No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Soju06 · Codex Skill · ★ 3.2k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is codex-lb safe to install? View the security audit →
codex-lb Load balancer for ChatGPT accounts. Pool multiple accounts, track usage, manage API keys, view everything in a dashboard. More screenshots Features Account PoolingLoad balance across multiple ChatGPT accounts Usage TrackingPer-account tokens, cost, 28-day trends API KeysPer-key rate limits by token, cost, window, model Dashboard AuthPassword + optional TOTP OpenAI-compatibleCodex CLI, OpenCode, any OpenAI client Auto Model SyncAvailable models fetched from upstream Quick Start bash Docker (recommended) docker volume creat
| Stars | 3,210 |
| Forks | 481 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 70.3396074074806/100 |
| Open Issues | 203 |
| Last Updated | 2026-09-21 |
| Created | 2026-01-07 |
| Platforms | codex, python |
| Est. Tokens | ~22k |
Looking for a codex-lb alternative? If you're comparing codex-lb with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
👻 Proxy API gateway for Kiro IDE & CLI (Amazon Q Developer / AWS CodeWhisperer). Use free Claude models with
Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across
Memory library for building stateful agents
Self-hosted AI gateway for multi-channel, multi-credential setups — API keys and subscription accounts, schedu
⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & e
AI observability platform for production LLM and agent systems.
Explore other popular codex skill tools:
codex-lb is Codex/ChatGPT multiple account load balancer & proxy with usage tracking, dashboard, and OpenCode-compatible endpoints. It is categorized as a Codex Skill with 3.2k GitHub stars.
codex-lb is primarily written in Python. It covers topics such as api-proxy, chatgpt, codex.
You can find installation instructions and usage details in the codex-lb GitHub repository at github.com/Soju06/codex-lb. The project has 3.2k stars and 481 forks, indicating an active community.
codex-lb is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to codex-lb on Agent Skills Hub include kiro-gateway, agent-sessions, honcho. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: