silasxbt/anti-api

Turn Antigravity / codex / github copilot into Anthropic & Openai API compatible server. Usable with Claude Code / Xcode etc.

What it solves

Anti-API acts as a local proxy that allows users to use various AI provider accounts (like GitHub Copilot, ChatGPT Codex, and others) within clients that expect standard OpenAI or Anthropic API formats. It solves the problem of fragmentation by providing a unified interface and a smart routing system to manage multiple accounts and providers.

How it works

The project implements a protocol-compatibility layer that translates requests from OpenAI/Anthropic-style clients into provider-specific formats. It includes a smart routing system that handles flow routing for custom model IDs and account routing for provider-native IDs. To ensure reliability, it features cooldown-aware failover, which automatically rotates through available accounts when encountering quota limits (429 errors) or other transient failures.

Who it’s for

It is designed for developers and power users who have access to multiple AI services and want to consolidate them into a single API endpoint for their local tools or IDEs (such as Claude Code).

Highlights

  • Multi-Provider Support: Integrates with Antigravity, ChatGPT Codex, GitHub Copilot, Zed hosted models, Amazon Kiro, and xAI Grok.
  • Unified API: Compatible with both OpenAI and Anthropic API formats.
  • Smart Routing: Features automatic account rotation and failover to bypass quota limits.
  • Management Dashboard: Includes a local dashboard for monitoring quotas, configuring routing, and managing accounts.
  • Security Boundary: Separates the management API and dashboard (loopback only) from a token-gated public inference gateway.
  • Multimodal Capability: Supports validated text, image, and tool calling across compatible providers.

Related

  • Project
    labring/aiproxy

    A production-ready AI gateway that provides intelligent routing, protocol conversion, and multi-tenant management for multiple AI providers via an OpenAI-compatible API.

  • Project
    Mirrowel/LLM-API-Key-Proxy

    A self-hosted universal LLM API proxy that provides OpenAI and Anthropic compatible endpoints for multiple providers with built-in key rotation and failover.

  • Project
    tashfeenahmed/freellmapi

    FreeLLMAPI aggregates free tiers from 34 LLM providers into one OpenAI-compatible endpoint, offering smart routing, fallback, and per-key rate tracking, so you can use billions of free tokens without juggling multiple APIs.

  • Project
    theopenco/llmgateway

    LLM Gateway is an open‑source API layer that lets you call many LLM providers through a single OpenAI‑compatible endpoint, with built‑in key management, cost tracking, and performance monitoring. It can be used as a hosted SaaS or self‑hosted via Docker.