcursor-agentfastapigatewaygeminiopenai-api

Quick Facts

Stars70
Forks20
LanguagePython
CategoryCodex Skill
Quality Score69.9115499936331/100
Last Updated2026-07-28
Created2025-12-15
Platformsclaude-code, cli, codex, gemini, python
Est. Tokens~18k

agent-cli-to-api alternative? Top 6 similar tools

Looking for a agent-cli-to-api alternative? If you're comparing agent-cli-to-api 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.

  • ClaudeR by IMNMV · ⭐ 337

    Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automa

  • NadirClaw by doramirdor · ⭐ 336

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

  • copilot-tunnel-proxy by noviaidrl · ⭐ 120

    GitHub Copilot as Local AI API Bridge for Claude Code 2026

  • ocp by dtzp555-max · ⭐ 113

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

  • UniClaudeProxy by vibheksoni · ⭐ 59

    Use any LLM with Claude Code — proxy that translates Anthropic API to OpenAI, Gemini, DeepSeek, Ollama, and mo

  • postman-mcp-server by postmanlabs · ⭐ 316

    Postman MCP Server — connect AI agents (Claude Code, Cursor, VS Code Copilot, Gemini CLI) to your Postman coll

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is agent-cli-to-api?

agent-cli-to-api is Expose agent CLIs (Codex, Cursor Agent, Claude Code, Gemini) as an OpenAI-compatible /v1 API gateway.. It is categorized as a Codex Skill with 70 GitHub stars.

What programming language is agent-cli-to-api written in?

agent-cli-to-api is primarily written in Python. It covers topics such as agent, chat-completions, claude-code.

How do I install or use agent-cli-to-api?

You can find installation instructions and usage details in the agent-cli-to-api GitHub repository at github.com/leeguooooo/agent-cli-to-api. The project has 70 stars and 20 forks, indicating an active community.

What are the best alternatives to agent-cli-to-api?

The top alternatives to agent-cli-to-api on Agent Skills Hub include ClaudeR, NadirClaw, copilot-tunnel-proxy. 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