Agentic coding tool from Anthropic for terminal, IDE, desktop and browser that reads and edits code, runs commands and opens pull requests.

Qwen Code overview and key facts (October 2026)
Open source coding agent from China's Qwen team for terminal, editor, desktop and chat, with Qwen, third-party or local models.
What is Qwen Code?
Qwen Code is the open source AI coding agent from the Qwen team, which lists China as its location. It runs in the terminal, in editors, as a desktop app, in a browser and in chat apps, and works with Qwen models, other major APIs or local models.
Qwen Code offers auto-memory, auto-skills, subagents, agent teams and MCP. It has integrations for VS Code, Zed and JetBrains, a desktop app for macOS, Windows and Linux, an experimental web UI, SDKs and chat channels such as Telegram, DingTalk, WeChat and Feishu. A headless mode runs it in scripts and CI/CD.
After the free Qwen OAuth tier ended on April 15, 2026, models are accessed through the Alibaba Cloud Coding Plan, the usage-based Token Plan with endpoints in Beijing or Singapore, or any OpenAI-compatible, Anthropic or Gemini key. The repository is under Apache 2.0, had 28,193 stars and was updated on September 28, 2026.
Qwen Code AI features and use cases
- Explains and changes repositoriesStarted in a project folder, Qwen Code explains the structure, answers questions and makes changes on request. New team members find their way into unfamiliar code faster.
- Switches models at runtimeBecause it speaks the Qwen, OpenAI, Anthropic and Gemini APIs and local runtimes, teams can switch providers without changing tools. Cost and data rules decide which model handles which task.
- Runs in pipelines and chatHeadless mode executes prompts in scripts and CI/CD, and chat channels let people assign tasks from messaging apps. Routine work such as batch changes runs without an open terminal.
What sets Qwen Code apart
- Supports several major model APIs and local models, avoiding lock-in to one provider.
- Chat integrations for DingTalk, WeChat and Feishu serve teams in China.
- Apache 2.0 license with desktop, web and SDK interfaces.
Where Qwen Code is strongest
The Qwen team lists China as its location. Chat integrations with DingTalk, WeChat and Feishu and plans through Alibaba Cloud Beijing show its focus on the Chinese market.
Questions to ask before you buy Qwen Code
Where code goes depends on the provider you configure: Alibaba Cloud endpoints are in Beijing or Singapore, other providers follow their own terms. For EU companies, check data transfers carefully or use local models. The installer downloads from Alibaba Cloud storage, so review this with IT security.
Qwen Code reviews
No reviews yet. Be the first to share how your team uses it.
Every review shows its verification level. We read each one before it goes live. How we check reviews
Questions about Qwen Code
Is Qwen Code still free to use?
The tool is open source under Apache 2.0. The free Qwen OAuth model access was discontinued on April 15, 2026, so you need a paid plan, an API key or a local model.
Can we use it with non-Qwen models?
Yes. It supports OpenAI-compatible providers, Anthropic, Google Gemini, custom endpoints and local models through Ollama or vLLM.
Which editors are supported?
The README lists integrations for VS Code, Zed and JetBrains, plus a desktop app and a web UI.
Qwen Code update historyno updates yet
No changes recorded for Qwen Code yet.
Changes the vendor made and confirmed user reports, each checked against the vendor's own pages. We review every tool monthly.
Alternatives to Qwen Code
Tools in the same category (Terminal agents) with the most overlapping markets.
Coding agent from JetBrains for the IDE, terminal, GitHub Actions and GitLab CI, with bring-your-own-key for more than ten models.
Open source AI agent from Google for the terminal with Gemini models, Google Search grounding, file access, shell commands and MCP.
Open source terminal coding agent from Mistral AI, with Mistral models, other compatible providers or local models offline.



