qwenlm/qwen-code is an open-source, terminal-based AI coding agent that automates software engineering workflows. It supports multiple model protocols—including OpenAI, Anthropic, Gemini, and Qwen APIs—alongside local models via Ollama and vLLM.
Project overview
It ships with agentic workflows, sub-agents, and multi-platform support while allowing users to choose between remote APIs and locally hosted models without vendor lock-in.
Project type
AI Coding
Use cases
Coding & Development
Deployment
Refer to project documentation
License
Apache-2.0
Best for
Developers, AI engineers, and operations teams who prefer terminal, desktop GUI, or API interactions and need to automate coding workflows using their choice of remote or local models.
Key capabilities
Supports OpenAI, Anthropic, Gemini, and Qwen APIs, as well as third-party or local models via Ollama/vLLM.
Limitations and risks
The agent requires an external model provider or a locally hosted model to function. Users choosing remote APIs depend on those external services.
Getting started
Installation is rated as easy, supporting standalone curl or PowerShell scripts, or NPM global install. Users can launch the interactive terminal UI with a single 'qwen' command.