qwen-code
An open-source AI coding agent that lives in your terminal.
What is qwen-code?
An open-source AI coding agent that lives in your terminal.
Overview of qwen-code
What it is
Qwen Code is an open-source AI coding agent that lives in your terminal, editor, desktop, browser, and chat.
Key features
- Agentic out of the box with Auto-Memory, Auto-Skills, SubAgents, Agent Teams, and MCP.
- Open-source framework and models (Qwen models) with no vendor lock-in.
- Multi-protocol support: OpenAI, Anthropic, Gemini, and Qwen APIs; any third-party provider or local model (Ollama/vLLM).
- Multiple interfaces: terminal, IDE plugins (VS Code, JetBrains, Zed), Desktop app, Web UI, SDKs, and chat integrations (Telegram, DingTalk, WeChat, Feishu).
- Daemon mode for multi-client shared agent sessions.
- Headless mode for scripts and CI/CD.
- Agent Arena for multi-model head-to-head comparison.
Use cases
- Explain a repository and show where to start.
- Automate coding tasks in scripts, CI/CD, or batch jobs.
- Use as a desktop automation agent with computer use.
- Integrate with chat platforms like Telegram, DingTalk, WeChat, or Feishu.
- Run as a long-lived daemon for browser, editor, SDK, and automation clients.
Getting started
bash curl -fsSL https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.sh | bash powershell irm https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.ps1 | iex bash npm install -g @qwen-code/qwen-code@latest bash brew install qwen-code bash cd /path/to/your-project qwen Inside the session, run /auth to configure your provider and API key.
License and pricing
Licensed under Apache-2.0. Open source and free to use.
Based on the project's public README and repository metadata.