ARouter – drop-in OpenAI/Anthropic proxy that cuts cost and fails over
OpenAI SDK calls Claude through one proxy with conformance-tested wire translation.
Minimal, auditable Claude Code and Agent SDK router — Anthropic · OpenRouter · Gemini · OpenAI · Groq · Mistral · Ollama. Inspired by musistudio/llms + musistudio/claude-code-router (MIT).
Switch Claude Code to Codex, Gemini, or Ollama without rewriting code.
Developers using Claude Code, Anthropic Agent SDK users
OpenRouter · Anthropic Agent SDK · LiteLLM (multi-provider routing)
OpenAI SDK calls Claude through one proxy with conformance-tested wire translation.
Multi-model LLM router with semantic cache, but caching+fallback already exist (Anthropic, LangSmith, Unify).
LiteLLM already does this with more providers, more features, and way more maturity.
Clever protocol translation, but routing around Anthropic's ToS is a hard limit.
Runs as a single binary with embedded SQLite and zero-config start, acting as a transparent, provider-agnostic proxy that logs model, tokens, latency, cost and API key hashes while leaving full body capture opt-in. It also proxies streaming responses in real time and exposes stable JSON analytics endpoints — a practical, instrumentable way to get reproducible, audit-ready traces for real LLM traffic, though long-term value depends on how it handles provider edge-cases and SDK compatibility.
Swaps LLM backends for Claude Code workers while keeping your main session auth untouched.