#50 · Primary category： AI Gateway & API Infrastructure
codex-lb
Codex/ChatGPT multiple account load balancer & proxy with usage tracking, dashboard, and OpenCode-compatible endpoints
Project last updated：08/29/26
GitHub Stars
2.9K
Forks
427
Contributors
108
License
MIT
Why we included this project
Running an OpenAI-compatible client like Codex CLI or OpenCode against a single ChatGPT account usually means hitting rate limits sooner or later. codex-lb sits between your clients and a pool of ChatGPT accounts, spreading requests across them so one account's quota doesn't cap the whole team. It speaks the standard OpenAI API, so existing tools connect with just a base URL change. The dashboard shows per-account token use and cost over 28 days, and API keys can carry their own rate limits by token, cost, window, or model, which helps when several people or agents share one proxy. Deployment is Docker or uvx, with SQLite by default and PostgreSQL as an option, so a small team can have it running in an afternoon.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
OmniRoute
Open-source AI gateway: one endpoint, 290+ providers (90+ free), 500+ models, auto-fallback, token compression, MCP/A2A, works with Claude Code, Codex, Cursor, Cline, Copilot.
CLIProxyAPI
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.6 Series, Grok 4.5, Claude model through API
kong
🦍 The API and AI Gateway
novu
The open-source communication infrastructure for agents and products
GPT_API_free
Free API for large models, supports GPT, DeepSeek, etc., 10k free points daily, paid plans at 10-20% of official price.