Skip to main content Skills Marketplace Descubre y explora habilidades de IA creadas por la comunidad.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Mostrar detalles del prompt Un comando directo omite el prompt de revisión. Revisa el origen antes de ejecutarlo.
npx skills add https://github.com/Aradotso/codex-skills --skill codex-lb-load-balancerEl comando permanece en una sola línea. Desplázate horizontalmente para revisarlo antes de copiarlo.
¿Prefieres una copia local? Descarga los archivos que SkillsMP tiene disponibles ahora.
Descargar Zip Descargando... Ocupaciones relacionadas SOC
Basado en la clasificación ocupacional SOC
name codex-lb-load-balancer description ChatGPT/Codex multi-account load balancer with usage tracking, API key management, and OpenAI-compatible proxy triggers ["set up codex load balancer for multiple accounts","configure chatgpt account pooling","track openai api usage across accounts","manage api keys with rate limits","deploy codex-lb with docker","balance load across multiple chatgpt accounts","set up openai compatible proxy","monitor chatgpt usage and costs"]
codex-lb Load Balancer
Skill by ara.so — Codex Skills collection.
Overview
codex-lb is a load balancer and proxy for ChatGPT/Codex accounts that pools multiple OpenAI accounts, tracks usage per account and API key, enforces rate limits, and provides a web dashboard for management. It exposes OpenAI-compatible endpoints (/v1/* and /backend-api/codex/*) for any client (Codex CLI, OpenCode, OpenClaw, OpenAI SDK).
Key features:
Pool multiple ChatGPT accounts with automatic load balancing
Per-account usage tracking (tokens, cost, 28-day trends)
API key management with per-key rate limits (token, cost, time window, model)
Dashboard with password + optional TOTP authentication
Auto-sync available models from upstream
WebSocket support for native Codex streaming
Installation
Docker (Recommended)
docker volume create codex-lb-data
docker run -d --name codex-lb \
-p 2455:2455 -p 1455:1455 \
-v codex-lb-data:/var/lib/codex-lb \
ghcr.io/soju06/codex-lb:latest
uvx (Python)
OpenAI v1: http://localhost:2455/v1
Codex backend: http://localhost:2455/backend-api/codex
Health check: http://localhost:1455/health
Configuration
First-Run Setup (Remote Access) When accessing the dashboard remotely for the first time, you need a bootstrap token to set the password.
Auto-generated token (default):
Open dashboard → enter token + new password → done.
docker run -d --name codex-lb \
-e CODEX_LB_DASHBOARD_BOOTSTRAP_TOKEN=your-secret-token \
-p 2455:2455 -p 1455:1455 \
-v codex-lb-data:/var/lib/codex-lb \
ghcr.io/soju06/codex-lb:latest
Local access (localhost) bypasses bootstrap entirely.
Adding Accounts
Open dashboard → Accounts → Add Account
Paste OpenAI session token or login credentials
Account syncs available models automatically
API Key Authentication API key auth is disabled by default . Enable in Settings → API Key Auth when:
Clients connect remotely
Running in Docker/VM/container with non-local networking
When enabled, clients must pass a Bearer token:
Authorization: Bearer sk-clb-YOUR_KEY_HERE
Create API keys in dashboard → API Keys → Create Key .
Configure rate limits per key:
Token limit (per window)
Cost limit (USD, per window)
Time window (e.g., 1 hour, 1 day)
Allowed models
Environment Variables Variable Default Description CODEX_LB_DASHBOARD_BOOTSTRAP_TOKENauto-generated Bootstrap token for first-run password setup CODEX_LB_UPSTREAM_STREAM_TRANSPORTautoauto, websocket, or http for Codex streamingCODEX_LB_UPSTREAM_WEBSOCKET_TRUST_ENVfalseUse environment proxies for WebSocket handshakes CODEX_LB_DATA_DIR/var/lib/codex-lbData directory for SQLite DB and state
Client Configuration
Codex CLI model = "gpt-5.3-codex"
model_reasoning_effort = "xhigh"
model_provider = "codex-lb"
[model_providers.codex-lb]
name = "OpenAI"
base_url = "http://127.0.0.1:2455/backend-api/codex"
wire_api = "responses"
supports_websockets = true
requires_openai_auth = true
[model_providers.codex-lb]
name = "OpenAI"
base_url = "http://127.0.0.1:2455/backend-api/codex"
wire_api = "responses"
env_key = "CODEX_LB_API_KEY"
supports_websockets = true
requires_openai_auth = true
export CODEX_LB_API_KEY="sk-clb-..."
codex
Enable native WebSocket streaming:
export CODEX_LB_UPSTREAM_STREAM_TRANSPORT=websocket
Verify WebSocket transport:
RUST_LOG=debug codex exec "Reply with OK only."
