Open Source · MIT License · v0.1.5

Claude Code with
any LLM you want.

Plug in GPT-4o, DeepSeek, Gemini, Llama, Mistral, Ollama, or any OpenAI-compatible model. All tools work. Zero lock-in.

terminal
~ npm install -g @aryanjsx/openclaude
added 70 packages in 4s

~ export CLAUDE_CODE_USE_OPENAI=1
~ export OPENAI_MODEL=gpt-4o

~ openclaude
OpenClaude v0.1.5 · model: gpt-4o · ready
>
200+
Compatible Models
15
Built-in Tools
786
Lines of Shim Code
0
Extra Dependencies

Everything Claude Code does, with any model

The full tool system, streaming, multi-step reasoning — all working through the model you choose.

>_

All 15 Tools

Bash, FileRead, FileWrite, FileEdit, Glob, Grep, WebFetch, WebSearch, Agent, MCP, LSP, NotebookEdit, Tasks, and more.

Real-Time Streaming

Token-by-token streaming output, just like the original. Watch your model think and act in real time.

🔗

Multi-Step Tool Chains

The model calls tools, gets results, reasons, and continues. Complex agentic workflows work out of the box.

👁

Vision Support

Pass images as base64 or URL to vision-capable models. Screenshots, diagrams, UI mockups — all supported.

/

Slash Commands

/commit, /review, /compact, /diff, /doctor — all the commands you know from Claude Code still work.

🧠

Sub-Agents & Memory

AgentTool spawns sub-agents using your provider. Persistent memory system keeps context across sessions.

Works with every major provider

Any model that speaks the OpenAI chat completions API. Cloud or local.

OpenAI

GPT-4o, GPT-4o-mini

DeepSeek

V3, R1

Gemini

via OpenRouter

🏰

Ollama

Local, free

Mistral

Large, Medium

Together AI

Llama, Qwen

Groq

Ultra-fast inference

Azure OpenAI

Enterprise

LM Studio

Local GUI

Any Compatible

OpenAI API format

Up and running in 60 seconds

Three steps. One command. Any model.

Install

One command to install globally via npm.

npm install -g @aryanjsx/openclaude

Configure

Set your provider and model with environment variables.

export CLAUDE_CODE_USE_OPENAI=1
export OPENAI_API_KEY=sk-...
export OPENAI_MODEL=gpt-4o

Run

Launch OpenClaude. That's it. Everything works.

openclaude

How the shim works

A thin translation layer. Claude Code doesn't know it's talking to a different model.

Claude Code Tool System
Anthropic SDK Interface (duck-typed)
openaiShim.ts — translates formats
OpenAI Chat Completions API
Any Compatible Model

Not all models are equal

A rough guide to what works best for agentic tool use.

Model Tool Calling Code Quality Speed
GPT-4o Excellent Excellent Fast
DeepSeek-V3 Great Great Fast
Gemini 2.0 Flash Great Good Very Fast
Llama 3.3 70B Good Good Medium
Mistral Large Good Good Fast
GPT-4o-mini Good Good Very Fast
Qwen 2.5 72B Good Good Medium
Smaller (<7B) Limited Limited Very Fast

Ready to try it?

Install in one command. Use any model. Ship faster.

$ npm install -g @aryanjsx/openclaude click to copy