Project-specific skills for the CCX AI API proxy: registering new Claude and non-Claude models, checking upstream Claude Code and Codex changes, bumping versions with CHANGELOG generation, and publishing CCX Desktop Store releases.
Claude Code
$ npx -y skills add BenedictKing/ccx --agent claude-code
Codex
$ npx skills add BenedictKing/ccx -a codex
Cursor
$ npx skills add BenedictKing/ccx -a cursor
Gemini CLI
$ npx skills add BenedictKing/ccx -a gemini-cli
GitHub Copilot
$ npx skills add BenedictKing/ccx -a github-copilot
OpenCode
$ npx skills add BenedictKing/ccx -a opencode
Windsurf
$ npx skills add BenedictKing/ccx -a windsurf
English | 简体中文
CCX is a high-performance AI API proxy and protocol translation gateway for Claude, OpenAI Chat, OpenAI Images, OpenAI Embeddings, Codex Responses, and Gemini. It provides a unified entrypoint, built-in web administration, channel orchestration, failover, multi-key management, and model routing.
PROXY_ACCESS_KEY and optional ADMIN_ACCESS_KEYVisual channel management with drag-and-drop priority adjustment and real-time health monitoring.
Supports multiple upstream service types and flexible API key, model mapping, and request parameter configuration.
Real-time monitoring of per-channel request traffic, success rate, and latency.
CCX exposes one backend entrypoint:
Client -> backend :3000 ->
|- / -> Web UI
|- /api/* -> Admin API
|- /v1/messages -> Claude Messages proxy
|- /v1/chat/completions -> OpenAI Chat proxy
|- /v1/responses -> Codex Responses proxy
|- /v1/images/{...} -> OpenAI Images proxy
|- /v1/embeddings -> OpenAI Embeddings proxy
|- /v1/models -> Models API
`- /v1beta/models/* -> Gemini proxy
Images endpoints currently include:
POST /v1/images/generationsPOST /v1/images/editsPOST /v1/images/variationsSee ARCHITECTURE.md for the detailed design.
CCX Desktop provides a native desktop experience with GUI for managing channels, keys, and agent configuration.
| Platform | Install Method | Notes |
|---|---|---|
| Windows | Search CCX Desktop in Microsoft Store | Recommended. Auto-update, no manual signing. Also available as setup.exe from GitHub Releases. |
| macOS | brew tap BenedictKing/ccx && brew install --cask ccx-desktop | Or download .dmg (arm64/amd64) from GitHub Releases. |
| Linux | Download .AppImage from GitHub Releases | Mark as executable and run. |
See CCX Desktop Guide for detailed setup instructions.
.env file next to the binary:PROXY_ACCESS_KEY=your-proxy-access-key
PORT=3688
ENABLE_WEB_UI=true
APP_UI_LANGUAGE=en
http://localhost:3000On Windows, if the client runs from cmd, PowerShell, WSL, or Docker and localhost does not reach CCX, use the Windows host IPv4 address instead, for example http://192.168.1.23:3000. When BIND_HOST is empty, CCX listens on all interfaces by default through :PORT; set BIND_HOST=127.0.0.1 for local-only access.
For background startup without Docker, see Service Startup.
docker run -d \
--name ccx \
-p 3000:3000 \
-e PROXY_ACCESS_KEY=your-proxy-access-key \
-e APP_UI_LANGUAGE=en \
-v $(pwd)/.config:/app/.config \
crpi-i19l8zl0ugidq97v.cn-hangzhou.personal.cr.aliyuncs.com/bene/ccx:latest
Run in the background with Docker Compose:
docker compose up -d
Enable Watchtower auto-update:
docker compose -f docker-compose.yml -f docker-compose.watchtower.yml up -d
Pull the latest image immediately after setup if needed:
docker compose pull ccx
docker compose up -d ccx
Prerequisites: Go 1.25+, Bun, and Make (macOS: xcode-select --install).
git clone https://github.com/BenedictKing/ccx
cd ccx
cp backend-go/.env.example backend-go/.env
make install # install all dependencies (frontend + Go modules + dev tools)
make run
Useful commands:
make dev
make run
make build
make frontend-dev
PORT=3688
ENV=production
ENABLE_WEB_UI=true
PROXY_ACCESS_KEY=your-proxy-access-key
ADMIN_ACCESS_KEY=your-admin-secret-key
APP_UI_LANGUAGE=en
LOG_LEVEL=info
GET /GET /health/api/*POST /v1/messagesPOST /v1/chat/completionsPOST /v1/responsesPOST /v1/images/generations, POST /v1/images/edits, POST /v1/images/variationsPOST /v1/embeddingsPOST /v1beta/models/{model}:generateContentGET /v1/modelsRecommended local workflow:
make dev
Frontend only:
cd "frontend"
bun install
bun run dev
Backend only:
cd "backend-go"
make dev
Join the QQ group for discussion: 642217364
MIT
Stars on GitHub
A development methodology for coding agents that makes the agent brainstorm before building, follow plans, run parallel work and finish branches in a disciplined way. You get fewer skipped steps and more consistent results from your coding assistant.
@obraHelps you take a change from a rough idea or bug report through to a tested, reviewed result, with each step handled by a focused skill. Its skills cover pinning down domain terms, designing module interfaces, diagnosing hard bugs, and reviewing changes against your repo's coding standards.
@mattpocockGives your coding agent a planning, testing and review routine to follow on every task. It plans before building, checks changes with tests, has a fresh reviewer look for regressions, and saves repeated wins as reusable skills.
@affaan-mDeveloper tools for working on the React codebase itself. Provides skills for extracting error messages, managing and debugging feature flags across release channels, running Flow type checks, and fixing lint and formatting issues before committing.
@facebookInstall it with the command on its page. It includes model-update, store-update, upstream-check. Its skills do not fire on their own yet. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it