CLI logs: connecting to websocket, successfully connected to websocket
codex-lb logs: WebSocket /backend-api/codex/responses
No fallback POST /backend-api/codex/responses
Migrate existing sessions from OpenAI provider:
find ~/.codex/sessions -name '*.jsonl' \
-exec sed -i '' 's/"model_provider":"openai"/"model_provider":"codex-lb"/g' {} +
sqlite3 ~/.codex/state_5.sqlite \
"UPDATE threads SET model_provider = 'codex-lb' WHERE model_provider = 'openai';"
OpenCode Important: Use the built-in openai provider with baseURL override. Custom providers with @ai-sdk/openai-compatible drop reasoning content.
Clear existing OpenAI credentials:
jq 'del(.openai)' ~/.local/share/opencode/auth.json > auth.json.tmp && mv auth.json.tmp ~/.local/share/opencode/auth.json
~/.config/opencode/opencode.json:
{
"$schema" : "https://opencode.ai/config.json" ,
"provider" : {
"openai" : {
"options" : {
"baseURL" : "http://127.0.0.1:2455/v1" ,
"apiKey" : "{env:CODEX_LB_API_KEY}"
} ,
"models" : {
"gpt-5.4" : {
"name" : "GPT-5.4" ,
"reasoning" : true ,
"options" : { "reasoningEffort" : "high" , "reasoningSummary" : "detailed" } ,
"limit" : { "context" : 1050000 , "output" : 128000 }
} ,
"gpt-5.3-codex" : {
"name" : "GPT-5.3 Codex" ,
"reasoning" : true ,
"options" : { "reasoningEffort" : "high" , "reasoningSummary" : "detailed" } ,
"limit" : { "context" : 272000 , "output" : 65536 }
}
}
}
} ,
"model" : "openai/gpt-5.3-codex"
}
export CODEX_LB_API_KEY="sk-clb-..."
opencode
OpenClaw ~/.openclaw/openclaw.json:
{
"agents" : {
"defaults" : {
"model" : { "primary" : "codex-lb/gpt-5.4" } ,
"models" : {
"codex-lb/gpt-5.4" : { "params" : { "cacheRetention" : "short" } } ,
"codex-lb/gpt-5.3-codex" : { "params" : { "cacheRetention" : "short" } }
}
}
} ,
"models" : {
"mode" : "merge" ,
"providers" : {
"codex-lb" : {
"baseUrl" : "http://127.0.0.1:2455/v1" ,
"apiKey" : "${CODEX_LB_API_KEY}" ,
"api" : "openai-responses" ,
"models" : [
{
"id" : "gpt-5.4" ,
"name" : "gpt-5.4 (codex-lb)" ,
"contextWindow" : 1050000 ,
"contextTokens" : 272000 ,
"maxTokens" : 4096 ,
"input" : [ "text" ] ,
"reasoning" : false } ,
{
"id" : "gpt-5.3-codex" ,
"name" : "gpt-5.3-codex (codex-lb)" ,
"contextWindow" : 400000 ,
"contextTokens" : 272000 ,
"maxTokens" : 4096 ,
"input" : [ "text" ] ,
"reasoning" : false }
]
}
}
}
}
export CODEX_LB_API_KEY="sk-clb-..."
OpenAI Python SDK from openai import OpenAI
client = OpenAI(
base_url="http://127.0.0.1:2455/v1" ,
api_key=os.environ["CODEX_LB_API_KEY" ],
)
response = client.chat.completions.create(
model="gpt-5.3-codex" ,
messages=[{"role" : "user" , "content" : "Hello!" }],
)
print (response.choices[0 ].message.content)
Any OpenAI-Compatible Client
Chat Completions API: http://127.0.0.1:2455/v1
Codex Backend API: http://127.0.0.1:2455/backend-api/codex
Pass API key as Authorization: Bearer sk-clb-... header if auth is enabled.
Usage Patterns
Multi-Account Load Balancing codex-lb automatically distributes requests across healthy accounts based on:
Account availability
Usage limits
Model availability per account
Add accounts in dashboard → Accounts → Add Account . Disable individual accounts temporarily without removing them.
