Repolode
Submit
QwenLM

QwenLM/qwen-code

An open-source AI coding agent that runs in your terminal, with companion desktop, web, editor, and chat interfaces.

Open-source alternative to:Claude Code

View on GitHubWebsite
Stars
28,592
Forks
3,231
Open issues
1,931
Last commit
4 hours ago

What is it?

Qwen Code is an AI coding agent you run from the command line inside a project directory. It can read and edit code, run commands, and answer questions about a repository, with support for subagents, persistent memory, skills, hooks, and MCP servers.

The project is not tied to a single model provider. It supports OpenAI, Anthropic, Gemini, and Qwen APIs, as well as third-party providers and local models served through Ollama or vLLM, and you can switch between them during a session.

Beyond the terminal, the same agent is available as a desktop app, a browser-based Web UI through `qwen serve`, IDE integrations for VS Code, Zed, and JetBrains, and chat channels such as Telegram, DingTalk, WeChat, and Feishu. It also offers headless mode for scripts and CI, plus TypeScript, Python, and Java SDKs.

Key features

  • 01Runs as an interactive agent in the terminal that reads and edits project code.
  • 02Supports OpenAI, Anthropic, Gemini, and Qwen APIs plus local models via Ollama or vLLM.
  • 03Supports subagents, agent teams, auto-memory, and reusable skills.
  • 04Connects to external tools through MCP servers.
  • 05Provides IDE plugins for VS Code, Zed, and JetBrains.
  • 06Offers headless mode and SDKs in TypeScript, Python, and Java for automation.

Use cases

  • Exploring an unfamiliar codebase and asking where to start.
  • Running coding tasks from scripts, CI/CD pipelines, or batch jobs in headless mode.
  • Using a local model through Ollama or vLLM while keeping code on your machine.
  • Delegating coding tasks from chat apps such as Telegram or Feishu.

Quick start

  1. 1

    Install via npm (requires Node.js 22+)

    npm install -g @qwen-code/qwen-code@latest
  2. 2

    Open a terminal in your project and start Qwen Code

    cd /path/to/your-project qwen
  3. 3

    Inside the session, run /auth to configure your provider and API key

Things to know

  • Requires configuring a model provider and API key, or a local model, before use.

Topics

#ai-agent#coding-agent#terminal#cli#llm#mcp#typescript#agentic#ai#ai-coding

FAQ

What is qwen-code?
An open-source AI coding agent that runs in your terminal, with companion desktop, web, editor, and chat interfaces. Qwen Code is an AI coding agent you run from the command line inside a project directory. It can read and edit code, run commands, and answer questions about a repository, with support for subagents, persistent memory, skills, hooks, and MCP servers.
Is qwen-code free to use? What license does it have?
qwen-code is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is qwen-code still maintained?
Actively maintained. The last commit to qwen-code was on Oct 20, 2026.
What can I use qwen-code for?
Exploring an unfamiliar codebase and asking where to start. Running coding tasks from scripts, CI/CD pipelines, or batch jobs in headless mode. Using a local model through Ollama or vLLM while keeping code on your machine. Delegating coding tasks from chat apps such as Telegram or Feishu.
How do I install qwen-code?
Install via npm (requires Node.js 22+): npm install -g @qwen-code/qwen-code@latest Open a terminal in your project and start Qwen Code: cd /path/to/your-project qwen Inside the session, run /auth to configure your provider and API key
Where can I get qwen-code?
The source code and installation instructions are on GitHub: https://github.com/QwenLM/qwen-code

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects