caozhiyuan/copilot-api

GitHub Copilot, OpenAI Codex, OpenCode Go, and third-party AI provider gateway with OpenAI and Anthropic API compatibility.

What it solves

Copilot API is a universal AI gateway that allows developers to use multiple AI providers (such as GitHub Copilot, DeepSeek, Kimi, and OpenRouter) through a single local endpoint. It solves the problem of fragmented API protocols by translating between OpenAI-compatible Chat Completions, OpenAI Responses, and Anthropic Messages formats, enabling a single server to power various AI coding agents and clients.

How it works

The gateway acts as a proxy that routes requests from clients to the appropriate AI provider. It supports three primary client-facing protocols: OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages. Depending on the provider's native capabilities, the gateway translates the request and response formats to ensure compatibility. For example, it can route GitHub Copilot traffic to its native Anthropic-style Messages API to preserve tool-heavy workflows.

Who it’s for

Developers using AI coding assistants like Claude Code, OpenCode, and Codex who want to consolidate their AI model access and switch between different providers without changing client configurations.

Highlights

  • Unified API Gateway: Supports OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages from one endpoint.
  • Multi-Provider Support: Integrates GitHub Copilot, a built-in Codex provider, and third-party providers like DeepSeek, Kimi, and DashScope.
  • Coding Agent Ready: Includes specialized setups and launchers for Claude Code, OpenCode, and Codex.
  • Desktop Application: Provides an Electron GUI for managing authentication, provider configuration, and monitoring token usage.
  • Streaming Support: Implements SSE streaming across all three client-facing protocols.

Related

  • Project
    ink1ing/anti-api

    A local protocol-compatibility and routing proxy that unifies multiple AI providers like GitHub Copilot, Codex, and Grok into a single OpenAI/Anthropic-compatible API.

  • Project
    heyhuynhgiabuu/proxypal

    A desktop app that bridges AI subscriptions like Claude, ChatGPT, and GitHub Copilot to any OpenAI-compatible coding tool via a local proxy.

  • Project
    icebear0828/codex-proxy

    A local proxy that converts Codex Desktop's API into OpenAI, Anthropic, and Gemini standard protocols to enable integration with any AI client.

  • Project
    romgX/openrelay

    A local AI quota aggregator and proxy that lets you use AI subscriptions from various providers (like Claude Pro or Cursor) across any AI tool or IDE.

  • Project
    duolahypercho/codex-router

    Codex Router is a community tool that lets the Codex desktop/CLI app use many external LLM providers (Anthropic, Kimi, DeepSeek, xAI/Grok, Gemini, Copilot, Ollama Cloud, etc.). It installs a background service, an optional Electron control‑center (tray/menu‑bar app with a macOS widget), and CLI helpers that securely store API keys or OAuth tokens. After a guided setup you can pick a “routed model” in Codex, and the router forwards requests to the chosen provider, optionally adding a Perplexity search side‑car. Installation is via a one‑click script (macOS/Linux/Windows) or a Homebrew formula (CLI‑only).