Claude Code model router

Lupin

Run Claude Code on any LLM provider without losing your setup, local-first proxy with verified profiles, OAuth device-flow login, failover, content-aware routing and an honest per-model compatibility doctor

Install

Install
npm install -g lupin-code

Found in the project README. Check it for setup steps after installing.

From source
git clone https://github.com/Fanfulla/Lupin.git

From the README

⠀⠀⠀⠀⠀⠀⠀⠀⣀⣠⣴⣶⣾⣿⣿⣧⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⣀⣤⣶⣿⣿⣿⣿⣿⣿⣿⣿⣿⣧⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⣠⣴⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣧⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⢾⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣷⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠻⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣦⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠹⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⡿⠿⠗⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠘⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣦⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠹⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣷⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⢀⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⣰⣿⡿⢿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠐⠛⠁⠀⠀⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣶⣤⣀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⢸⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣷⣄⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠈⠛⢉⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣷⣶⣶⣦⣤⣤⣀⣀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠐⠋⠁⠀⢹⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣶⣄⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠛⠛⠛⠉⠉⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣷

Lupin

Claude Code, on any model.
The gentleman router: it borrows the Claude Code harness and lends it to other models.

Your whole setup lives in Claude Code, not in the model: MCP servers, skills, CLAUDE.md, hooks, memories, plugins. But Claude Code speaks one protocol, the Anthropic Messages API, so trying another model means changing tool and starting over.

Lupin changes the model. Nothing else moves.

Start here

Prerequisites

Lupin supports Windows, macOS and Linux. The proxy binds only to
127.0.0.1. Prompts and responses are never persisted.

Fastest path

With the Rust sidecar on the PATH (next section) that second command is the
guided add-provider screen: masked key input, a real 1-token verification,
OAuth with browser polling, local runtimes with live model discovery. Without
the sidecar, bare lupin starts the setup daemon and prints the authenticated
curl calls that list the providers and verify your key: the first verified
provider persists the config. Either way, nothing is saved before a
verification succeeds, and then:

That command starts Claude Code with its API traffic pointed at…
Read the full README on GitHub

Details

Repository
Fanfulla/Lupin
Language
TypeScript
License
Apache-2.0
Last updated
1 September 2026
Topics
anthropicchatgptclaude-codeclideepseekdeveloper-toolsgeminikimillmllm-routeroauthollama

FAQ

What is Lupin?

Run Claude Code on any LLM provider without losing your setup, local-first proxy with verified profiles, OAuth device-flow login, failover, content-aware routing and an honest per-model compatibility doctor It is a model router for Claude Code, from Fanfulla/Lupin on GitHub.

How do I install Lupin?

Run npm install -g lupin-code, then follow the setup in the README.

Is Lupin popular?

Fanfulla/Lupin has 34 GitHub stars and 5 forks. It was last updated on 1 September 2026.

More model routers & proxies

Claude Code Gemini Proxy

36

kele527/claude_code_gemini_proxy

这是一个无缝桥接 Anthropic Messages API 与 Google Gemini API的代理工具,它能够实时地将来自客户端(如 Claude Code)的 Anthropic API 格式请求,转换为 Gemini 模型所需的格式,并将 Gemini 的响应再转换回 Anthropic 格式。 适用于没有claude api,但是又想用claude code的用户,用gemini2.5pro的api来替代。

Model routers & proxies

Problem Solver Skill

36

cathrynlavery/problem-solver-skill

Claude Code skill for systematic problem diagnosis using progressive disclosure — 55-line router + 7 on-demand framework references

Model routers & proxies

Delegate Router

33

pvjbuilds/delegate-router

Claude Code and Codex CLI skill: an LLM router that delegates bulk, already-decided coding tasks to another model you already pay for (GPT via Codex, Gemini via agy, a Claude Opus subagent), on another subscription first. Benchmark-checked routes, cost per task measured on a bench, cross-model review. The host verifies every diff.

Model routers & proxies

LocalCodeCli

33

Corporationakht/LocalCodeCli

A powerful local proxy for Claude Code CLI and Codex CLI supporting NVIDIA NIM, Google,Gemini, DeepSeek, and local Ollama models. Use claude code and codex for free in the terminal, VSCode extension, and discord like OpenClaw (voice supported)

Model routers & proxies

Opencode Configs

30

jesseoue/opencode-configs

Self-healing, config-as-code stack for the OpenCode AI coding agent — one key, 17 curated OpenRouter frontier models (GLM/DeepSeek/Gemini/Qwen/Kimi), multi-agent teams, cost guards, telemetry off. Claude Code / Cursor alternative on your terminal.

Model routers & proxies17

Helm API

31

EasyMetaAu/helm-api

Self-hosted LLM gateway — route OpenAI/Anthropic/Gemini traffic by config, not code. Fallback, protocol translation, telemetry.

Model routers & proxies

Browse the most popular Claude Code mods, all model routers & proxies, or the skills and MCP server directories.