qwen-code
Qwen Code is an open-source AI coding agent from the Qwen team that reads a repository, explains it and does work from the terminal. Both the framework and the Qwen models are open-source and evolve together, and the README notes the project uses its own agent and models to file issues, submit PRs and review code.
It is agentic out of the box, with Auto-Memory, Auto-Skills, SubAgents, Agent Teams and MCP, so dynamic workflows need little setup. It is multi-protocol, speaking OpenAI, Anthropic, Gemini and Qwen APIs, including any third-party provider or a local model through Ollama or vLLM, switchable at runtime, so you are not locked to one vendor.
It runs beyond the terminal: a desktop app for macOS, Windows and Linux, an experimental web UI via qwen serve, IDE integrations for VS Code, Zed and JetBrains, SDKs, and chat integrations for Telegram, DingTalk, WeChat and Feishu. Install is a standalone script, npm or Homebrew; inside a session /auth sets the provider and key.
Features
Why choose it
Trade-offs
Maintenance check
- Last commit
- 2026-10-23
- Commits, last 90 days
- 100+
- Releases, last 90 days
- 30
- Latest release
- v0.26.0-nightly.20261023.5a0be33432 (2026-10-23)
- Open issues
- 2059
- Recent issues with at least one comment
- 5/5
Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.
Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.
Compatibility
Quick start
Use cases
Alternatives
Comments
No comments yet. Be the first!