Claude Code model router

Claude Code Open

Claude Code with any LLM provider (OpenRouter, Gemini, Kimi K2)

Install

Install
go install github.com/Davincible/claude-code-open@latest

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

From source
git clone https://github.com/Davincible/claude-code-open.git

From the README

πŸš€ Claude Code Open

*A universal LLM proxy that connects Claude Code to any language model provider*

Production-ready LLM proxy server that converts requests from various LLM providers to Anthropic's Claude API format. Built with Go for high performance and reliability.

As simple as CCO_API_KEY="" cco code and then selecting openrouter,qwen/qwen3-coder as model and voila

*Inspired by Claude Code Router but rebuilt from the ground up to actually work reliably.*

✨ Features

🌐 Multi-Provider Support
- OpenRouter - Multiple models from different providers
- OpenAI - Direct GPT model access
- Anthropic - Native Claude model support
- NVIDIA - Nemotron models via API
- Google Gemini - Gemini model family

⚑ Zero-Config Setup
- Run with just CCO_API_KEY environment variable
- No configuration file required to get started
- Smart defaults for all providers

πŸ”§ Advanced Configuration
- YAML Configuration with automatic defaults
- Model Whitelisting with pattern matching
- Dynamic Model Selection using comma notation
- API Key Protection for enhanced security

πŸ”„ Smart Request Handling
- Dynamic Request Transformation between formats
- Automatic Provider Detection and routing
- Streaming Support for all providers

πŸš€ Quick Start
πŸ’‘ Note: When installed with go install, the binary is named claude-code-open. Throughout this documentation, you can substitute cco with claude-code-open or create an alias as shown in the installation section.

πŸ“¦ Installation

πŸ“₯ Option 1: Install with Go (Recommended)

The easiest way to install is using Go's built-in installer:

πŸ”¨ Option 2: Build from Source

βš™οΈ Option 3: Install with Custom Binary Name

πŸ”‘ Quick Start with CCO_API_KEY

For the fastest setup, you can run without any configuration file using just the CCO_API_KEY environment…
Read the full README on GitHub

Details

Language
Go
Last updated
16 August 2025

FAQ

What is Claude Code Open?

Claude Code with any LLM provider (OpenRouter, Gemini, Kimi K2) It is a model router for Claude Code, from Davincible/claude-code-open on GitHub.

How do I install Claude Code Open?

Run go install github.com/Davincible/claude-code-open@latest, then follow the setup in the README.

Is Claude Code Open popular?

Davincible/claude-code-open has 70 GitHub stars and 13 forks, and is included in 1 curated Claude Code list. It was last updated on 16 August 2025.

More model routers & proxies

Cnb2api

92

dengyie/cnb2api

Turn CNB cloud-workspace in-network AI into production OpenAI & Anthropic (Claude Code) APIs. Zero deps, v5.2 self-healing HA, quota CLI.

Model routers & proxies57

Litellm Relay

113

LiteLLM-Labs/litellm-relay

Onboard AI tools in one step, and catch the rest. Relay sets up Claude Desktop, Claude Code, and Codex to run through your LiteLLM AI Gateway with zero dev setup and routes shadow AI (Notion AI, Perplexity, …) there too.

Model routers & proxies11

Dsh Permission Rules

134

PerryLink/dsh-permission-rules

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

Model routers & proxies

Anthropic Proxy Rs

94

m0n0x41d/anthropic-proxy-rs

A proxy server that intercepts Anthropic API requests and converts them to OpenAI-compatible format, enabling integration with dozens of inference providers such as OpenRouter, Together.ai, Novita AI, and other third-party API services. Primary use cases include Claude Code and other Claude Agent SDK-based tools.

Model routers & proxies36

Tokenbank

110

wink-run/tokenbank

Token Bank β€” the local LLM gateway that sits between your AI agents and every provider. Know where tokens go Β· Spend less with smart routing to Ollama, Groq, GitHub Models Β· Earn by sharing idle quota on a community P2P network. One-click onboarding for Cursor, Claude Code, Codex CLI, Gemini CLI β€” no agent changes. Full trace, seamless model swap

Model routers & proxies18

Ocgo

100

emanuelcasco/ocgo

OCGO Provides an Ollama-style CLI for running Claude Code through an OpenCode Go subscription via a local Anthropic-compatible proxy.

Model routers & proxies20

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