hotricenoodles/crosslink

一个门户。所有型号。零锁定。

OpenAI 与人类兼容的大型语言模型 API 网关

英文 |中文 |العربية

一个统一代理，具有真正的双向协议转换，已分类错误 故障切换、带有每个工具RBAC的MCP网关、可插拔的护栏以及内置 admin dashboard — 适用于 OpenAI、Anthropic、Azure、DeepSeek、Qwen、Ollama 及任何 兼容OpenAI的提供商。

入门指南 ·亮点 ·专题 ·架构 ·文档 ·贡献

---

为什么要CrossLink？

每个LLM提供商都有不同的API格式、认证机制和功能集。 为每个版本调整代码既繁琐又容易出错，而且会让你被锁定。

CrossLink 是你的应用与任何大型语言模型提供商之间的通用适配器：

• 一个端点 — 你的代码与单一 API 通信，格式为 OpenAI 或 Anthropic 格式
• 任何提供者 — 请求会被路由到 OpenAI、Anthropic、Azure、DeepSeek、Qwen， Ollama，或任何兼容 OpenAI 的服务
• 真正的双向转换 — OpenAI 之间的完整流式 SSE 转换， Anthropic，以及OpenAI响应API，包括工具使用和扩展思考
• 按分类判断韧性 — 故障切换不是盲重试。

---

Why CrossLink?

Every LLM provider has a different API format, auth mechanism, and feature set. Adapting your code for each one is tedious, error-prone, and locks you in.

CrossLink is a universal adapter between your application and any LLM provider:

• One endpoint — Your code talks to a single API in either OpenAI or Anthropic format
• Any provider — Requests are routed to OpenAI, Anthropic, Azure, DeepSeek, Qwen, Ollama, or any OpenAI-compatible service
• True bidirectional translation — Full streaming SSE conversion between OpenAI, Anthropic, and the OpenAI Responses API, including tool use and extended thinking
• Resilient by classification — Failover isn’t blind retry. Errors are classified as persistent (quota/billing — one strike, long cooldown) or transient (rate limit — threshold-based), so retries go where they can actually succeed
• Observable routing — Every response carries x-crosslink-fallback-* headers, and a routing-stats API shows configured-vs-actual traffic distribution so you can see drift

---

Highlights

What makes CrossLink different — each backed by code, not marketing.

• 🔁 Bidirectional streaming translation — OpenAI ↔ Anthropic ↔ Responses API, all three directions, via a real state machine (not request-level rewrites). Handles thinking blocks,