Run any LLM inside Claude Code. A local auditable proxy for 7 providers
Switch Claude Code to Codex, Gemini, or Ollama without rewriting code.
A restful API designed to route user prompts to various AI model providers.
Free-tier failover across Gemini, Groq, Mistral beats single-provider rate limits.
Developers building AI applications on limited budgets
LiteLLM · Portkey · AI gateway services
Switch Claude Code to Codex, Gemini, or Ollama without rewriting code.
First gateway with native MCP server—connect Claude Code or Cursor in one command.
Free AI gateway with failover, but LiteLLM already aggregates providers with better maturity.
Reverse-engineers free Gemini API; smart quota rotation, but against Google's terms of service.
Multi-model LLM router with semantic cache, but caching+fallback already exist (Anthropic, LangSmith, Unify).
Zero-trust networking via zrok beats LiteLLM when your GPUs sit behind NAT.