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 HanHan666666 · Codex Skill · ★ 77
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is codebuddy2openai safe to install? View the security audit →
codebuddy2openai 把 CodeBuddy / WorkBuddy（腾讯代码助手） 的订阅，转换成 OpenAI 兼容 API，让你能在任何支持 OpenAI 协议的客户端（ZCode、Cherry Studio、NextChat、LobeChat 等）里复用它。 ⚠️ 关于 Codex CLI：新版 Codex CLI 已不再支持 ，只支持 格式，因此本工具无法直接接入 Codex CLI，请改用下方「OpenAI 兼容客户端」方案。 English · 中文文档 中文文档 一个极简的本地协议转换器（proxy / adapter）：读取你本机已登录的 CodeBuddy 桌面端凭据，把它的对话能力包装成标准的 OpenAI 、 接口。不碰登录授权、不碰你已有的客户端配置、跨平台、单文件。 ✨ 特性 🔄 OpenAI 兼容：标准 （支持流式 SSE）、、。 🛠️ Function Calling（工具调用）：支持请求里的 ，返回 OpenAI 格式的 ，可在 ZCode / Cherry Studio 等 agent 客户端里驱动工具、多轮回传结果。 🪶 单文件、极简：核心就一个 ，不复杂。 🔐 零授权改动：直接调用本机已登录的 CLI，自动复用桌面端登录态，不重新登录、不存密码。 🖥️ 跨平台：自动定位 macOS / Windows / Linux 上的 CLI 与登录文件。 🛡️ 安全：默认只监听 ；工具的声明与执行都由客户端负责，转换器只做鉴权与透传。 ⚡ 流式输出：实时增量 token，体验与原生 OpenAI 流式一致。 🧠 它是怎么工作的 ZCode / Cherry Studio / 任意 OpenAI 客户端 │ POST /v1/chat/completions (标准 OpenAI 协议，含 tools) ▼ ┌────────────────────┐ │ converter.py │ ← 本地 FastAPI 服务 (127.0.0.1:8787) │ 读 token + 注入 │ │ 鉴权 header + 透传│ └────────────────────┘ │ POST /v2/chat/completions (带 Authorization/X-User-Id 等头) ▼ ┌────────────────────────────────┐ │ copilot.tencent.com 后端 │ ← 原生标准 OpenAI 协议 │ (GLM-5.2 / Kimi / DeepSeek) │ 含原生 tools / toolcalls / SSE 流式 └─────────────────────────
| Stars | 77 |
| Forks | 18 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 65.5042425007708/100 |
| Open Issues | 5 |
| Last Updated | 2026-09-22 |
| Created | 2026-06-19 |
| Platforms | cli, codex, python |
| Est. Tokens | ~5k |
Looking for a codebuddy2openai alternative? If you're comparing codebuddy2openai 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.
WorkBuddy 国际国内多账号反代网关 — 双域独立路由与切换、稳定设备指纹防风控、国内成长任务全自动完成、后台定时调度器、Web监控看板，支持 Codex / Claude Code / DSH与标准 OpenAI
Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premi
OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch).
Bridgic is the next-generation agent development framework for building intelligent systems.
Expose agent CLIs (Codex, Cursor Agent, Claude Code, Gemini) as an OpenAI-compatible /v1 API gateway.
Dual API router (Anthropic + OpenAI compatible) for Claude MAX Plan - Use flat-rate billing with ANY AI too
Explore other popular codex skill tools:
codebuddy2openai is Convert CodeBuddy/WorkBuddy (Tencent coding assistant) subscription into an OpenAI-compatible API. Use CodeBuddy GLM-5.2/Kimi/DeepSeek models in Codex CLI or any OpenAI client. Cross-platform, single-. It is categorized as a Codex Skill with 77 GitHub stars.
codebuddy2openai is primarily written in Python. It covers topics such as api-gateway, codebuddy, codebuddy-api.
You can find installation instructions and usage details in the codebuddy2openai GitHub repository at github.com/HanHan666666/codebuddy2openai. The project has 77 stars and 18 forks, indicating an active community.
codebuddy2openai is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to codebuddy2openai on Agent Skills Hub include workbuddy2api-hub, NadirClaw, lm-proxy. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: