Back to directory

Codex Assistant

A zero-dependency local proxy that lets the Codex CLI call DeepSeek, MiMo or other chat-completion models by translating between OpenAI's Responses API and the Chat Completions API, with a desktop UI for managing providers and keys.

Codex Assistant

Codex Assistant is a local proxy and desktop management tool that sits between the Codex coding agent and model providers such as DeepSeek and Xiaomi's MiMo. Codex speaks OpenAI's Responses API while these providers speak the Chat Completions API, so the proxy converts requests and streaming responses in both directions, including tool calls and thinking-mode output.

A Tauri and WebView2 desktop app lets a user add and test providers, encrypt stored API keys to the local machine, switch the active model, and export logs and configuration, without hand-editing config files. It also enforces inbound authentication, CSRF protection on the web UI, and SSRF checks on upstream URLs.

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.