# Soju06/codex-lb

Codex/ChatGPT multiple account load balancer & proxy with usage tracking, dashboard, and OpenCode-compatible endpoints

Repository: https://github.com/Soju06/codex-lb
Canonical: https://ross.abutalabs.com/products/codex-lb
Homepage: https://soju06.github.io/codex-lb/
Language: Python
License: MIT
License Family: permissive
Topics: api-proxy, chatgpt, codex, dashboard, fastapi, load-balancer, oauth, openai, python, rate-limit, sqlalchemy, usage-tracking, opencode, multiple-accounts, openclaw
Last push: 2026-08-26T10:07:13+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 17
- inputs: {"age_days": 238, "days_push": 7, "days_rel": 7, "gap_med": 1.0, "n_releases_24m": 61}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2867, forks 427 (observed 2026-08-28T04:07:26.397971+00:00)

## What it is
A self-hosted load balancer and proxy for ChatGPT/Codex accounts that pools multiple accounts behind OpenAI-compatible endpoints. It includes usage tracking, per-key rate limits, API key management, and a web dashboard with password/TOTP auth.

## Use cases
- pool multiple ChatGPT accounts behind one proxy endpoint
- load balance Codex CLI requests across accounts
- track token usage and cost per account
- set per-key rate limits by token, cost, window, or model
- use OpenCode or any OpenAI-compatible client with pooled accounts
- self-host a dashboard for monitoring account quotas

## When to choose
- you have multiple ChatGPT/Codex accounts and want to distribute requests across them
- you need usage and cost tracking per account with a web dashboard
- you want OpenAI-compatible endpoints for Codex CLI, OpenCode, or other clients
- you want per-key rate limiting and API key management for a shared proxy

## When to avoid
- you only have a single ChatGPT account and no need for pooling
- you need a general-purpose LLM gateway for arbitrary providers beyond OpenAI/ChatGPT
- you cannot self-host a service or run Docker/uvx

## Facets
- artifact type: service
- maturity: active
- function: proxy, api-gateway, load-testing, monitoring, auth, rate-limiting
- domain: large-language-models, self-hosted, developer-tools, apis
- platform: self-hosted, python, cli
- tags: chatgpt, codex, opencode, account-pooling, usage-tracking, openai-compatible, fastapi, api-keys, totp, dashboard, ai-agents, docker, web-server

## Member repositories
- Soju06/codex-lb (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:26.397971+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:36:04.891103+00:00, confidence not recorded.
  - readme: https://github.com/Soju06/codex-lb (fetched 2026-08-28T04:07:26.397971+00:00, sha 4e8c6376fe67)
  - homepage: https://soju06.github.io/codex-lb/ (fetched 2026-08-29T09:51:43.059303+00:00, sha dcbe3d799543)
- Data as of 2026-08-30T08:39:29.467469+00:00.