litellm-claude-code
🥈SilverLiteLLM Claude Code Provider offers an OpenAI-compatible API interface for Claude Code. It enables developers to integrate Claude's capabilities into existing workflows using familiar OpenAI SDK patterns. Ideal for operations teams looking to automate code-related tasks, this provider supports Docker containers and connects to Claude agents.
2250Updated 2mo ago
Intermediate30min to implementautomation
Saves ~30 min per use
Quick InstallView Source
git clone https://github.com/cabinlab/litellm-claude-code.gitWorks with:
Claude
Overview
About This Skill
LiteLLM Claude Code Provider bridges Claude Agent SDK with the OpenAI API standard, allowing developers to integrate Claude into applications built for OpenAI without code changes. The service runs as a Docker container and supports OAuth authentication for Claude Pro/Max users or Anthropic API keys, with automatic token persistence across restarts. It exposes Claude Opus, Sonnet, and Haiku models through a standard `/v1` endpoint, making Claude available to tools like LangChain, Open WebUI, and Graphiti. Setup requires downloading docker-compose configuration, setting a master key, and providing a Claude OAuth token—no complex credential management needed. Operations teams and developers can now leverage Claude's capabilities in existing workflows using familiar OpenAI SDK patterns.
How to Use
Clone the repository or download docker-compose.yml and .env.example, set your LITELLM_MASTER_KEY in .env, generate a Claude OAuth token using `claude setup-token`, add the token to .env as CLAUDE_CODE_OAUTH_TOKEN, then run `docker-compose up -d`. The API will be available at http://localhost:4000/v1 with models named sonnet, opus, and haiku.
Use Cases
Integrate Claude into LangChain applications expecting OpenAI API keys
Use Claude with Open WebUI or other tools requiring OpenAI-compatible interfaces
Provide Claude access to teams via a centralized OpenAI-format API endpoint
Migrate from OpenAI to Claude without rewriting application code
Tags
Setup & Installation
Quick Install
No install command available. Check the GitHub repository for manual installation instructions.
Alternative Install (Git Clone)
git clone https://github.com/cabinlab/litellm-claude-codeRequirements
- Claude Code or compatible AI agent
- Works with: Claude
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
I'm integrating LiteLLM Claude Code Provider into my [COMPANY]'s [INDUSTRY] workflow. I need to automate [SPECIFIC CODE TASK] using Docker containers. Provide me with a step-by-step guide and sample code snippets for this integration.
Example Output
## Integration Guide for LiteLLM Claude Code Provider
### Step 1: Set Up Docker Container
```bash
# Pull the LiteLLM Docker image
docker pull litellm/litellm
# Run the container with Claude Code Provider
docker run -p 8000:8000 litellm/litellm --model claude-code
```
### Step 2: Install OpenAI SDK
```bash
pip install openai
```
### Step 3: Configure API Key
```python
import os
os.environ['OPENAI_API_KEY'] = 'your-api-key'
```
### Step 4: Make API Requests
```python
from openai import OpenAI
client = OpenAI(api_key=os.environ['OPENAI_API_KEY'])
response = client.chat.completions.create(
model='claude-code',
messages=[{'role': 'user', 'content': 'Write a Python function to analyze sales data.'}]
)
print(response.choices[0].message.content)
```
### Step 5: Handle Responses
```python
# Example response handling
if response.choices[0].finish_reason == 'stop':
print('Task completed successfully.')
else:
print('Task encountered an error.')
```Apply to these tools
Browse all toolsLiteLLM
Single API for 100+ LLM providers
OpenAI
Pioneering accessible, high-performance AI models
Claude
AI assistant built for thoughtful, nuanced conversation
Microsoft Teams
Get more done every day with Microsoft Teams – powered by AI
Respell
Agentic AI Workflow platform
Notion
Connected workspace for docs, wikis, and projects
Compatible MCP servers
Browse all MCP servers
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan