AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
LLM Infra/
codex-pooler
codex-pooler logo

codex-pooler

Active·★ 233·NOASSERTION·Updated 2026-10-22

Codex Pooler is a self-hosted gateway designed to aggregate and share Codex account capacity across various agents, tools, and teams. It routes requests intelligently based on account availability, model support, and session state, providing stable API keys and a unified management dashboard for operators.

codex-pooler sits in the LLM Infra category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward One stable API key for multiple Codex accounts and dynamic capacity pooling.. A representative use case is Centralized management and distribution of Codex API access for development teams.. The listed license is NOASSERTION. GitHub stars are currently 233. Relevant tags include API Gateway, LLM Proxy.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#API Gateway#LLM Proxy#Load Balancing#Session Management#API Key Management#Self-hosting#Elixir#OpenAI API Compatibility
$ Install
$ git clone https://github.com/icoretech/codex-pooler.git && cd codex-pooler && scripts/self-host/generate-env.sh && docker compose pull && docker compose up -d
↗ Visit site★ GitHub
01

Features

01One stable API key for multiple Codex accounts and dynamic capacity pooling.
02Intelligent request routing based on model support, limits, and session continuity.
03Compatibility with both Codex backend and OpenAI-style SDK clients.
04Comprehensive operator dashboard for account, key, and policy management with privacy-focused observability.
05Self-hostable with Docker Compose or Kubernetes for fault-tolerant, scalable deployment.
02

Why choose it

+One stable API key for multiple Codex accounts and dynamic capacity pooling.
+Intelligent request routing based on model support, limits, and session continuity.
+Centralized management and distribution of Codex API access for development teams.
+Supports 7 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Compatibility

OpenAI API
Compatibility
Verified via docs
Codex Backend
Compatibility
Verified via docs
Python
SDK
Verified via docs
Node.js
SDK
Verified via docs
Docker Compose
Deployment
Verified via docs
Kubernetes
Deployment
Verified via docs
05

Quick start

1
$ git clone https://github.com/icoretech/codex-pooler.git
2
$ cd codex-pooler
3
$ scripts/self-host/generate-env.sh
4
$ docker compose pull
5
$ docker compose up -d
06

Use cases

↳Centralized management and distribution of Codex API access for development teams.
↳Deploying LLM agents that require stable API keys and benefit from pooled backend capacity.
↳Integrating with various AI development tools (e.g., Aider, Continue, Hermes Agent) through a unified OpenAI-compatible endpoint.
↳Operators needing a single dashboard for monitoring usage, audit logs, and account health across multiple Codex subscriptions without exposing raw secrets.
07

Alternatives

⚡Top VS:
VSfreellmpool★129→VSconduit★235→VSllmtrim★255→VSmcp-compress-router★21→
freellmpool logo
freellmpool★ 129
Free LLM API pool: 19 LLM providers cataloged, 235 routes, 355 cataloged chat models, keyless start when available.
VSCompare→
conduit logo
conduit★ 235
Local MCP gateway that cuts your agent's tool-token overhead ~90%. Every MCP server's tools collapse to 3 meta-tools the agent searches on demand. Measured: 97% less per request, same results. Keys in your OS keychain, no cloud.
VSCompare→
llmtrim logo
llmtrim★ 255
Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift).
VSCompare→
mcp-compress-router logo
mcp-compress-router★ 21
Compress all connected MCP into a single router MCP and save up to 99% on tokens
VSCompare→
bifrost logo
bifrost★ 9.0k
Fastest LLM gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
VSCompare→
harnessrouter logo
harnessrouter★ 3.2k
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
VSCompare→
tunnel-client logo
tunnel-client★ 589
Customer-run client for Secure MCP Tunnel: connect private or localhost MCP servers to ChatGPT, Codex, the Responses API, and AgentKit without exposing them to the public internet.
VSCompare→
emisar logo
emisar★ 331
An MCP that lets AI tools securely connect to your infrastructure, write IaaS code, debug issues, and assist during incidents - without risking production stability. Built for security teams to approve and infrastructure teams to experience like magic.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases07Alternatives
icoretech /
codex-pooler
↗

🤖 Pool and route Codex accounts behind one Gateway

233
Last commit1d ago
StatusActive
CategoryLLM Infra
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.