Claude Code is incredible. But you already pay for other AI subscriptions. Why not use your Gemini Advanced, ChatGPT Plus, Grok, or Kimi subscription with Claude Code's interface?
Claudish is the answer. It's a universal proxy that sits between Claude Code and any AI API, translating schemas bidirectionally and routing calls to the model you specify. No patches to Claude Code. No config files to hand-edit. Just claudish --model and you're using any model Claude Code supports.
Claude Code only supports Anthropic models. If you have a Gemini, ChatGPT, Grok, or Kimi subscription, you can't use it with Claude Code's interface. You're forced to choose between:
Claudish eliminates this choice. You use Claude Code's interface. You pay for whatever subscription you want. It just routes the calls.
Claudish doesn't hack Claude Code. It intercepts calls via a local proxy, translates schemas, and forwards to the target API. The translation is bidirectional and happens at runtime.
Claudish starts a proxy on port 3000. Claude Code sends all API calls to localhost:3000 instead of api.anthropic.com. Claudish captures these calls.
The schemas are converted in real-time:
<tool_use> → Target's JSON {function_call}{content: json} → Claude's XML <result>The target model executes the request natively. Claudish re-serializes the response to look exactly like Claude 3.5 Sonnet output. Claude Code never knows it's talking to a different model.
Claudish supports 15+ direct providers plus 580+ models via OpenRouter. Here's the breakdown:
| Provider | Direct API | Notes |
|---|---|---|
| Anthropic Max | Native passthrough | Use your existing Claude credits or Pro plan |
| Gemini Advanced | @gemini-3.1-pro-preview | Google's latest, 1M context |
| ChatGPT Plus | @gpt-5.4 | OpenAI's flagship |
| Kimi | @kimi-k2.5 / @kimi-for-coding | Oauth authentication |
| GLM / Zhipu | @glm-5 | Chinese LLM, 1M context |
| MiniMax | @MiniMax-M2.7 | Enterprise tier |
| Vertex AI | @gemini-3.1-pro-preview | Google Cloud managed |
| Z.AI | @glm-5 | 10% off with affiliate link |
| OllamaCloud | @qwen3-coder-next | Cloud-hosted local models |
| OpenRouter | @openai/gpt-5.4 | 580+ models, free tier available |
| Ollama (Local) | @llama3.2 | 100% offline, $0 cost |
Claudish isn't just a one-model proxy. You can route different models to different tasks within the same session:
claudish \ --model-opus google/gemini-3.1-pro-preview \ --model-sonnet openai/gpt-5.4 \ --model-haiku x-ai/grok-code-fast \ --model-subagent minimax/minimax-m2
This enables a multi-model mesh:
The orchestrator manages compute nodes, latency, and cost in real-time:
Some models (GLM 5, Kimi 2.5) don't support images. Claudish solves this with a Vision Proxy:
When Claude Code sends an image, Claudish intercepts it, calls a vision API to extract text/structure, and forwards a text description to the target model:
Source: Claude Code
{
"type": "image_url",
"url": "data:image..."
}
Claudish Proxy:
Extracting layout, text, and structure via Vision API...
Destination (Kimi 2.5 / GLM 5):
{
"type": "text",
"text": "UI shows a navigation bar with logo and menu items..."
}
This lets you use text-only models for tasks that require image understanding, without breaking Claude Code's image workflows.
Claude Code expects 200K context. Claudish remaps larger context windows to this expectation:
On supported models, this unlocks full 1M+ token windows via context remapping.
Claudish bypasses Claude's default pricing logic and intercepts token usage statistics to show exact API spend:
The orchestrator displays tokens/sec, latency, CPU/MEM usage, and network traffic for each compute node.
# Homebrew brew tap MadAppGang/tap && brew install claudish # npm (recommended) npm install -g claudish # Free tier claudish --free
Claudish runs as a CLI that intercepts Claude Code's calls. It starts a proxy on port 3000 and routes everything through it. No daemon, no systemd service, no manual configuration.
Claudish's unique value is the unified Claude Code interface across all providers. No other tool combines this level of integration.
Claudish is the most practical solution to the multi-model problem we've seen. It doesn't try to be clever — it takes a well-understood approach (proxy + schema translation) and applies it correctly to Claude Code's workflow.
808 stars, 432 commits, active development by MadAppGang (the team behind Magmux). MIT licensed. One npm install and you're live.
# Install npm install -g claudish # Use your Claude Max subscription (native passthrough) claudish --model claude-sonnet-4-6 # Use OpenRouter's free tier — real top models claudish --free # Use a specific provider claudish --model @gemini-3.1-pro-preview # Multi-model orchestration claudish \ --model-opus google/gemini-3.1-pro-preview \ --model-sonnet openai/gpt-5.4 \ --model-haiku x-ai/grok-code-fast
Repository: github.com/MadAppGang/claudish
Documentation: claudish.com/docs