Wren Coder is a model-agnostic command-line AI workflow tool forked from Qwen CLI Coder, which was itself a fork of Gemini CLI (Please refer to this document for more details). Currently supports OpenAI-compatible APIs, with plans to expand support to non-OpenAI-compatible models in the future.
Warning
Wren Coder may issue multiple API calls per cycle, resulting in higher token usage, similar to Claude Code. We’re actively working to enhance API efficiency and improve the overall developer experience.
- Model Agnostic - Currently supports OpenAI-compatible APIs with plans for broader model support
- Code Understanding & Editing - Query and edit large codebases beyond traditional context window limits
- Workflow Automation - Automate operational tasks like handling pull requests and complex rebases
- Enhanced Tool Support - Comprehensive tool ecosystem for file operations, shell commands, and web integration
Ensure you have Node.js version 20 or higher installed.
curl -qL https://www.npmjs.com/install.sh | shnpm install -g @wren-coder/wren-coder-cli
wren --versionThen run from anywhere:
wrenOr you can install it from source:
git clone https://github.com/wren-coder/wren-coder-cli.git
cd wren-coder
npm install
npm install -g .Wren Coder currently works with OpenAI-compatible APIs. Configure your API settings using environment variables or a .env file in your project root.
export OPENAI_API_KEY="your_api_key_here"
export OPENAI_BASE_URL="your_api_base_url_here" # e.g., https://api.openai.com/v1
export OPENAI_MODEL="your_model_name_here" # e.g., gpt-4, deepseek-coder, etc.Currently Supported (OpenAI-Compatible):
- OpenAI (GPT-4, GPT-3.5)
- DeepSeek (deepseek-coder, deepseek-chat)
- Anthropic (via OpenAI-compatible proxy)
- Local models (Ollama, vLLM, etc.)
- Any OpenAI-compatible API endpoint
Future Support Planned:
- Native Ollama integration
- Direct Anthropic API support
- Additional model providers and protocols
See our ROADMAP.md for detailed plans on expanding model support.
cd your-project/
wren
> Describe the main pieces of this system's architecture> Refactor this function to improve readability and performance> Analyze git commits from the last 7 days, grouped by feature and team member> Convert all images in this directory to PNG format> What are the core business logic components?
> What security mechanisms are in place?
> How does the data flow work?
> What parts of this module can be optimized?
> Help me refactor this class to follow better design patterns
> Add proper error handling and logging
> Generate comprehensive JSDoc comments for this function
> Write unit tests for this component
> Create API documentation
| Agent | Model | Accuracy |
|---|
wren-coder/
├── packages/ # Core packages
│ ├── cli/ # Command-line interface
│ ├── core/ # Core functionality
│ └── vscode-ide-companion/ # VS Code extension
├── docs/ # Documentation
├── examples/ # Example code
└── tests/ # Test files
For detailed development plans and upcoming features, see our ROADMAP.md.
See CONTRIBUTING.md to learn how to contribute to the project.
If you encounter issues, check the troubleshooting guide.
This project is a fork of Qwen CLI Coder, which was originally forked from Google Gemini CLI. We acknowledge and appreciate the excellent work of both the Gemini CLI team and the Qwen team. Our main contribution focuses on creating a model-agnostic solution with enhanced tool support and improved compatibility across different AI providers.