Qwen Code

Alibaba Qwen's open-source coding agent for the terminal, IDEs, desktop and chat apps, with memory, skills, subagents and support for any model provider.

28.9k stars, 3.3k forks TypeScript On GitHub since June 2025

Visit website View on GitHub How to run it

What is Qwen Code?

Qwen Code started from Google's Gemini CLI and has grown into its own agent. It adds automatic memory and skills, subagents and agent teams, and MCP support out of the box. It speaks the OpenAI, Anthropic, Gemini and Qwen APIs, so it works with third-party providers and local models served by Ollama or vLLM, and you can switch at runtime. Beyond the terminal it offers IDE plugins, a desktop app, a web UI, SDKs and chat integrations for Telegram, DingTalk, WeChat and Feishu.

Good fit if

  • You use Qwen models and want an agent developed alongside them.
  • Your team works in DingTalk, WeChat or Feishu and wants the agent there.
  • You want an Apache-licensed agent with no lock-in.

Look elsewhere if

  • You want an agent tuned for OpenAI's models: Codex CLI.
  • You want an agent inside VS Code with step approvals: Cline.

Before you adopt it

Qwen Code is Apache-2.0, with no paid parts. It changes quickly, with thousands of commits in the last three months.

Drafted with AI from the project's README and repository data, then checked against that data on 30 October 2026. Report a correction

Qwen Code health: is it still maintained?

80 of 100, actively developed

  • Activity
    3,601 commits in the last 90 days, the latest on 1 November 2026.
    30 / 30
  • Contributors
    22 people wrote the latest 100 commits; the most active wrote 55% of them.
    18 / 20
  • Releases
    10 releases in the last 12 months; the latest, v0.26.5, on 1 November 2026.
    18 / 20
  • Replies to issues
    Too few recent issues from outside the team to measure, so this part gets a neutral score.
    10 / 20
  • Security practices
    OpenSSF Scorecard 4.1 of 10.
    4 / 10

Read from GitHub on 1 November 2026. How the score works

Qwen Code license: is it open source?

Qwen Code uses Apache-2.0, an open-source license approved by the OSI.

  1. June 2025First published on GitHub.
  2. TodayApache-2.0.

How to run Qwen Code yourself

Docker
Dockerfile or compose file in the repository
Compose file
None in the repository
Setup effort
Not rated: no compose file to judge from
Kubernetes
Helm chart in the repository
Desktop and mobile
Builds for Linux, Windows, macOS, including ARM in GitHub releases
Interface languages
8 languages

Install instructions: qwenlm.github.io or the README on GitHub.

Alternatives to Qwen Code

  • CodewhaleOpen-source agent for the terminal written in Rust. Use any provider or model. Issues & PRs always welcome 82 health · MIT · 41.2k stars
  • RepomixRepomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for… 72 health · MIT · 29.1k stars
  • ArchonThe first open-source harness builder for AI coding. Make AI coding deterministic and repeatable. 68 health · MIT · 23.8k stars
  • Kilo CodeKilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular… 76 health · MIT · 27.8k stars
  • Continueopen-source coding agent 18 health · Apache-2.0 · 36.4k stars

All 27 projects in AI coding agents

Questions about Qwen Code

Is Qwen Code open source?

Yes. Qwen Code is published under Apache-2.0, an OSI-approved open-source license.

Is Qwen Code still maintained?

Its health score is 80 of 100 (actively developed). It had 3,601 commits in the last 90 days, the latest on 1 November 2026, and its latest release came out on 1 November 2026.

How do I run Qwen Code?

You can run it with Docker, on Kubernetes with the Helm chart in the repository, as an app for Linux, Windows, macOS, including ARM. The README on GitHub has the exact steps.

What are the alternatives to Qwen Code?

Close alternatives in the AI coding agents category include Codewhale, Repomix, Archon.