codex-lb
Codex/ChatGPT multiple account load balancer & proxy with usage tracking, dashboard, and OpenCode-compatible endpoints
What is codex-lb?
Codex/ChatGPT multiple account load balancer & proxy with usage tracking, dashboard, and OpenCode-compatible endpoints
Overview of codex-lb
What it is
codex-lb is a load balancer and proxy for multiple ChatGPT accounts. It pools accounts, tracks usage per account, manages API keys, and provides a dashboard. It also exposes endpoints compatible with OpenAI clients such as Codex CLI and OpenCode. The project is open source and licensed under MIT.
Key features
- Account pooling: load balance across multiple ChatGPT accounts - Usage tracking: per-account tokens, cost, and 28-day trends - API keys: per-key rate limits by token, cost, window, and model - Dashboard authentication: password plus optional TOTP - OpenAI-compatible endpoints: works with Codex CLI, OpenCode, and any OpenAI client - Auto model sync: available models are fetched from upstream
Use cases
codex-lb is suitable for users who need to distribute requests across several ChatGPT accounts to avoid rate limits or manage costs. It can be used with OpenAI-compatible tools like Codex CLI, OpenCode, OpenClaw, Hermes Agent, and the OpenAI Python SDK. The dashboard provides visibility into account usage and API key management.
Getting started
bash # Docker (recommended) docker volume create codex-lb-data docker network inspect codex-lb-net >/dev/null 2>&1 || docker network create codex-lb-net docker run -d --name codex-lb --network codex-lb-net -p 2455:2455 -p 1455:1455 -v codex-lb-data:/var/lib/codex-lb ghcr.io/soju06/codex-lb:latest # or uvx uvx codex-lb # or nix nix run github:Soju06/codex-lb Open localhost:2455 → Add account → Done. For remote dashboard access, a one-time bootstrap token is required.
License and pricing
The project is open source and licensed under MIT. Pricing is not stated beyond the open source license.
Based on the project's public README and repository metadata.