Qwen Cline
ArchivedQwen AI Integration for Cline IDE Extension
Qwen Cline is a lightweight server built on top of qwen-api that exposes OpenAI-compatible endpoints (/v1/models and /v1/chat/completions). This allows the Cline VS Code extension to use Qwen AI models as its backend, providing real-time streaming AI assistance for coding tasks. Supports Docker deployment and configurable thinking/web search modes.
Features
OpenAI-Compatible API
Exposes /v1/models and /v1/chat/completions endpoints compatible with any OpenAI client.
Cline Integration
Seamless integration with the Cline VS Code extension for AI-powered coding assistance.
Docker Ready
Available as a Docker image (rosyihuddin/qwen-cline) for easy deployment anywhere.
Configurable Modes
Toggle thinking mode, web search, and web development mode via environment variables.
Documentation
Getting Started
Installation
git clone https://github.com/arosyihuddin/qwen-cline.git
cd qwen-cline
Using Docker (Recommended)
docker pull rosyihuddin/qwen-cline:latest
cp .env.example .env
# Edit .env with your QWEN_AUTH_TOKEN and QWEN_COOKIE
docker run -d -p 8000:8000 --env-file .env rosyihuddin/qwen-cline:latest
Manual Installation
pip install -e .
uvicorn src.server:app --host 0.0.0.0 --port 8000
Configuration
Create a .env file:
QWEN_AUTH_TOKEN=<your_auth_token>
QWEN_COOKIE=<your_cookie>
THINKING=true
THINKING_BUDGET=3000
WEB_SEARCH=false
WEB_DEVELOPMENT=false
Integration with Cline
1. Open Cline sidebar in VS Code
2. Select LM Studio as provider
3. Enter base URL: http://localhost:8000
4. Cline auto-detects the model
5. Start coding with AI assistance!