ccLoad
Self-hosted AI API gateway for Claude Code, Codex and Gemini: pool API keys and subscription accounts behind one endpoint with failover, protocol conversion and
What is ccLoad?
Self-hosted AI API gateway for Claude Code, Codex and Gemini: pool API keys and subscription accounts behind one endpoint with failover, protocol conversion and cost tracking.
Overview of ccLoad
What it is
ccLoad is a self-hosted AI API gateway for Claude Code, Codex, Gemini, and OpenAI-compatible clients. It pools multiple upstream AI sources—such as official API keys, third-party relay services, and subscription accounts—behind a single endpoint. The gateway provides failover, protocol conversion, and cost tracking. Clients only need the ccLoad address and a ccLoad token; they never see the real upstream keys.
Key features
- Pools API keys and subscription accounts (Codex/ChatGPT, Claude, Antigravity, xAI, CodeBuddy, Z.ai Coding Plan, Cursor, Zed) behind one endpoint - Automatic failover: if one upstream fails or quota runs out, ccLoad retries the next channel - Protocol conversion between different AI providers - Cost tracking and usage logging for every request - Admin console (web UI) for managing channels, API tokens, and viewing logs - Channel management with priorities, health-based ordering, scheduled checks, CSV import/export - API tokens with model, budget, and concurrency limits
Use cases
- Developers with several AI subscriptions: combine ChatGPT, Claude, and other plans with spare API keys so Claude Code and Codex keep running when one quota runs out - Teams sharing model access: give each teammate a token with limits; upstream credentials stay in one place and can be revoked at any time - Operators running many channels: manage channels with priorities, health checks, and detailed logs
Getting started
Docker (recommended): bash docker run -d --name ccload -p 8080:8080 -e CCLOAD_PASS=your_admin_password -v ccload_data:/app/data ghcr.io/caidaoli/ccload:latest Docker Compose: bash curl -o docker-compose.yml https://raw.githubusercontent.com/caidaoli/ccLoad/master/docker-compose.yml curl -o .env https://raw.githubusercontent.com/caidaoli/ccLoad/master/.env.docker.example # Edit .env and set CCLOAD_PASS to your admin password docker compose up -d Homebrew (macOS / Linux): bash brew tap caidaoli/ccload https://github.com/caidaoli/ccLoad.git brew install caidaoli/ccload/ccload mkdir -p $(brew --prefix)/var/ccload cd $(brew --prefix)/var/ccload (umask 077; touch .env) ${EDITOR:-vi} .env brew services start caidaoli/ccload/ccload Download binary: get the file for your platform from Releases. On Linux: bash chmod +x ccload-linux-amd64 CCLOAD_PASS=your_admin_password ./ccload-linux-amd64 After starting, open http://localhost:8080/web/ and sign in with the admin password. Then add channels and create API tokens. Point your clients at http://localhost:8080 with the token.
License and pricing
The license is MIT. The project is open source and free.
Based on the project's public README and repository metadata.