Codex LB Enhanced alternatives

Codex LB Enhanced (aafqaq/codex-lb-enhanced): Codex LB Enhanced is a self-hosted gateway that pools several upstream accounts behind Codex-compatible and OpenAI-compatible endpoints, with failover, session recovery, quota headers, and diagnostics. See its 4 use cases.

Similar repos

1. Reuse Before Build Ai-Eastern/reuse-before-build · Python
   reuse-before-build is an Agent Skill that makes coding agents search existing code, tests, and libraries before writing new ones, then decide to Take, Borrow, or Build. Developers and engineering leads who use Claude Code, Codex, or another Agent Skills compatible coding agent and want fewer duplicate helpers, redundant tests, and unvetted library picks.
   3 use cases, for example Add retry logic without duplicating existing helpers
2. Aibuildai LLM Posttrain Agent aibuildai-inc/aibuildai-llm-posttrain-agent · Python · 110 stars
   A source-code release of a recursive self-improving agent that designs, runs, and iterates on post-training experiments for LLMs. ML engineers and small teams with a Linux GPU host who want an agent to post-train a model against their own task and score.
   4 use cases, for example Post-train a base model on a math task overnight
3. FlowX AIpRoBuilder/FlowX · Python · 182 stars
   FlowX is an open-source MCP server and Python SDK that turns plain-language process descriptions into stored, runnable AI agent workflows. Developers and agent builders who want an AI agent to create, run, and refine repeatable workflows on their own machine.
   3 use cases, for example Build a support ticket workflow from a chat request
4. Codex Guard Akimiya-z/codex-guard · JavaScript · 133 stars
   A GitHub Action and CLI that checks AI-generated pull requests for TODO leftovers, leaked secrets, sloppy commit subjects and failing CI before they reach main. Engineering teams and maintainers who receive pull requests from AI coding agents and want automatic checks before human review.
   5 use cases, for example Gate AI-generated PRs before they merge to main
5. Kyb alex09x/kyb · Rust
   KYB is a git-backed, searchable shared memory and incident tracker that AI agent fleets can use through a CLI, HTTP API and MCP server. Engineers and ops teams running several AI coding agents across machines who need them to share infrastructure facts, incident history and task state.
   4 use cases, for example Give every agent one shared record of your infrastructure
6. Review Skills amElnagdy/review-skills · JavaScript · 155 stars
   A GitHub, GitLab, and Azure DevOps review tool where two AI models debate a pull request, one review with inline comments is posted from your own account, and a babysitter works the review rounds. Developers and teams who want a second model to check pull requests before merge and want an agent to handle the follow-up review rounds.
   4 use cases, for example Get a two-model review on a GitHub pull request
7. Heimdall ArihantDeva/heimdall · JavaScript · 137 stars
   Heimdall is a local, CPU-first memory daemon that indexes the code and notes across your repositories so AI coding agents can search past work with verified, ranked results. Indie developers and engineers with many side projects who want their AI coding agent to reuse work they already built instead of rebuilding it.
   4 use cases, for example Find a solution you already built in another repo
8. Brew Ping banmu123/BrewPing · Swift · 100 stars
   BrewPing is a local-network remote control that lets you monitor, steer, and approve tasks from coding agents already running on your own Mac or Windows computer, from an iPhone, Apple Watch, or Android phone. Developers who already run CLI coding agents on a Mac or Windows machine and want to watch or approve their work from a phone or watch while away from the desk.
   4 use cases, for example Approve risky agent commands from your iPhone

Best AI repos for Software and DevOps · All use cases

Questions

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer