Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

opencodex

opencodex• Pinned

opencodex: A lightweight local gateway for using chosen models with AI coding tools.

What problem it solves

AI coding tools often expect particular provider protocols, making it difficult to use the models and providers a user prefers. A local gateway can translate between supported client APIs and provider APIs while preserving capabilities such as streaming, tool calls, reasoning, and images.

Key features

  • Provider protocol translation — The gateway translates Responses, Chat Completions, and Anthropic Messages requests into the protocol used by the selected provider.

    Source: README, src

  • Broad provider and client support — Providers include Claude, Gemini, Grok, DeepSeek, Ollama, and OpenAI-compatible endpoints. Clients can connect through managed integrations or compatible base URLs.

    Source: README

  • Virtual model routing and combos — Configured models can be selected with provider/model syntax. Combos can provide failover or weighted round-robin behavior across providers.

    Source: README

  • Dashboard and request visibility — The web dashboard configures providers and models, manages accounts, and displays request activity with cache token counts.

    Source: README

  • Multiple operating modes — The proxy can run interactively, as a background service, or through an on-demand Codex shim. A desktop application also provides the proxy and dashboard in a native window.

    Source: README

Quick start

Copied verbatim from the project's README.

npm install -g --allow-scripts=bun @bitkyc08/opencodex   # Node 18+; the Bun runtime is bundled automatically
ocx start                         # proxy + dashboard on localhost:10100
codex -m "anthropic/claude-opus-5" "Explain this stack trace"
codex -m "google/gemini-3-pro" "Write unit tests for auth.ts"
codex -m "ollama/llama3" "Refactor this function"

Who it may suit

Inference: This may suit developers who want to choose models independently of the coding client they use. It may also suit teams operating local or self-hosted provider gateways.

Topics to discuss

  • Which provider protocols and client capabilities should receive the most testing attention?

  • How should failover and weighted round-robin behavior be configured for local development?

  • What configuration and observability improvements would make gateway operation easier to manage?

Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/lidge-jun/opencodex#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/lidge-jun/opencodex

Comments

…