qwen-code
An open-source AI coding agent that lives in your terminal.
qwen-code is an open-source AI coding agent developed by QwenLM that operates directly in your terminal to assist with development tasks. It supports multiple AI providers including OpenAI, Anthropic, Gemini, and Qwen, offering dynamic agentic workflows with features like auto-memory, sub-agents, and MCP integration. Developers can use it interactively via terminal UI, headless mode for automation, through IDE plugins, or as a daemon service.
Key Features
Use Cases
- 01Interactive code development and debugging within terminal sessions using natural language commands
- 02Automated code review, batch processing, and continuous integration workflows in headless mode
- 03Multi-model comparison via Agent Arena to evaluate different AI models on identical coding tasks
- 04Building coding assistant bots for team collaboration platforms like Telegram or DingTalk
- 05Embedding AI coding capabilities into custom applications through TypeScript, Python, or Java SDKs
- 06Running shared agent sessions for team development via daemon mode with multiple concurrent clients
Related Agents
View moreunsloth
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
codegraph
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
claude-code-best-practice
from vibe coding to agentic engineering - practice makes claude perfect
system_prompts_leaks
Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.
qwen-code — FAQ
What is qwen-code?+
qwen-code is an open-source AI coding agent that runs in your terminal and assists with software development tasks. It supports multiple AI providers and offers agentic workflows with features like sub-agents, auto-memory, and MCP integration.
How do I install qwen-code?+
On Linux or macOS, run the installation script with curl. On Windows, use PowerShell with irm. Alternatively, install via npm (requires Node.js 22+) or Homebrew. Restart your terminal after installation.
Do I need an API key to use qwen-code?+
Yes, after installation you need to configure authentication using the /auth command to set up your AI provider and API key. The agent supports OpenAI, Anthropic, Gemini, Qwen, and local models.
Which AI clients and IDEs work with qwen-code?+
qwen-code provides official plugins for VS Code, JetBrains IDEs, and Zed editor. It also offers a standalone desktop app for macOS, Windows, and Linux, plus SDK integration for custom clients.
Is qwen-code free and open-source?+
Yes, qwen-code is fully open-source with both the framework and Qwen models available under open licenses. API costs depend on which third-party provider you configure (OpenAI, Anthropic, etc.) or you can use free local models.
Can qwen-code run in CI/CD pipelines?+
Yes, qwen-code supports headless mode via the -p flag for scripting, batch processing, and automated workflows. This makes it suitable for continuous integration and deployment pipelines without requiring a UI.
How do I install qwen-code?+
Open the source repository on GitHub and follow its README. qwen-code is a agent — MCP Agents Market links you directly to the official repo.
Is qwen-code free?+
qwen-code is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.