Back to directory

mimo2codex

mimo2codex is a local proxy that lets the latest OpenAI Codex CLI or desktop app talk to other large language models, with built-in support for Xiaomi MiMo and DeepSeek and a generic mechanism for any OpenAI-compatible or native Responses API provider.

mimo2codex

mimo2codex sits between Codex and an upstream model provider, translating Codex's Responses API to the provider's Chat Completions API on the fly and routing each request to the right provider based on the model field the client sends. It exists because some providers' official Codex integration only supports the older chat wire protocol, which newer Codex versions reject; mimo2codex lets Codex stay on its latest version while still reaching those providers.

It supports tool calling, web search, vision and reasoning, including MiMo's native web search and multi-turn reasoning content, and can switch the active Codex model from an admin web console that also shows the model catalog, chat logs and token statistics, backed by SQLite.

It can be run as a command-line tool, in Docker for shared team setups with per-user login and bring-your-own-key support, or as a background desktop app for Windows and macOS.

More in LLM gateways

See all 106
  • aihappey-ai

    github.com

    A stateless, multi-provider .NET AI gateway exposing normalized OpenAI- and Anthropic-compatible endpoints, managed agents and skills across a very large catalog of models.

  • Unified AI System

    happy520ai.github.io

    A self-hosted, protocol-first AI gateway and agent control plane for OpenAI, Anthropic, Gemini, MCP and A2A, turning a rough request into a structured, reviewable prompt before it runs.

  • Subroute

    github.com

    A local AI gateway and desktop control desk that gives coding tools one steady endpoint, so switching between AI subscriptions, API providers and local models doesn't mean reconfiguring every client.