qwen-code: Use AI Agents to Work on Code

Summary
Qwen Code is an AI coding agent for working with repositories through a terminal and other interfaces. It supports multiple model providers and can also be used from editors, desktop, web, chat, scripts, or SDKs.
At a glance
- Language
- TypeScript
- License
- Apache-2.0
- Stars
- 28.3k
- Forks
- 3.2k
- Added to OSRepos
- November 16, 2025
- Last analyzed
- October 3, 2026
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Overview
Qwen Code is a TypeScript coding agent that works with a project from the terminal and can also connect to editor, desktop, web, and chat interfaces. It helps developers delegate repository tasks such as understanding code, making changes, and running workflows to an AI agent.
It supports Qwen and other model APIs, as well as third-party providers and local models. It is a fit for developers who want to choose their model provider and workflow interface rather than use a single-model terminal tool.
Key Features
- Interact with an agent in a project directory using the
qwencommand. - Connect to Qwen, OpenAI, Anthropic, Gemini, third-party providers, or local models.
- Use agent capabilities including SubAgents, Agent Teams, Auto-Memory, Auto-Skills, and MCP.
- Integrate with VS Code, Zed, JetBrains, a desktop app, and an experimental web UI.
- Connect chat channels including Telegram, DingTalk, WeChat, and Feishu.
- Run non-interactively for scripts and CI/CD, or build integrations with TypeScript, Python, and Java SDKs.
Use Cases
- Developers exploring an unfamiliar repository can ask the agent to explain its layout and point out where to start.
- Individual contributors can delegate code changes and development workflows from the terminal or a supported editor.
- Teams that use different model providers can use one coding-agent framework with compatible APIs or local models.
- Automation engineers can invoke the agent from scripts, CI/CD, or custom applications through headless mode and SDKs.
- Developers who prefer chat or desktop workflows can access the agent without staying in a terminal session.
Project Facts
- Language: TypeScript
- License: Apache-2.0
- Stars: 28.3k
- Forks: 3.2k
- Topics: agentic, ai, ai-agent, ai-coding, cli, coding-agent, developer-tools, llm, mcp, qwen, terminal, typescript
- Archived: No
Getting Started
Install with npm, then launch the agent in a project directory:
npm install -g @qwen-code/qwen-code@latest
cd /path/to/your-project
qwen
The npm installation requires Node.js 22 or later. Run /auth in the session to configure a provider and API key. See the README and user documentation for installation options and configuration details.
Alternatives
- zero: Zero is a Go terminal agent focused on scriptable local sessions and explicit controls over side effects.
- DeepSeek-Reasonix: DeepSeek-Reasonix emphasizes prefix-cache stability and persistent, continuous autonomous operation.
- grok-build: Grok Build is a Rust agent with full-screen terminal and headless modes, plus web search for longer tasks.
- pi: Pi is a TypeScript agent toolkit with a unified provider API and an extensible design for custom workflows.
Considerations
- The npm installation requires Node.js 22 or later. Standalone installers and Homebrew are also listed in the README.
- Model-provider access and authentication need to be configured before use.
- The README labels the web UI and daemon mode as experimental.
- The project covers several interfaces and integration types, so users should consult the documentation for setup requirements specific to their chosen workflow.
Source repository
Open the original repository on GitHub.
18 counted GitHub visits
Related repositories
Similar repositories that may be relevant next.

OrcaReplay: Record and Replay AI Agent Runs
October 2, 2026
OrcaReplay records AI agent runs so developers can inspect what happened, replay interactions offline, and fork a run from a checkpoint onto another model. It is a TypeScript CLI for debugging and comparing agent behavior without modifying the agent.

openmake_llm: Coordinate AI Models, Agents, and Tools
October 1, 2026
OpenMake is a self-hosted AI workspace that coordinates chat models, agents, and tools in one place. It suits people who want multi-step AI workflows with local or open-weight models, while keeping infrastructure and model choices under their control.

zennotes: Manage Markdown Notes with Keyboard-First Tools
October 1, 2026
ZenNotes is a local-first Markdown notes app for people who prefer plain files, keyboard navigation, and Vim motions. It runs as an Electron desktop app or a self-hosted web app, with search, diagrams, CLI, and MCP integrations.

Kun: Local-First AI Agent Workspace
September 27, 2026
Kun is a local-first workspace for using AI agents across coding, writing, design, research, and automation. Its desktop GUI and terminal TUI share one runtime, keeping tasks and approvals connected.