Rate Limiting Configure per-API-key limits in dashboard → API Keys → Edit Key :
Max tokens: 100000
Window: 1 hour
Max cost: 5.00 USD
Window: 1 day
Allowed models: gpt-5.3-codex, gpt-5.4-mini
Usage Tracking Dashboard → Accounts shows per-account:
Total tokens used
Total cost (USD)
28-day usage trends
Model availability
Dashboard → API Keys shows per-key:
Requests made
Tokens consumed
Cost incurred
Rate limit status
WebSocket Streaming (Codex) codex-lb supports native WebSocket streaming for Codex CLI:
export CODEX_LB_UPSTREAM_STREAM_TRANSPORT=websocket
export CODEX_LB_UPSTREAM_STREAM_TRANSPORT=http
Reverse proxy setup — ensure your reverse proxy forwards WebSocket upgrades:
location / {
proxy_pass http://codex-lb:2455;
proxy_http_version 1.1;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
}
reverse_proxy localhost:2455
(Caddy handles WebSockets automatically)
Troubleshooting
Bootstrap token not working
API key rejected
Auth disabled: Set Authorization: Bearer dummy or any non-empty string. If remote request is rejected, enable API key auth in dashboard.Auth enabled: Create API key in dashboard → API Keys . Pass as Authorization: Bearer sk-clb-....Rate limit: Check dashboard → API Keys for limit status. Increase limits or wait for window reset.
WebSocket connection fails (Codex)
Verify transport: Run RUST_LOG=debug codex exec "test" and check logs for connecting to websocket.Reverse proxy: Ensure proxy forwards WebSocket upgrades (see nginx/Caddy examples above).Direct connection: Set CODEX_LB_UPSTREAM_WEBSOCKET_TRUST_ENV=false to bypass environment proxies.Fallback to HTTP: codex-lb automatically falls back. Check logs for POST /backend-api/codex/responses instead of WebSocket.
Account sync fails
Usage not tracking
Codex sessions not appearing after migration Run migration commands to update model_provider in session files and SQLite DB:
find ~/.codex/sessions -name '*.jsonl' \
-exec sed -i '' 's/"model_provider":"openai"/"model_provider":"codex-lb"/g' {} +
sqlite3 ~/.codex/state_5.sqlite \
"UPDATE threads SET model_provider = 'codex-lb' WHERE model_provider = 'openai';"
Dashboard won't load
High latency or timeout
Add more accounts: Distribute load across more ChatGPT accounts.Check account health: Dashboard → Accounts → disable slow or failing accounts.Increase timeout: Configure client timeout (e.g., OpenAI SDK timeout=120).
Advanced Configuration
Multi-Replica Setup For high availability, run multiple codex-lb replicas sharing the same encryption key:
SHARED_KEY=$(openssl rand -hex 32)
docker run -d --name codex-lb-1 \
-e CODEX_LB_ENCRYPTION_KEY=$SHARED_KEY \
-p 2455:2455 -p 1455:1455 \
-v codex-lb-data:/var/lib/codex-lb \
ghcr.io/soju06/codex-lb:latest
docker run -d --name codex-lb-2 \
-e CODEX_LB_ENCRYPTION_KEY=$SHARED_KEY \
-p 2456:2455 -p 1456:1455 \
-v codex-lb-data:/var/lib/codex-lb \
ghcr.io/soju06/codex-lb:latest
Put replicas behind a load balancer (nginx, HAProxy, etc.).
Custom Data Directory docker run -d --name codex-lb \
-e CODEX_LB_DATA_DIR=/custom/path \
-v /host/custom/path:/custom/path \
-p 2455:2455 -p 1455:1455 \
ghcr.io/soju06/codex-lb:latest
Kubernetes/Helm See project repository for Helm chart. Key points:
Share encryption key across pods via Secret
Use PersistentVolumeClaim for SQLite database
Configure Ingress for WebSocket support
Common Patterns
Development Team Usage Each developer gets an API key with daily cost limit:
client = OpenAI(
base_url="https://codex-lb.company.com/v1" ,
api_key=os.environ["DEV_A_API_KEY" ],
)
client = OpenAI(
base_url="https://codex-lb.company.com/v1" ,
api_key=os.environ["DEV_B_API_KEY" ],
)
Monitor usage in dashboard → API Keys .
CI/CD Integration Separate API key for CI with token limit:
- name: Run AI tests
env:
CODEX_LB_API_KEY: ${{ secrets.CI_CODEX_KEY }}
run: |
pytest tests/ai/
Model-Specific Routing Restrict expensive models to specific keys:
Production key: gpt-5.4, gpt-5.3-codex allowed, $50/dayDevelopment key: gpt-5.4-mini, gpt-5.1-codex-mini allowed, $10/day
Configure in dashboard → API Keys → Allowed Models .
This skill enables AI coding agents to help developers deploy, configure, and troubleshoot codex-lb for managing multiple ChatGPT/Codex accounts with load balancing, usage tracking, and rate limiting.
